WO2001046946A1 - Hands-free, voice-operated remote control transmitter - Google Patents
Hands-free, voice-operated remote control transmitter Download PDFInfo
- Publication number
- WO2001046946A1 WO2001046946A1 PCT/US2000/035107 US0035107W WO0146946A1 WO 2001046946 A1 WO2001046946 A1 WO 2001046946A1 US 0035107 W US0035107 W US 0035107W WO 0146946 A1 WO0146946 A1 WO 0146946A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- circuit
- recognition
- speech recognition
- mode
- voice
- Prior art date
Links
- 230000004913 activation Effects 0.000 claims abstract description 161
- 230000006870 function Effects 0.000 claims description 39
- 230000001419 dependent effect Effects 0.000 claims description 38
- 230000005236 sound signal Effects 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 21
- 230000008878 coupling Effects 0.000 claims 1
- 238000010168 coupling process Methods 0.000 claims 1
- 238000005859 coupling reaction Methods 0.000 claims 1
- 230000004044 response Effects 0.000 abstract description 37
- 238000000034 method Methods 0.000 description 73
- 230000008569 process Effects 0.000 description 68
- 230000008859 change Effects 0.000 description 40
- 238000012545 processing Methods 0.000 description 33
- 230000003321 amplification Effects 0.000 description 28
- 238000003199 nucleic acid amplification method Methods 0.000 description 28
- 238000004422 calculation algorithm Methods 0.000 description 26
- 238000010586 diagram Methods 0.000 description 20
- 230000000007 visual effect Effects 0.000 description 18
- 230000000994 depressogenic effect Effects 0.000 description 15
- 230000007704 transition Effects 0.000 description 15
- 238000003909 pattern recognition Methods 0.000 description 14
- 230000015572 biosynthetic process Effects 0.000 description 11
- 238000005286 illumination Methods 0.000 description 11
- 238000003786 synthesis reaction Methods 0.000 description 11
- 238000012549 training Methods 0.000 description 11
- 230000000881 depressing effect Effects 0.000 description 10
- 230000035945 sensitivity Effects 0.000 description 10
- 230000001953 sensory effect Effects 0.000 description 8
- 239000003990 capacitor Substances 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000012163 sequencing technique Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 239000004020 conductor Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 239000003550 marker Substances 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 230000008054 signal transmission Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000009849 deactivation Effects 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000004593 Epoxy Substances 0.000 description 1
- 101000794213 Homo sapiens Thymus-specific serine protease Proteins 0.000 description 1
- AZFKQCNGMSSWDS-UHFFFAOYSA-N MCPA-thioethyl Chemical compound CCSC(=O)COC1=CC=C(Cl)C=C1C AZFKQCNGMSSWDS-UHFFFAOYSA-N 0.000 description 1
- 102100030138 Thymus-specific serine protease Human genes 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000002730 additional effect Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000003467 diminishing effect Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C2201/00—Transmission systems of control signals via wireless link
- G08C2201/30—User interface
- G08C2201/31—Voice input
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/228—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context
Definitions
- This mvention relates to devices for remotely controlling electronic equipment, and more particularly, to a wireless, user-programmable, voice-activated and voice-operated remote control system for controlling appliances.
- appliances for example, electronic appliances, such as, televisions, NCRs, digital satellite systems, audio systems, and related accessories, have been remotely controlled by hand-held transmitters used to generate signals to receivers incorporated into the electronics of the remotely controlled appliances.
- Signals for such appliances correspond to control commands, such as channel selection/tuning, power on/off, audio volume adjustment, and muting controls, typically generated by the user by depressing buttons on a remote control transmitter keypad.
- control commands such as channel selection/tuning, power on/off, audio volume adjustment, and muting controls
- Such remote control transmitters are generally designed to be sufficiently small to be hand-held during operation.
- the small size and mobility often contribute to misplacement or loss of the transmitter.
- hand-held remote controls may not provide sufficient access to the command controls of the remotely controlled appliances.
- an interruption in the activity may be required to operate the hand-held remote control, causing inconvenience to the operator and potentially having an adverse effect on productivity.
- U.S. Pat. No. 5,226,090 further discloses a voice-operated remote control system which contains a detector for detecting whether a voice command is received or not. A detected signal from the detector is applied to a power supply circuit. When there is no voice command received as detected by the detector, the power supply control circuit cuts off electric energy supplied to a speech recognition circuit.
- the voice command detector circuit is implemented by a detecting program stored in the ROM in a controller.
- the detecting program determines whether the talk switch has been depressed.
- the transmitter operates depending on whether the talk switch has been depressed. If the talk switch has been depressed, the transmitter is enabled to remote control signals. Once the talk switch is released, the transmitter is kept in a low power consumption mode, waiting for voice commands to be applied.
- the means for generating and transmitting a remote control signal based on the recognized spoken voice command is not hands-free, requiring the manual intervention of pressing a talk switch to accomplish these functions.
- U.S. Patent No. 5,852,804 discloses a system for controlling several external appliances connected to a speech recognition system.
- the system disclosed in the '804 patent requires physical interconnections between the control system and the appliance which makes it difficult for a user to add additional appliances or change controlled appliances.
- U.S. Patent No. 5,878,394 discloses asystem which includes connections to a remote control network for transmitting infrared codes and a graphical user interface on a personal computer (PC).
- PC personal computer
- a user In addition to the inconvenience of establishing the remote control network, a user must have access to a PC and desire to make the PC available for such control functions.
- the system disclosed in the '394 patent has only limited utility for consumers who have access to a PC or can afford the expense of a PC and thus excludes a significant portion of consumers who may otherwise desire to add speech recognition control to their electronic appliances if an inexpensive alternative is available.
- U.S. Patent No.5,774,859 discloses a subscriber information system with a speech interface, similar to the system disclosed in U.S. Patent No.
- Patent No. 5,852,804 discloses a system, where one speech command may be defined which is capable of manipulation of more than one connected appliance.
- this system requires that each controlled appliance be physically connected to the system and that the controlled appliance be manually manipulated during setup for each function to be executed upon recognition of the speech command.
- time delays of variable lengths may be inserted within the series of control functions to accommodate the initialization periods for certain controlled appliances. For example, if a voice command sends signals to a television to power it on and turn to a specified channel, a period of time may elapse between the receipt of the power on command until the television warms up and is ready to receive additional commands.
- a single recognition vocabulary is that the recognition of voice command always yields the same response. In a multiple recognition vocabulary set scheme, the same voice command may yield different results upon recognition if placed within different vocabulary recognition sets.
- a still further disadvantage of a single recognition vocabulary is that the recognition vocabulary words must be phonetically distinctive from each other which may limit the use of words that may be intuitive for their intended function but are too phonetically similar to other words in the recognition vocabulary, forcing the user to remember a word that is less intuitive.
- a user must be able to quickly submit a voice command following the recognition of a prior voice command, and then the recognition of the latter voice command, the submission of a remote control signal and the detection of the signal by the appliance must occur within the time limit if the appliance is to interpret the commands as a related series of commands instead of individual commands.
- the present invention relates to a method and apparatus that enables a user to control the function of one or more electric appliances or other electrical equipment solely with voice commands.
- An important aspect of the invention relates to voice- actuated mode switching for switching the present invention from a low power consumption mode.
- a hands-free speech recognizing transmitter in accordance with the invention which may be a light-weight small base mounted unit, is adapted to be located near the controlled appliances.
- a voice-operated selection mechanism is provided for selecting any one of a number of categories of appliances to be controlled.
- a universal remote control code library may be provided which allows codes to be selected for control of different types of appliances as well as appliances manufactured by different manufacturers.
- Infrared signal receiving, decoding and storage capabilities further enhance the mvention by providing means to learn infrared codes from other remote control transmitters, such as an appliance's original remote control transmitter. This feature is advantageous for appliances whose codes are not contained in the universal library stored in the invention's memory and also serves to render the invention much less susceptible to obsolescence than speech recognizing transmitters disclosed in the prior art.
- a scheme is provided where both speaker independent and speaker dependent vocabulary may be used as voice commands.
- a speaker independent vocabulary structure provides the user with the means of navigating multiple linked recognition vocabulary sets. At any one time, a single recognition set is made active by the speech recognition circuit. A voice command in one recognition vocabulary set may be used to activate another recognition vocabulary set. In this fashion, a user may verbally navigate among different types of remote control functions and target appliances in an intuitive fashion, while minimizing the number of alternative words from which the speech recognition circuit must select during any given recognition process.
- recognition vocabulary sets are created such that the contents within each set have either functional similarities or otherwise share a relationship that is intuitive to the user.
- the present invention monitors conditions with a time-out counter and an error counter to automatically return to a general default mode if certain conditions are met. In other words, a predetermined number of recognition errors or a period during which no successful recognition occurs will result in a known default state.
- Custom speaker dependent voice commands may be trained by the user and associated with infrared signals during product setup processes. These speaker dependent commands may be accessible from the vocabulary structure described above.
- the present invention has the capability of transmitting multiple control signals, such as infrared signals, to one or more appliances in response to a single voice command by the user.
- Such macro programs may be programmed by the user during a product setup process. For example, a user may desire that the response to the voice command "Video” is for the invention to issue commands to turn a TV power on, wait for the TV to warm up until it is ready to receive control signals, such as infrared signals, set the channel to "3,” select the VCR for control, turn on the VCR, and execute the VCR's play function.
- the user may desire that the response to the user-trained voice command "Sports" is for the invention to issue commands to a TV to turn to channel 123.
- the system may be configured to be self-contained in a single freestanding or stand-alone housing.
- the housing may contain a directional microphone mounted to be rotationally adjusted by the user to enable the user to adjust the sensitivity of the microphone so that the microphone's high sensitivity region is pointed toward the user and microphone noise generating sources, such as an appliance's loudspeaker are located in a region of low microphone sensitivity.
- Visual indication lights may be provided in a manner to remain in line of sight with the user to communicate operation status, such as availability for recognition and results of prior recognition attempts.
- a small keypad may be provided to assist the user during product setup sequences.
- a speaker is also provided to enable output speech synthesized prompts to further assist the user during setup sequences.
- FIG. 1 is a functional block diagram of the electronic elements and circuits in one embodiment of the present invention
- FIG. 2a is a functional block diagram showing the details of the speech recognition circuit in one embodiment of the present invention.
- FIG. 2b is a functional block diagram showing the details of the infrared signal controlling circuit in one embodiment of the present invention.
- FIG. 2c is a schematic circuit diagram showing the details of the audio switching circuit and the sound activation circuit in one embodiment of the present invention.
- FIGs.2d-2f illustrate alternate embodiments of the sound activation circuit illustrated in Fig. 2c.
- FIG. 3 is a perspective view of the physical housing for one embodiment of the present invention
- FIG. 4a is a side view of the housing illustrated in FIG. 3.
- FIG.4b is an exploded perspective view of the housing illustrated in FIG. 3.
- FIG. 4c is a partial sectional view of the housing illustrated in FIG. 3.
- FIG.5 is a functional block diagram showing the default operation modes of one embodiment of the present invention.
- FIG. 6 is a functional block diagram showing the sound activation mode sequence steps for one embodiment of the present invention.
- FIG. 7 is a functional block diagram showing the different recognition modes that may be utilized when different recognition vocabulary sets are activated in one embodiment of the present invention.
- FIG.8 is a functional block diagram showing the sequence of steps for the response prompting recognition mode for one embodiment of the present invention
- FIG. 9 is a functional block diagram showing the sequence of steps for the pattern queuing recognition mode for one embodiment of the present invention.
- FIG. 10 is a functional block diagram showing a continuation of the sequence of steps for pattern queuing recognition mode for one embodiment of the present invention shown in FIG. 9;
- FIG. 11 is a functional block diagram showing the sequence steps for executing a macro program in one embodiment of the present invention;
- FIGS. 12A and 12B is a functional block diagram showing the sequence steps for initiating the product setup process for one embodiment of the present invention
- FIGS. 13A-13C is afunctionalblockdiagramshowingthesequencesteps for selecting a controlled appliance code during a product setup process for one embodiment of the present mvention
- FIGS. 14A and 14B is a functional block diagram showing the sequence steps for learning an infrared signal from another remote control transmitter during a product setup process for one embodiment of the present invention
- FIG. 15 is a functional block diagram showing the sequence steps for teaching custom, speaker dependent voice command names during a product setup process for one embodiment of the present invention
- FIGS. 16A and 16B is a functional block diagram showing the sequence steps for creating a macro program during a product setup process for one embodiment of the present invention
- FIG. 17 is a schematic circuit diagram showing the details of the power supply circuit of one embodiment of the present invention.
- FIG. 18a is a functional block diagram of an alternative embodiment of an audio switching circuit in accordance with one embodiment of the present invention.
- FIG. 18b is a functional block diagram of an alternate embodiment utilizing separate microphones for the sound activation circuit and speech recognition circuit in accordance with the present mvention
- FIG. 18c is a functional block diagram of another alternate embodiment utilizing separate microphones for the sound activation circuit and speech recognition circuit in accordance with the present invention.
- the present invention relates to a truly hands-free universal control unit system for controlling various appliances, such as entertainment appliances, for example, TVs, VCRs, stereo's and the like and may also be used for non-entertainment appliances and virtually any device that is amenable to remote control.
- the universal remote control system in accordance with the present invention is user programmable to enable any number of appliances to be programmed by the user.
- the universal control system in accordance with one embodiment of the invention may be battery operated. During periods when no voice commands are being issued the system enters a sleep or sound activation mode.
- An important aspect of the invention relates to the ability of the system to switch from a sleep mode to an active mode solely by voice commands, to provide true hands-free remote operation.
- FIG. 1 A block diagram of the system in accordance with the present invention is illustrated in FIG. 1 and generally identified with the reference numeral 10.
- the system 10 enables hands-free operation of one or more appliances in a wireless manner.
- the system 10 includes a microphone 20, an audio switching circuit 30, a sound activation circuit 40, a speech recogmtion circuit 50, and a transmitter, for example, an infrared signal controlling circuit 70 and one or more infrared light-emitting diodes 80.
- the system 10 may also contain an infrared receiver 71, a read/write memory device 72 for storage of received IR signal data one or more indicators 52, a keypad 51 and a speaker 53.
- a power supply circuit 90 is also included. The power supply 90 may be configured for DC operation to enable portability of the system 10 or alternatively AC operation.
- An output signal from the microphone 20 is electrically connected to an automatic audio switching circuit 30.
- the microphone 20 may be one or more directional microphones, which have higher sensitivity to sound generated in predetermined regions in relation to the microphone's position than in other predetermined regions.
- a suitable microphone is a model number Mil 8HC directional microphone, available from Lucent Technologies and described in detail in; "DM 1000 Component Directional
- Sound arriving at the microphone is converted into an electric audio output signal by the microphone 20 and is directed to the audio switching circuit 30.
- the microphone audio signal output is directed to the speech recognition circuit 50 if the speech recognition circuit 50 is not in a sound activation mode.
- the audio switching circuit 30 routes the microphone audio signal output to a sound activation circuit 40.
- the output signal of the microphone 20 is electrically connected to the sound activation circuit 40 which includes an amplification circuit (shown in detail in FIG. 2c), that amplifies the signal and a trigger circuit 43 (shown in FIG.2c) that receives the amplified signal from the output of the amplification circuit.
- An output of the trigger circuit 43 is electrically connected to an input/output pin of the speech recognition circuit 50. If the amplified signal is of sufficient amplitude to activate the trigger circuit 43, the output of the trigger circuit causes a logic state change on the input/output pin of the speech recognition circuit 50, causing the invention to change modes from a sleep or sound activation mode to an awake or speech recognition mode.
- the mode change may be done in software and/or hardware to cause the logic state of a mode output pin 65 (shown in FIG. 2a) of the speech recognition circuit
- the speech recognition circuit 50 may include output pins that are electrically connected to a infrared signal controlling circuit 70. Upon recognition of a voice command associated with an instruction to the transmitter, for example, an infrared signal controlling circuit 70, the speech recognition circuit 50 sends one or more signals using the output pins to the infrared signal controlling circuit 70.
- the system 10 as illustrated and described herein translates the voice commands to infrared signals for controlling the appliance by way of an infrared link.
- the output from the speech recognition circuit 50 is directed to a wireless transmitter, formed from an infrared signal controlling unit 70 and one or more infrared light emitting diodes 80 capable of transmitting infrared light in one or more wavelengths.
- the present invention utilizes conventional infrared remote control microcontroller- based technologies, including the conventional universal appliance code libraries that are familiar to those skilled in the art.
- the system may utilize other wireless links, other than infrared or in addition thereto, such as RF, ultrasonic and optical links.
- certain aspects of the invention including the mode changing from a sleep to an awake mode are adapted to be used with appliances that are either wired and wirelessly coupled to the system.
- the appliances may be coupled to the system 10 over a power distribution network.
- the principles of the present invention enable truly hands free control of the appliances.
- the infrared signal controlling circuit 70 is electrically connected to one or more infrared light emitting diodes 80.
- the infrared signal controlling circuit 70 receives and interprets signals from the speech recognition circuit 50 and if the signals communicate instructions to transmit infrared signals to a controlled appliance, the infrared signal controlling circuit 70 identifies the appropriate remote control code and sends a remote control signal representing the code to the infrared light emitting diode(s) 80, which transmits the signal to the controlled appliance.
- An infrared receiver 71, a read/write memory 72, and an indicator 52d may be electrically connected to the infrared signal controlling circuit 80.
- the infrared receiver 72 detects and receives the infrared remote control signals transmitted by other remote control transmitters in a learn mode.
- the infrared signal controlling circuit 70 receives these signals as digital output from the infrared receiver 72.
- the infrared signal controlling circuit 70 decodes and stores the digital signals as codes in the read/write memory 72 for later transmission.
- the indicator 52d may be used to provide a visual indicator to the user during said infrared signal receiving and transmitting operations.
- a keypad 51, indicators 52a, 52b and 52c, and a speaker 53 may be electrically connected to the speech recognition circuit 50.
- the keypad 51 buttons may be utilized by the user to send signals to the input pins of the speech recognition circuit 50 during a product setup process and to provide a power switch for the invention.
- the indicators 52 may be utilized to provide the user with visual status of the system during setup and operation.
- the speaker 53 is driven by the speech recognition circuit 50 pulse width modulation output and is primarily used to provide synthesized speech prompts to the user during product setup processes.
- Software executed by the speech recognition circuit 50 monitors conditions with a sound activation time-out counter and an error recognition counter.
- the speech recognition circuit 50 software Upon the attainment of predetermined conditions discussed below, the speech recognition circuit 50 software enters a low power consuming sleep or sound activation mode.
- a power supply circuit 90 electrically connects a power source (not shown) to circuitry distributing electric power to the electromc elements of the present invention.
- the power source may be either AC or DC or a combination thereof.
- commercially available alkaline batteries or rechargeable battery packs are suitable for a DC power supply.
- FIG. 17 shows the power supply circuit 90 in greater detail than that shown in FIG. 1.
- one of the buttons present on the keypad 51 may be connected to a momentary switch, which, when depressed and held for a sufficient duration of time, establishes an electrical connection between a power source 91 and an input control pin of a digitally controlled CMOS single-pole, single-throw (SPST) analog switch 93.
- SPST digitally controlled CMOS single-pole, single-throw
- An example of a commercially available SPST switch for such purposes is a model number ADG701, available from Analog Devices, Inc. and described in a data sheet entitled; CMOS Low Voltage 2 ⁇
- the input control pin responds to this electrical connection with the power source 91 in a manner equivalent to receiving a logic high digital input, resulting in a closed electrical connection between switch 93 source and drain pins and allowing a connection to be established between the power source 91 and a power distribution plane 94.
- the speech recognition circuit IC 55 becomes electrically connected with the power source 91 as described above, the software stored within its ROM 61 executes a program to set a predetermined output pin 68 to a logic high state.
- the output pin 68 is electrically connected to the input control pin of the switch 93.
- the software contained within the ROM 61 of the speech recognition circuit 50 may respond to the recognition of a speech command such as "Power" when the appropriate recognition vocabulary set is active and under the conditions described below by executing a command to change the logic state of said output pin 68 to a logic low condition.
- This logic low is then received by the input control pin of switch 93, which responds by creating an open connection between switch 93 source and drain pins, and thus disconnecting power distribution plane 94 from the power source 91.
- the present mvention may be powered down via voice command. If the power switch 93 is open as shown in FIG. 17, the circuit elements reliant on this connection to receive energy do not receive electric energy. Also shown in FIG.
- FIG.2a illustrates the speech recognition circuit 50 in greater detail .
- the electronic elements of the speech recognition circuit 50 that process the microphone audio signal output received from the audio switching circuit 30 may be in the form of a microcontroller- based integrated circuit, IC chip 55.
- IC chip 55 Such microcontroller-based ICs specifically designed for speech applications in consumer electronic products are well described in the prior art and are commercially available.
- An example of a suitable IC is a type RSC-300/364 speech recognition microcontroller as manufactured by Sensory, Inc.
- the IC 55 contains as a minimum a preamplifier 56, an analog to digital converter (A/D) 57, a speech processing unit 58, an automatic gain control (AGC) 59, a microcontroller 60, a read-only memory (ROM) 61, a random access memory (RAM) 62, a pulse width modulation (PWM) output 67 or a digital to analog converter (not shown), a mode output
- a clock 63 included in the speech recognition circuit 50 are a clock source 64, a read/write memory device for storage of speech reference pattern data 54, and, optionally, additional read/write memory device(s) 69 or ROM devices (not shown) connected to the external memory interface 66.
- the description of the operation of the speech recognition circuit 55 is provided in general terms for the specific speech recognition IC mentioned above and is specific only in areas where the present invention departs from prior art disclosures or is beneficial to the explanation of aspects of the present invention.
- a conventional microprocessor or a digital signal processor capable of executing speech recognition software algorithms may be used as an alternate to the speech recognition IC 55. Any of the speech recognition circuit elements described above that are not included in said conventional processors may be provided in circuitry external to said IC.
- the present invention executes pattern generation algorithms and speech recognition algorithms that are known to those skilled in the art.
- One speech recognition algorithm for speaker independent recognition uses a pre-trained neural network described in prior art, for example, as is provided by Sensory, Inc. as described below.
- One process for speaker dependent speech recogmtion involves creating a reference pattern for each voice command word or phrase during a user-controlled product setup process. During this set-up process, a pattern is generated when a voice command is spoken by the user.
- a pattern is a compact representation of the significant acoustic information in a voice command word or phrase.
- a speaker dependent reference pattern is created by averaging patterns generated as the voice command is spoken two or more times and the reference pattern is stored in a read/write memory 54.
- speaker dependent speech recognition then involves comparing an unknown pattern generated from a voice command spoken by the user to the speaker dependent reference patterns within a specified recognition vocabulary set. This comparison may involve distance measurements and calculations of the fit of the unknown pattern to each of the reference patterns to determine the closest matching reference pattern.
- the present invention may implement one or more generally known algorithms, including but not limited to pattern matching that compares an unknown pattern with reference patterns, neural networks, and/or hidden Markov models.
- Speaker independent speech recognition is designed to recognize words spoken by a plurality of users and is language dependent. Speaker independent command reference data are generally derived from recordings of the specified spoken commands from several hundred individuals with different speech characteristics and accents in conditions similar to the environment of a product's intended use. Therefore, speaker independent commands require no voice training from the user. Speaker dependent recognition generally involves a user training a product to recognize specific words, and is therefore not language dependent.
- the implementation of linked recognition sets as previously described also allows the user to easily access and navigate among both speaker dependent and speaker independent recognition vocabulary sets.
- Other embodiments of the present invention may be of the form of a speaker independent only version or a speaker dependent version where a user niay follow a set-up sequence to train speaker dependent words in place of the speaker independent structure of the embodiment described herein.
- the audio switching circuit 30 provides an electric connection between the microphone audio signal output and the preamplifier 56 in the speech recognition circuit 50.
- the preamplifier 56 provides signal amplification to a level suitable for analog to digital conversion.
- the analog to digital converter (A/D) 57 preferably having an accuracy of at least 12 bits, is coupled to the output of the preamplifier 56 and converts the incoming audio waveform into digital representations of the incoming signal.
- the digital output of the analog to digital converter 57 is directed to the speech processing unit 58.
- the speech processing unit 58 is controlled by the controller 60 and utilizes RAM 62 for temporary storage of data, control information and result registers, and an arithmetic logic unit (not shown) to produce band-pass-filtered representations of the input waveform in several frequency bands.
- the output of the speech processing unit 58 is received by the controller 60.
- the controller 60 Utilizing code stored in ROM 61 as discussed below, and register space and data space provided by the RAM 62, the controller 60 analyzes the filtered input waveforms to produce a pattern in real time that contains the significant acoustic information in the input signal.
- the controller 60 executes recognition algorithm software to determine which voice command in the active recognition vocabulary set is the best match and was most likely spoken by the user.
- the controller 60 Utilizing code stored in ROM 61 as discussed below, and register space and data space provided by the RAM 62, the controller 60 analyzes the filtered input waveforms to produce a pattern in real time that contains the significant acoustic information in the input signal.
- the controller 60 executes
- ACG automatic gain control
- the speech recognition circuit 50 may include one or more microphone gain resistors, such as user-adjustable thumbwheel potentiometer 35, as well as capacitors (not shown), as part of the preamplification circuitry. Some or all of these components may be integrated into preamplifier 56. Such preamplification circuitry is well known to those skilled to the electronic arts and, for example, is described in the previously referenced in Data Book RSC-300/364. pages 1-50, published by Sensory Inc., Sunnyvale, California, copyright August 1999.
- the IC 55 contains at least one oscillator which functions as a clock 63, driven by a clock source 64 external to the IC 55.
- the IC 55 contains an external memory bus 66 which serves as an interface for addressing additional ROM or RAM located external to the IC if additional memory capacity is needed for control code or data.
- the pulse width modulation (PWM) output pins 67 are electrically connected to a speaker 53 and used primarily to provide synthesized speech prompts and/or audio sounds to direct the user during product set-up sequences.
- the digital to analog converter (not shown) is electrically connected to an audio amplifier (not shown), and may be used as an alternate to the pulse width modulation (PWM) output 67, electrically connected to the speaker 53 to provide synthesized speech prompts.
- the controller 60 utilizes register space in the RAM 62 to control the logic states of predetermined control register bits to determine if the clock 63 is enabled or disabled and if the controller 60 is in a low power consuming mode or not.
- the controller 60 may place the speech recognition circuit 50 into a low power consuming sound activation mode by changing the logic states of said control register bits, removing the clock source 64 from the oscillator 63 of IC 55.
- the controller 60 software also changes the logic state of a mode output 65 pin of the speech recognition circuit 50, as it enters the sound activation mode.
- An input control for the audio switching circuit 30 is electrically connected to said mode output 65 pin which changes logic states as the speech recognition circuit changes modes between speech recognition mode and sound activation mode.
- the input control for the audio switching circuit 30 changes as the logic state of the mode output pin changes, causing the electric signal output from the microphone 20 to be electrically connected to the sound activation circuit 40.
- the audio switching circuit connections are shown in detail in FIG. 2c.
- the speech recognition circuit 50 remains in this sound activation mode until the sound activation circuit 40 causes a bit transition at a predetermined input 68 pin.
- the bit transition changes the state of the previously set control register bits which removes the speech recognition circuit 50 from the low power consuming sleep or sound activation mode and enables the oscillator clock 63.
- the code stored in the ROM 61 instructs the controller 60 to place the speech recognition circuit 50 into speech recognition mode running a continuous listening pattern generation and recognition software routine.
- the software also instructs the controller to change the logic state of the mode output 65 pin.
- Stopping and restarting the speech recognition circuit 50 as previously described does not cause a reset of the controller 60, nor cause loss of contents of internal registers and thus allows the input/outputs 68 to remain where last set.
- the power requirement for the speech recognition circuit is significantly reduced, but the ability to maintain its energy supply allows the speech recognition circuit to retain the contents of its internal register and previously set input/output 68 conditions and resume operation in a relatively uninterrupted manner.
- the energized speech recognition circuit remains capable of detecting input events at the IC 55 input 68 pins even when placed in low power consuming sound activation mode, further supporting the hands-free activation capability of the sound activated circuit 40.
- the present mvention may also contain software code stored in the ROM
- recognition vocabulary sets are generally created such that the voice commands, represented by the reference data within each said set, have either functional similarities or otherwise share a relationship that is intuitive to the operator. A voice command in one recognition vocabulary set may activate another recognition vocabulary set.
- a user may verbally navigate among different types of function selections and target appliance selections in an intuitive fashion, while limiting the number of alternative words among which the speech recognition circuit must discriminate during any given recognition process. Furthermore, since a pattern generated by a voice command is compared only to the words in the active recognition vocabulary set, the use of phonetically similar words is possible if such similar words are placed in different recognition vocabulary sets.
- the present invention monitors conditions with a time- out counter and an error counter to automatically return to a general default mode if certain conditions are met. In other words, when no match is found or a period elapses in which no recognition attempts occur, the system returns to a known default state.
- the controller 60 executes the control code instruction associated with the matching reference command.
- the control code instruction may direct the controller 60 to (a) activate a new recognition vocabulary set; (b) utilize IC 55 output 68 pins to communicate instructions to the infrared signal controlling circuit 70; or (c) disconnect predetermined elements of the present invention circuitry from the power supply circuit for long term deactivation of the unit.
- a control code instruction directing the controller 60 to activate a new recognition vocabulary set may also direct the controller 60 to enter a new operating mode utilizing different pattern generating and/or speech recognition software.
- the present mvention may be provided with a user selectable default recognition vocabulary set, which is appropriate for an intended appliance category, to which the software causes the controller 60 to return following the recognition of certain voice commands or as the result of other predetermined conditions such as the elapse of time-out periods or the detection of a specified number of speech recognition errors.
- Recognition vocabulary sets contain reference command data representing the group of voice commands the invention is expecting to receive at any time, i.e. when a particular recognition vocabulary set is active.
- the software running while a default recognition vocabulary set is available for speech recognition may typically be executing a routine where the speech recognition circuitry remains continuously available to generate patterns from detected voice commands unless otherwise processing a previous voice command for recognition or measuring the silence level to provide compensation for background noise.
- the controller 60 executes the control code instruction(s) associated with the matching reference command.
- the control code instruction(s) may direct the controller 60 to activate a new recognition vocabulary set or utilize IC 55 output 68 pins to communicate instructions to the infrared signal controlling circuit 70.
- Control code instructions directing the controller 60 to activate a new recognition vocabulary set may also direct the controller 60 to enter a new operating mode utilizing different pattern generating and/or speech recognition software.
- FIG. 2b illustrates the infrared signal controlling circuit 70 in greater detail.
- the infrared signal controlling circuit 70 includes a controller 76, an interface 75 to the speech recognition circuit, one or more clock sources 73, and one or more infrared driver circuits 74.
- the electronic elements of the controller are in the form of an microcontroller integrated circuit, IC chip 76 as shown in FIG. 2b.
- Such microcontroller-based ICs specifically designed for infrared remote control transmitter applications which support infrared signal learning are well described in the prior art and are commercially available.
- An example of a commercially available controller for such purpose is a model number Z86L98, available from Zilog, Inc.
- the controller IC 76 generally contains, a controller, a read-only memory
- ROM read only memory
- RAM random access memory
- a clock an external memory interface
- timer a timer
- modulator a modulator
- input ports one or more output ports
- encoder an encoder
- a plurality of stored infrared instruction codes and a plurality of program instructions are generally stored within a ROM memory.
- the RAM is used by controller IC 76 to store data for operations and control.
- the controller IC 76 oscillator derives its source from clock source 73, such as a crystal or a ceramic resonator.
- the controller IC 76 is electrically connected to an infrared receiver 71 that receives externally transmitted infrared function codes (from a teaching transmitter, not shown) and supplies them to controller IC 76 where they are conventionally decoded by the decoder, shown internally to controller IC 76 in FIG. 2a.
- the external memory interface is used by the controller
- IC 76 to store and access learned infrared signal codes in the external read/write memory 72.
- An infrared driver which is generally transistor-based, is electrically connected to controller IC 76 and electrically connected to infrared light-emitting diode 80.
- An indicator light-emitting diode 52d is also comiected to controller IC 76 which provides the user message prompts and other information, such as indicating operating stages and prompting desired user actions, for assisting in the programming of the present invention.
- the universal library of appliance codes are generally stored within the ROM memory of the controller IC 76 or stored within a ROM memory external to controller IC 76 and accessible through an external memory interface. Codes acquired through infrared code learning are typically stored in a read/write memory external to controller IC 76.
- the memory devices are typically organized into a plurality of pages with the various infrared function codes for a particular appliance model being generally assigned to a specific memory page.
- an interface 75 provides electrical connections between the speech recognition circuit 50 and the controller IC 76.
- a plurality of output pins PO 0 , PO ... PO r . ! at the controller IC 76 are electrically connected as data inputs to each of a series of multiplexers (MUX 0 , MUX l5 ... MUX, ⁇ ) within the interface 75, which in one embodiment may be a programmable logic device configured to operate a switching matrix, connecting controller IC 76 outputs to controller IC 76 inputs.
- a suitable programmable logic device is a MACH 4 CPLD logic device, available from
- the output 68 pins of the speech recognition IC 55 are electrically connected as select inputs SI 0 , SL , ... SI m-1 to each of the multiplexers contained within the interface
- each multiplexer is electrically connected exclusively to one input pin PI 0 , PI l5 ... PI n-1 of controller IC 76.
- the output 68 pins send a binary instruction to the select pin inputs of the interface 75 multiplexers shown in FIG. 2a.
- each multiplexer may select zero or one of the data inputs to be electrically connected to the multiplexer output.
- the interface 75 further controls the output enable of each multiplexer such that the output is enabled only if one of the data inputs has been selected for that multiplexer. This process produces an input at controller IC 76 input pins that is equivalent to that resulting from a button depress on a keypad of a conventional remote control transmitter which generates circuit connections.
- the controller IC 76 software interprets the instruction received at its input ⁇ in(s) and responds by (a) identifying a section of the ROM to be made available for subsequent access if the instruction is associated with an appliance category selection; (b) by identifying a memory location within its internal ROM and retrieving the control code stored therein if the instruction is associated with a command stored within the universal library of codes stored in ROM or (c) retrieving a learned infrared code stored in read/write memory 72 if the instruction is associated with a learned infrared signal.
- the controller 76 utilizes its formatting program and its modulator to generate the precise carrier frequency, pulse width, pulse modulation, and overall timing format for a signal based upon the control code retrieved, and submits the signal to an infrared driver 74 which drives one or more infrared light emitting diodes 80.
- the infrared light emitting diode 80 converts the electrical signal received into an infrared signal which is transmitted to one or more target appliances.
- FIG.2c illustrates the audio switching circuit 30 and the sound activation circuit 40 in greater detail.
- FIG. 2c shows the present invention in the sound activation mode as indicated by the audio switching circuit 30 maintaining a switch closure and therefore electrical connection between the microphone 20 output and the sound activation circuit 40.
- the audio switching circuit 30 in the preferred embodiment of the present invention contains a commercially available digitally controlled, single-pole, double-throw (SPDT) analog switch, for example, a model number ADG 719 (CMOS Switch), available from Analog Devices and described in a data sheet entitled; CMOS Low Voltage 4 ⁇ SPDT Switch ADG 719. Rev a, pages 1-8, available from Analog
- SPDT digitally controlled, single-pole, double-throw
- Figures 2d through 2f show alternative embodiments of the sound activation circuit 40 shown in Fig. 2c.
- Fig. 2d shows a sound activation circuit 40 with a microphone load resistance value and a time constant value for a timing circuit that differ from the respective values shown in Fig. 2c. Different values affect the microphone 20 sensitivity while in sound activation mode and the time constant duration of said timing circuit, respectively, in manners that are well known to those skilled in the electronic arts.
- the sound activation circuit 40 shown in Fig. 2d also includes fewer components than that shown in Fig. 2c.
- the general operation of the sound activation circuit 40 described below and shown in Fig. 2c also describes the sound activation circuit 40 shown in Fig. 2d.
- FIG. 2e shows another alternative sound activation circuit 40 that combines an additional Schmitt trigger inverter 43f, a 2- input NAND gate 44, a resistor and a capacitor with the sound activation circuit 40 shown in Fig. 2d.
- the sound activation circuit 40 shown in Fig. 2e is less susceptible to activation by sounds that exceed a predetermined activation amplitude threshold, but are not maintained at or above said threshold for at least a predetermined duration.
- the sound activation circuit 40 shown in Fig. 2e is responsive to such sounds as spoken words that exceed an activation amplitude threshold for at least a predetermined duration, but is less responsive to incidental sounds that do not meet both amplitude and duration criteria.
- the output signal from microphone 20 is electrically connected by audio switching circuit 30 to the sound activation circuit 40 as shown in Fig. 2e.
- the sound activation circuit 40 contains one or more audio amplification stages that amplify the electric signal output from the microphone 20.
- Fig. 2e shows an audio signal amplification stage based upon an NPN transistor 41a, followed by another audio signal amplification stage based upon an NPN transistor 41b.
- the sound activation circuit 40 also contains trigger circuitry.
- the trigger circuitry shown in Fig. 2e utilizes four inverting Schmitt trigger circuits, shown as part of IC 43 because the IC's are commercially available which integrate several such circuits into a single device package.
- the amplified output signal from the last audio amplification stage is electrically connected to an input of a first inverting trigger 43 a.
- the inverting trigger 43 a activates, outputting a logical low, and leading to a logical high output at inverting trigger 43b and inverting trigger 43f.
- the logical high output of inverting trigger 43b leads to a logical high condition at a first input pin of a 2-input NAND gate 44.
- the logical high output of the inverting trigger 43f is electrically connected to a resistor/capacitor time delay circuit that is electrically connected to a second input pin of 2-input NAND gate 44. If the output of the inverting trigger 43b is held in a logical condition for a predetermined duration, the time delay circuit will allow the second input of 2-input NAND gate 44 to reach the equivalent of a logical high condition.
- the sound activation circuit 40 also contains a potentiometer which allows resistance modification within the amplification circuit.
- This potentiometer is accessible to the user in the form of a thumbwheel knob 45 which the user can adjust to change a resistance value within the amplification circuit which modifies the sensitivity of the sound activation circuit.
- the logic state change at the output pin of 2-input NAND gate 44 causes a bit transition at the input 68 pin of speech recognition circuit controller 60. As described below this bit transition is detected by controller 60 winch responds by removing the speech recognition circuit from the low power consuming sound activation mode and enabling the controller clock 63. This activates speech recognition circuit 50 for subsequent speech recognition processing as shown in step S503 in Fig. 5.
- the software also instructs controller 60 to change the logic state of mode output 65 pin.
- the speech recognition circuit 50 then maintains mode output 65 pin in the logic state consistent with the speech recognition mode.
- an input control pin of audio switching circuit 30 is electrically connected to said mode output 65 pin, causing the state of audio switching circuit 30 to be controlled by said mode output pin.
- Fig. 2f shows yet another alternative sound activation circuit 40 that combines additional Schmitt trigger inverters 43d-43f, 3-input NAND gates 46a-46c, digitally controlled analog switches 47a and 47b, and multiple timing circuits including resistors, capacitors and diodes with the sound activation circuit 40 shown in Fig. 2d.
- the sound activation circuit 40 shown in Fig. 2f is less susceptible to activation by sounds that exceed a predetermined activation amplitude threshold, but are not maintained at or above said threshold for at least a predetermined duration.
- This sound activation circuit 40 is also less susceptible to activation by certain sounds, including speech, that exceed a predetermined activation amplitude threshold and are maintained at or above said threshold for a period of time that exceeds a predetermined duration.
- the sound activation circuit 40 shown in Fig. 2f is less responsive to sounds that continue to exceed a predetermined activation amplitude threshold for a predetermined second duration, thus allowing for further restriction of the durations of sounds that may activate the system from a sound activation mode. Assuming that the system is in sound activation mode, the output signal from microphone 20 is electrically connected by the audio switching circuit 30 to the sound activation circuit 40 as shown in Fig.2f.
- the sound activation circuit 40 contains one or more audio amplification stages that amplify the electric signal output from microphone 20.
- Fig.2f shows an audio signal amplification stage based upon an NPN transistor 41a, followed by another audio signal amplification stage based upon an NPN transistor 41b.
- the sound activation circuit 40 also contains trigger circuitry.
- the trigger circuitry shown in Fig. 2f utilizes six inverting Schmitt trigger circuits, shown as part of
- the amplified output signal from the last audio amplification stage is electrically connected to an input of a first inverting trigger 43a. If the resulting amplified electric audio signal representing the sound received by microphone 20 reaches a predetermined amplitude threshold equal in magnitude to a logic state change (bit transition) at the input of inverting trigger 43a, inverting trigger 43a activates, outputting a logical low.
- a logical low at the output of inverting trigger 43a leads to a logical high output at inverting trigger 43b and a logical low condition at a first input of a 3-input
- NAND gate 46c preventing the output of 3-input NAND gate 46c from transitioning to a logical low condition while the input of inverting trigger 43b is held in a logical low condition.
- a logical high output of the inverting trigger 43b leads to a logical low condition at the output of inverting trigger 43c and a logical high condition at a first input of a 3- input NAND gate 46b.
- the output of 3-input NAND gate 46b is electrically connected to a timing circuit including a diode, resistor and capacitor that is electrically connected to an input of an inverting trigger 43f.
- a logical high condition at the first input of the 3-input NAND gate 46b leads to a logical low at the output of 3- input NAND gate 46b unless a second input of 3-input NAND gate 46b is held in a logical low condition by a timing circuit described below that is electrically connected to the second input of 3-input NAND gate 46b.
- a logical low condition at the output of 3-input NAND gate 46b leads to a logical low condition at the input of inverting trigger 43f, remaining in this condition for at least a duration determined by a time constant value of the associated timing circuit electrically connected to the input of inverting trigger 43f.
- a logical low condition present at the input of inverting trigger 43f leads to a logical low at the output of inverting trigger 43e.
- a logical low at the output of inverting trigger 43e leads to a logical high output at inverting trigger 43 d and a logical low condition at a second input of 3-input NAND gate 46c, preventing the output of 3-input NAND gate 46c from transitioning to a logical low condition while the input of inverting trigger 43f is held in a logical low condition.
- a logical low at the output of inverting trigger 43 e also leads to a logical low condition at a second input of 3-input NAND gate 46b, returning the output of 3-input NAND gate 46b to a logical high condition and maintaining this condition for at least a duration determined by a time constant value of the associated timing circuit electrically connected to the second input of 3-input NAND gate 46b.
- a control input pin of a digitally controlled analog switch 47b is also electrically connected to the second input of 3-input NAND gate 46b as shown in Fig.2f.
- a logical low condition at the second input of 3-input NAND gate 46b causes the switch 47b to open and remain open for a duration determined by the duration of the presence of a logical low condition at the output of inverting trigger 43e plus a time constant value of the associated timing circuit electrically connected to the second input of 3-input NAND gate 46b.
- the open position of switch 47b disconnects an electrical connection between a third input of 3-input NAND gate 46c and a circuit that remains in a logically low condition. As shown in Fig.
- the output of inverting trigger 43d is electrically connected to a timing circuit including a diode, resistor and capacitor that is electrically connected to a control input pin of a digitally controlled analog switch 47a.
- a logical high condition at the output of inverting trigger 43d causes the switch 47a to close and remain closed for a duration determined by the duration of the presence of a logical high condition at the output of inverting trigger 43d plus a time constant value of the associated timing circuit electrically connected to the control input pin of switch 47a.
- the closure of switch 47a establishes an electrical connection between the output of 3- input NAND gate 46a and a third input to 3-input NAND gate 46c.
- a logical high output of inverting trigger 43b leads to a logical low condition at the output of inverting trigger 43c.
- the output of inverting trigger 43 c is electrically connected to a timing circuit including a diode, resistor and capacitor that is electrically connected to a first input of a 3-input NAND gate 46a.
- a logical low condition at the output of inverting trigger 43c leads to a logical high condition at the output of 3-input NAND gate 46a which is held in said logical high condition for a duration determined by the duration of the presence of the logical low signal received from the output of inverting trigger 43 c plus a time constant value of the associated timing circuit electrically connected to the first input of a 3-input NAND gate 46a.
- a logical high condition at the output of 3-input NAND gate 46a leads to a logical high condition at the third input to 3 -input NAND gate 46c while an electrical connection is maintained by switch 47a and switch 47b remains open.
- the three inputs to 3-input NAND gate 46c may be simultaneously held in logical high condition if sound exceeding a predetermined threshold is initially detected, continues to be detected after a predetermined period of time, and ceases to be detected within a following predetermined period of time. If said sound is detected and continues to be present after a predetermined time delay, then the second and third input pins of 3 -input NAND gate 46c are held in a logical high condition.
- 3-input NAND gates 46a-46c are electrically connected to a power source and are electrically connected to a common ground. The general operation of such signal amplification, triggering and time delay circuits are well known to those skilled in the electronics art.
- Sound activation circuit 40 also contains a potentiometer which allows resistance modification within the amplification circuit.
- This potentiometer is accessible to the user in the form of a thumbwheel knob 45 which the user can adjust to change a resistance value within the amplification circuit which modifies the sensitivity of the sound activation circuit.
- the logic state change at the output pin of 3-input NAND gate 46c causes a bit transition at input 68 pin of speech recognition circuit controller 60. As described below, this bit transition is detected by controller 60 which responds by removing the speech recognition circuit from the low power consuming sound activation mode and enabling the controller clock 63. This activates the speech recognition circuit 50 for subsequent speech recognition processing as shown in a step S503 in Fig. 5.
- the software also instructs the controller 60 to change the logic state of mode output 65 pin.
- the speech recognition circuit 50 then maintains mode output 65 pin in the logic state consistent with the speech recognition mode. As indicated previously and shown in Fig. 2f, an input control pin of audio switching circuit 30 is electrically connected to said mode output 65 pin, causing the state of audio switching circuit 30 to be controlled by said mode output pin.
- the logic state change at mode output 65 pin results in a logic state change at the input control pin of audio switching circuit 30, causing said circuit to electrically connected microphone 20 output signal to speech recognition circuit 50, disconnecting it from sound activation circuit 40, as shown in step S504 in Fig. 5. This connection is maintained until speech recognition circuit 50 determines that predetermined conditions have been met to return to the sound activation mode.
- FIG. 18a One alternate embodiment is shown in FIG. 18a which employs a commercially available digitally controlled (digitally enabled input control), single-pole, single-throw (SPST) analog switch, instead of the SPDT switch employed within the embodiment described above, within the audio switching circuit 30.
- SPST digitally controlled
- FIG. 18a an electrical connection is always maintained between the microphone 20 output and the speech recognition circuit 50, but the switch is used to either electrically connect or disconnect the sound activation circuit 40 to the microphone 20 output depending on the state of the mode pin 65 of the speech recognition circuit 50.
- the speech recognition circuit 50 controls the mode pin 65 logic state as described in further detail below for the embodiment discussed above such that the sound activation circuit 40 is electrically connected to the microphone 20 output only when the invention is placed into sound activation mode.
- FIG. 18b Another alternate embodiment is shown in FIG. 18b which employs two microphones 20a and 20b, the output of each is dedicated to the speech recognition circuit 50 or the sound activation circuit 40, respectively.
- the microphone outputs remain exclusively electrically connected to the speech recognition circuit 50 or the sound activation circuit 40.
- FIG. 18c Another alternate embodiment is shown in FIG. 18c, which is a combination of the two alternate schemes presented above. This scheme employs two microphones 20a and 20b, the output of each is dedicated to the speech recognition circuit 50 or the sound activation circuit 40, respectively. As shown in FIG.
- an electrical connection is always maintained between the microphone 20a output and the speech recognition circuit 50, but an SPST switch as described above is used to either electrically connect or disconnect the sound activation circuit 40 to the microphone 20b output depending on the state of the mode pin 65 of the speech recognition circuit 50.
- the speech recognition circuit 50 controls the mode pin 65 logic state in the same manner as described later in further detail for the preferred embodiment such that the sound activation circuit 40 is electrically connected to the microphone 20 output only when the invention is placed into sound activation mode.
- FIGS. 3 and 4a-4c illustrate an exemplary embodiment of a housing for the present invention. Referring first to FIG. 3 , shown is speech recognizing transmitter
- a housing which includes a main housing portion 11, a microphone base 12 which holds a microphone 20 and that may be rotated independently from said main enclosure section 11, as described below and a removable battery access panel (not shown) on the bottom of the unit.
- Two ports 96, 98 in the form of openings are provided in the top of the microphone base 12, through which sound is received by the microphone.
- An opening in the main enclosure section 11 is provided for sound generated from a speaker 53.
- the opening may be formed from many small openings in the indicated area which may take the form of slits or cross-hatched pattern openings through which sound generated by the speaker 53 may pass through the main enclosure section 11.
- the indicators 52a, 52b, 52c and 52d are light-emitting diodes operating in visible light wavelengths that are used to communicate operating status to the user.
- Openings may also be provided in the main enclosure 11 for each of said indicators.
- a keypad 51 may be provided to enable the user access to buttons used primarily to communicate with the system during product setup processes. Openings are provided in the main enclosure 11 for each button of said keypad.
- a user-adjustable thumbwheel potentiometer 35 may also be provided to allow the microphone sensitivity adjustment for electric audio signals directed to a speech recognition circuit.
- a user-adjustable thumbwheel potentiometer 45 may be provided to allow adjustment of the amplification level of electric audio signals directed to a sound activation circuit. Openings may be provided in the main enclosure 11 for each of said thumbwheel potentiometers.
- vibration-absorbing, adhesive-backed feet 19 made of rubber or similar compounds that are conducive to vibration absorption may be mounted to the bottom of main enclosure section 11.
- FIG. 4a is a side elevational view of the physical structure of one embodiment of the present invention. In addition to those components shown in FIG. 3.,
- FIG. 4a shows infrared light-emitting diode 80 and a battery holding compartment 18.
- Openings are provided in the main enclosure section 11 for each of the indicators and for mating of the removable battery access panel 17 (FIG. 4b) to the main enclosure section 11.
- Electronic components are either mounted upon or are electrically connected by wiring to a printed circuit board assembly 16 shown with hidden lines.
- FIGS. 4b and 4c show the rotatable IR transmitter and rotatable microphone feature in more detail.
- the housing 11 may be formed from a front housing portion 82 and rear housing portion 84.
- the front and rear housing portions 82 and 84 are formed within continuous edges 86 and 88, respectively, to enable the front 82 and rear housing portion 84 to be joined together with a suitable adhesive, such as an epoxy, or by way of ultrasonic welding or otherwise formed to be coupled together.
- Each of the front 82 and rear 84 housing portions includes a semi-circular opening 85, 87 formed at the top of the housing 11.
- Semicircular annular notches 95 and 97 are formed adjacent to each of the semicircular openings 85 and 87.
- these semicircular annular notches 95 and 97 are for receiving a microphone base 12 and enabling it to rotate.
- the microphone base 12 for example, as discussed above, includes a outer rim portion 99 formed as a disk.
- the outer rim portion 99 is adapted to be received in a semi-circular annular notches 95 and 97 in order to enable the microphone base 12 to be rotatably mounted with respect to the housing 11.
- Electrical conductors 21 are used to connect the microphone 20 to the circuitry described above. In order to protect the electrical connection between the electrical conductors 21 and the microphone from being damaged as a result of rotation of the microphone base 12, sufficient slack is provided in the conductors 21.
- the microphone 20 may be a directional microphone. As such, the microphone 20 is provided with a pair of sound ports 22 and 23. Rectangular openings 96 98 are provided in the microphone base 12 to allow sound to reach the microphone ports 22 and 23. A radially extending rib 100 may be provided on the outer rim portion 99.
- An axially extending rib 102 may be formed in one of the semicircular annular notches 95, 97 to form a stop.
- the axial rib 102 is adapted to engage the radial rib 100 on the outer rim portion 99 of the microphone base 12 to limit rotation of the microphone base 12.
- Another important feature of the invention relates to the fact that the infrared light emitting diode 80 may be rotatably mounted relative to the rear housing portion 84.
- an opening 104 may be provided in the rear housing portion 84.
- a pair of spaced apart plates 106 and 108 may be formed adjacent to the opening 104 and configured to extend into the rear housing portion 84 as generally shown in FIG. 4b.
- Apair of protuberances 110 maybe formed on the upper and lowerplate 106 and 108 to form a pivot axis.
- the infrared light emitted diodes 80 may be carried by an i ⁇ egularly shaped housing 112 having a top side 114 and a bottom side 116.
- the housing 112 is open on one end and contains apertures 118 and 120 in the top 114 and bottom 116 sides.
- the apertures 118 and 120 are configured to receive the protuberances 110 and the top
- the housing portion 112 is adapted to carry the infrared light emitting diodes 80.
- Electrical conductors 89 are used to provide an electrical connection between the infrared light emitting diode 80 and the balance of the circuitry. The conductors 89 are provided with sufficient slack to avoid effecting the electrical connections to the electrical conductors when the housing 112 is rotated.
- the system may be AC or DC. In DC embodiments as shown in FIG. 14b, a battery access hatch 17 may be provided on the bottom of the housing 11.
- FIG. 5 is a flowchart form of two default modes of the present invention.
- a sound activation mode is the default mode when the invention is operating in a low power consuming manner in a step S501. Otherwise, a continuous listening speech recognition mode is the default mode in a step S505 unless a user is performing product setup processes.
- the speech recognition circuit 50 remains electrically connected to the power supply circuitry 90 and receives electric power while in both of these modes. It should be noted that means is also provided to electrically disconnect the electric power source from the section of the power supply circuit that distributes electric power to other electronic elements within the present invention if it is desirable to prevent unintentional activation or if the invention is not to be used for an extended period of time.
- the command to disconnect power from said electronic elements is not included within a default recognition vocabulary set to prevent unintentional deactivation of the invention and to prevent confusion with using the invention to power on and off controlled appliances.
- the command is placed in a recognition vocabulary set that must be accessed by a command in another recognition vocabulary set to ensure recognition of said command is intentional.
- the operation of the invention depends on whether or not the invention is in sound activation mode as shown in a step S501.
- the user can visually determine this state because no indicators 52a, 52b. 52c or 52d are illuminated during the sound activation mode. If the system is not in the sound activation mode, then it is either in the default speech recognition mode listening for voice commands as shown in a step S505 or temporarily executing a speech recognition routine involving another recognition vocabulary set. Again, it should be noted that an exception applies if the user is performing a product setup process, during which time the invention may also enter modes where it is waiting for the user to depress a button.
- the invention will automatically return to the default speech recognition mode after the user has completed submitting voice commands within the recognition vocabulary set active at that time.
- the conditions under which other speech recognition routines cease and the default speech recognition mode becomes active are described later.
- the microphone 20, the audio switcliing circuit 30, the sound activation circuit 40 and the speech recognition circuit IC 55 While in the sound activation mode as shown in a step S502, the microphone 20, the audio switcliing circuit 30, the sound activation circuit 40 and the speech recognition circuit IC 55, as a minimum, receive electric energy from the power supply circuit 90.
- the microphone 20 converts the acoustic signal into an electric signal.
- the electric signal output from the microphone 20 is electrically connected to either the sound activation circuit 40 if the system is in sound activation mode or the speech recognition circuit 50 if the system is in speech recognition mode.
- the audio switching circuit 30 is set to one of these two possible states. As shown in FIG. 2c, an input control for the audio switching circuit 30 is electrically connected to a speech recognition circuit 50 mode output 65 pin which changes logic states as the speech recognition circuit changes modes between sound activation mode and speech recognition mode. The input control for the audio switching circuit 30 automatically detects the logic state of said mode output pin and changes the electrical connections for the electric signal output from the microphone 20 accordingly.
- the sound activation circuit 40 contains one or more audio amplification stages that amplify the electric signal output from the microphone 20.
- FIG. 2c shows an audio signal amplification stage based upon an NPN transistor 41a, followed by another audio signal amplification stage based upon an NPN transistor 41b.
- the sound activation circuit 40 also contains a trigger circuit.
- the trigger circuit shown in FIG.2c utilizes a series of three inverting Schmitt trigger circuits, shown collectively as IC 43 because IC are commercially available which integrate several such circuits into a single device package.
- the amplified output signal from the last audio amplification stage is electrically connected to an input of a first trigger circuit. If the resulting amplified electric audio signal representing the sound received by the microphone 20 reaches a predetermined amplitude threshold equal in magnitude to a logic state change (bit transition) at the input of the trigger circuit, the trigger circuit activates, indicating the sound has been detected as shown in a step S502.
- the first inverting trigger circuit then outputs a logical low, leading to a logical high output af the second inverting trigger followed by a logical low output at the third inverting trigger in IC 43. It is the output of the third inverting trigger that is electrically connected to the input pin 68 of the speech recognition circuit 50.
- the general operation of such signal amplification and triggering circuits are well know to those skilled in the electronics arts.
- the sound activation circuit 40 also contains a potentiometer which allows resistance modification within the amplification circuit.
- This potentiometer is accessible to the user in the form of a thumbwheel knob 45 which the user can adjust to change a resistance value within the amplification circuit which modifies the sensitivity of the sound activation circuit.
- the logic state change of the output pin on the trigger circuit causes a bit transition at the input 68 pin of the speech recognition circuit controller 60. This bit transition is detected by the controller 60 which responds by removing the speech recognition circuit from the low power consuming sound activation mode and enabling the controller clock 63. This activates the speech recognition circuit
- the software also instructs the controller 60 to change the logic state of the mode output 65 pin.
- the speech recognition circuit 50 then maintains the mode output 65 pin in the logic state consistent with the speech recognition mode.
- an input control pin of the audio switching circuit 30 is electrically connected to the mode output 65 pin, causing- the state of the audio switching circuit 30 to be controlled by the mode output pin.
- the logic state change at mode output 65 pin results in a logic state change at the input control pin of the audio switching circuit 30, causing the circuit to electrically connect the microphone 20 output signal to the speech recognition circuit 50, disconnecting it from the sound activation circuit 40, as shown in a step S504. This connection is maintained until the speech recognition circuit 50 determines that predetermined conditions have been met to return to the sound activation mode.
- the controller 60 utilizes the ROM 61 to activate the speech recognition mode software as shown in a step S505.
- a sound activation mode time-out counter and a recognition error counter are set to zero as shown in a step S506.
- the sound activation time-out counter tracks elapsed time between attempts made by the speech recognition circuit 50 to recognize sounds and if a predetermined time value TMAX elapses between recognition attempts, the speech recognition circuit software initiates a routine to enter sound activation mode and changes the logic states of the previously described control register bits.
- the recognition error counter tracks the number attempts made by the speech recognition circuit 50 to recognize sounds for which no match is identified.
- a green light-emitting diode 52a is activated and remains illuminated in a step S507 while the speech recognition mode is available to execute a pattern generation algorithm to provide a visual indicator to the operator that the invention is ready to receive a voice command. It should be noted that this indicator will briefly deactivate during a silence level detection period, pattern generation or during speech recognition processing to inform the user that the speech recognition circuit 50 is temporarily unavailable to receive a voice command, but the green light-emitting diode
- the default speech recogmtion mode software executes a continuous listening routine.
- the green light-emitting diode 52a illuminates while the speech recognition circuit is waiting to detect sounds for which to create patterns and submit for recognition processing as shown in step S508.
- the speech recognition circuitry executes a software routine that cycles among states where it monitors environmental sound level until a suitable silence level is detected, generates a pattern for a detected sound, compares the duration of the acquired pattern representing the detected sound to a defined duration for the active recognition vocabulary set commands, and when the duration of the detected sound pattern is consistent with said active recognition vocabulary set duration, executes a recognition algorithm to determine if a match can be identified for the acquired unknown pattern and one of the commands in the active recognition vocabulary set. Acquired patterns that are not consistent in duration with recognition vocabulary set commands (too long or too short) are ignored, and the speech recognition circuit software returns to execute the silence level detection routine.
- the silence level detection routine listens (remains in a detection mode) until the noise level drops below a predetermined threshold, meaning a certain silence level is achieved. During this silence level detection routine, result codes are returned and compared to a noise threshold value until a result code is returned indicating the noise level has dropped below the predetermined threshold. Pattern generation can then be performed if a sound is detected. This cycle is shown as steps S508 through S517. Such continuous listening software routines are well known to those skilled in the art.
- the default mode speech recognition circuit software cycles between a silence level detection routine and a listening (ready for pattern generation) routine shown in steps S508, S509 and S510 while waiting for the detection of a sound.
- the sound activation time-out counter value is periodically compared to the predetermined value TMAX in a step S509. If the time-out period elapses before a sound is detected, the speech recognition circuit 50 executes software code to enter the sound activation mode and disable the clock 63 from the clock source 64 as shown in FIG. 6. If the timeout period has not elapsed, the speech recognition circuit 50 continues to cycle between a sound level detection routine and a listening (ready for pattern generation) routine, returning to steps S508, S509 and S510.
- the green light-emitting diode 52a ceases to illuminate and a pattern is generated to represent the acoustically significant elements of the sound in a step S511.
- the duration of the acquired unknown pattern for the detected sound is compared to determine if its duration is consistent with the duration of the recognition vocabulary set commands in a step S512.
- the duration check obviates the need to complete the speech recognition process if the pattern generated for the unknown sound, word, or phrase is either shorter or longer in duration than the commands in the active recognition vocabulary set, thus serving as a quick filter to allow the speech recognition circuit 50 to remain available for pattern generation for a increased proportion of the time.
- the value of the recognition error counter is incremented by one and the value of TMAX is reset to zero in a step S515 and a red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator in a step S516.
- the recognition error counter value is then compared to a value EMAX, which is a predetermined value for the maximum number of recognition errors allowed, to determine if the two values are equal in a step S517. If the recognition error counter value is equal to value EMAX, the speech recognition circuit 50 executes software to enter the sound activation mode and disable the controller clock 63 from the clock source and shown in FIG. 6.
- the recognition error counter value is not equal to value EMAX, the green light-emitting diode 52a is activated and remains illuminated and the speech recognition circuit 50 executes software which cycles between the silence level detection routine and the listening (ready for pattern generation) routine in steps S508, S509 and S510.
- step S511 If the pattern generated in step S511 is found to be consistent in duration with the recognition vocabulary set command duration in a step S512, then the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold in a step S513. The result of this comparison is identified in a step S514.
- step S514 If a match for the acquired pattern is not identified in step S514, the value of the recognition error counter is incremented by one and the value of TMAX is reset to zero in a step S515 and the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified in a step S516.
- the recognition error counter value is then compared to value EMAX in a step S517. If the recognition error counter value is equal to value EMAX, the speech recognition circuit 50 executes software stored in its ROM 61 to enter the sound activation mode and disable the clock 63 from the clock source 64 and as shown in FIG. 6.
- the recognition error counter value is not equal to value EMAX, the green light-emitting diode 52a is activated and remains illuminated and the speech recognition circuit 50 executes software which cycles between the silence level detection routine and the listening (ready for pattern generation) routine in steps S508, S509 and S510.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command in a step S518 and determines if the operation is to send an instruction to the speech recognition circuit controller 60 to activate a new recognition set vocabulary or to output a signal to the infrared controlling circuit 70 using the speech recognition circuit input/output 68 pins.
- the signal to the infrared controlling circuit 70 communicates either a appliance category selection command in a step S520 or a command to transmit one or more infrared signals for specified functions to the currently controlled appliance in a step S521.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to reset the values TMAX and EMAX to zero in a step S506, activates the green light-emitting diode 52a in a step S107 and returns to a continuous listening routine which cycles between the silence level detection routine and the listening (ready for pattern generation) routine in steps S508, S509 and S510.
- FIG. 7 shows the steps followed when the speech recognition circuit controller 60 receives a signal instructing it to activate a new recognition set.
- the present invention uses conventional silence level detection, continuous listening, pattern generation, and speech recognition algorithms to perform the aforementioned software routines. These algorithms are well documented in the prior art and are familiar to those skilled in the electronics arts. For example, exemplary speech recognition algorithms are available from Sensory, Inc., Sunnyvale, California, under their brand name Sensory Speech 5.0 Technology. Other speech recogmtion algorithms which contain some of the features in the present invention include Voice DirectTM, TSSP and Voice ActivationTM software, all available from Sensory, Inc.. Other speech recognition algorithms are also suitable. As indicated in steps S509 and S517 in FIG. 5, the speech recognition circuit software periodically monitors the status of two counter values that are independently controlled by the software.
- the speech recognition circuit 50 changes the mode of the system from speech recognition mode to sound activation mode. Otherwise, as indicated in steps S506 and S515 shown in FIG. 5, these counters are also reset to zero.
- FIG. 6 shows in a step S620 the sound activation mode is entered only from a default recognition mode. If the active recognition vocabulary set is not a default recognition vocabulary set operating in a default recognition mode, then upon attainment of a maximum allowed counter value for a time-out counter or a recognition error counter, the software will return to a default recognition mode before the sound activation mode is entered as shown by a step S620 in FIG. 6 referring to a step S505 in FIG. 5.
- Step S621 shows that when operating in a default recognition mode, and upon the attainment of the value TMAX for the sound activation time-out counter value or the value EMAX for the recognition error counter value, the speech recognition circuit 50 inactivates or disables the electronic elements that are not needed during sound activation mode, such as indicators 52a, 52b, 52c and t
- a step S622 the system enters a sound activation mode as described previously by changing the states of control register bits that disable the clock oscillator 63 from its clock source 64 and place the speech recognition circuit in a low power consuming mode and setting the mode output 65 pin to the logic state defined for sound activation mode.
- an input control for the audio switching circuit 30 is electrically connected to said mode output 65 pin which changes logic states as the speech recognition circuit changes modes between speech recognition mode and sound activation mode.
- the input control for the audio switching circuit 30 detects the logic state of the mode output pin and electrically connects the electric signal output from the microphone 20 to the sound activation circuit 40.
- the speech recognition circuit remains in this sound activation mode, listening for sound. While in the sound activation mode, the microphone 20, the audio switching circuit 30, the sound activation circuit 40 and the speech recognition circuit IC 55, as a minimum, receive electric energy from the power supply circuit 90. The microphone 20, the audio switching circuit 30, the sound activation circuit 40 and the speech recognition circuit IC 55, as a minimum, have low power consuming characteristics at least while in the sound activation mode. When the microphone 20 receives an acoustic signal from an area su ⁇ ounding the present invention, the microphone 20 converts the acoustic signal into an electric signal. The state of the audio switching circuit 30 is set to electrically connect the electric signal output from the microphone 20 to the sound activation circuit 40.
- the sound activation circuit 40 contains one or more audio amplification stages, shown in FIG. 2c, that amplify the electric signal output from the microphone 20.
- the sound activation circuit 40 also contains a trigger circuit 43 shown in FIG. 2c.
- the amplified output signal from the last audio amplification stage is electrically connected to an input of the trigger circuit. If the resulting amplified electric audio signal representing the sound received by the microphone 20 reaches a predetermined amplitude threshold equal in magnitude to a logic state change (bit transition) at the input of the trigger circuit, the sound activation circuit activates, indicating the sound has been detected at a step S625 in FIG. 6 and referring to a step S502 in FIG. 5.
- the sound activation circuit is shown in detail in FIG. 2c.
- step S518 shown in FIG. 5 when a match is identified during the pattern recognition process and the operation associated with the recognized command is an instruction to activate a different recognition vocabulary set, the software will execute the instruction to enter the appropriate recognition mode for the indicated recognition vocabulary set in step S628 shown in FIG. 7.
- Recognition modes are commercially available that are capable of executing software that involves different recognition routines, such as continuous listening, pattern queuing and response prompting recognition as described below.
- the continuous listening recognition mode was described previously in the explanation of FIG. 5 steps.
- a continuous listemng routine may also be executed for a non-default recognition vocabulary set. For brevity, an additional description of this mode is not provided. Instead, the system returns to step S505 in FIG. 5, after which the same basic process follows. The primary exception being that when the maximum allowed time-out or recognition error counter value is attained, the speech recognition circuit 50 will not enter sound activation mode, but will instead enter the default continuous listening recognition mode as indicated in a step S620 in FIG. 6.
- a response prompting recognition mode is shown in FIG. 8.
- the speech recognition circuit software activates a recognition vocabulary set and executes a response prompting routine as shown in a step S630, the user is expected to select a voice command from the active recognition vocabulary set and respond when prompted by an illuminated green light emitting diode 52b.
- a green light emitting diode 52 a remains illuminated in this mode when the speech recognition circuit 50 is available to generate patterns to indicate to the user that the active recognition mode is not the default
- a time-out counter and a recognition error counter are set to zero when the response prompting recognition mode is activated.
- the maximum allowed values for both of these counters are typically less than those for continuous listening recognition mode.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S635, S633 and S634. If a voice command is detected in a step S635, a pattern is generated in a step S636 and submitted for pattern recognition processing in a step S637.
- the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold. The result of this comparison is identified in a step S638.
- the value of the recognition e ⁇ or counter is incremented by one in a step S638 and the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified in a step S640.
- the recognition error counter value is then compared to a maximum allowed recognition error counter value EMAX1 in a step S641. If the recognition error counter value is equal to value EMAX1 , the speech recognition circuit 50 executes software stored in its ROM 61 to terminate the response prompting routine and return to a default continuous listening recognition mode as shown in a step S641 and a step S505 in FIG. 5.
- the recognition error counter value is not equal to value EMAXl , the green light-emitting diode 52b is activated and remains illuminated and the speech recognition circuit 50 executes software to enter a pattern generating mode, returning to a step S633 and waiting for a voice command to be detected. As previously indicated, until time TMAXl has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S635, S633 and S634.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command in a step S642 and determines if the operation is to send an instruction to the speech recognition circuit controller 60 to activate a new recognition vocabulary set or not. If a new recognition vocabulary set is to be activated, the software executes the instruction to enter the appropriate recognition mode for the indicated recognition vocabulary set in a step S628 shown in FIG. 7.
- a step S644 if the operation associated with the recognized command is to send an instruction to the speech recognition circuit controller 60 to output a signal to the infrared controlling circuit 70, the software uses the speech recognition circuit input/output 68 pins.
- the signal to the infrared controlling circuit communicates either a appliance category selection command in a step S645 or a command to transmit an infrared signal for a specified function to the currently controlled appliance in a step S646.
- the speech recognition circuit controller 60 executes software stored in its
- ROM 61 to determine whether to remain in the active recognition vocabulary set to receive additional voice commands or to terminate the response prompting routine and return to a default continuous listening recognition mode as shown in a step S647 and a step S505 in FIG. 5. If remaining in the active recognition vocabulary set, the software resets the values TMAXl and EMAXl to zero in a step S631, activates the response prompting green light-emitting diode 52b in a step S632 and enters a pattern generating mode in a step S633, waiting for a voice command to be detected until either TMAXl or EMAXl counter values are attained, at which time the software will terminate the response prompting routine and return to a default continuous listening recognition mode as shown in steps S634 or S641, followed by a step S505 in FIG. 5.
- pattern queuing involves the user providing a voice command after each prompt within a series of prompts. The number of prompts in the series is predetermined. A pattern is generated for each voice command as it is received, and the pattern is queued into memory. After patterns have been generated and queued into memory for all received voice commands, the voice commands are submitted one by one for recognition. Following recognition of each pattern, the operation instruction associated with the command in the active recognition vocabulary set identified as a match with the unknown pattern is queued into memory. When all patterns within the series have been recognized, and all associated operation instructions have been queued into memory, the controller
- the system utilizes a pattern queuing routine to allow a user to submit a string of consecutive voice commands, which may be separated by brief pauses, selected from a vocabulary recognition set which includes the names of digits zero through nine.
- a user submits the word "channel" during the continuous listening default routine.
- the software activates the recognition vocabulary set including digit names and initiates a pattern queuing routine, prompting the user to submit one, two or three digit names to identify a desired channel number for an appliance.
- the speech recognition circuit software activates a recognition vocabulary set and executes a pattern queuing routine as shown in a step S660
- the user is expected to select a voice command from the active recognition vocabulary set and respond when prompted by an illuminated green light emitting diode 52b.
- the green light emitting diode 52a remains illuminated in this mode when the speech recognition circuit 50 is available to generate patterns to indicate to the user that the active recognition mode is not the default recognition mode.
- a time-out counter is set to zero when the pattern queuing recognition mode is activated as shown in a step S661. However, the maximum allowed value TMAX2 for this counter is typically less than that for continuous listening recognition mode. Also at this time, a pattern counter and a queue counter are set to zero in a step S662.
- the pattern counter value is incremented each time after a pattern is generated until a maximum pattern counter value MAXP is attained. In this manner each pattern counter number value is representative of a single generated pattern and the maximum number attained by said counter is equal to the number of patterns generated.
- the value MAXP represents the maximum number of patterns the routine will generate before terminating the pattern generation process and beginning a speech recognition process.
- the mimmum value for the pattern counter before the routine will generate speech recognition processing is one. If no patterns are generated within the time allowed, then the software returns to the default continuous listening mode.
- the queue counter is utilized in a similar manner to the pattern counter, except that it is used to track operation instructions identified during a speech recognition process. As a match is identified for an unknown pattern during the pattern recognition process, the operation instruction of the associated recognition vocabulary set command determined to be the best match is queued into memory until all generated patterns are processed through the speech recognition process. In this manner each queue counter number value is representative of an operation instruction now associated with a single generated pattern and is useful in retaining sequential order during the storage and retrieval of said instruction from memory. The maximum value attained by said queue counter is equal to the number of patterns generated. Unknown patterns for which no match is identified during the speech recognition process are ignored, in which cases the queue counter is not incremented.
- the speech recognition circuit 50 software begins a listening routine (ready to generate apattem) awaiting a voice command in a step S664.
- steps S664, S665 and S670 the speech recognition circuit 50 system remains in this routine until either a voice command is detected in a step S665 or the time-out counter value reaches the value TMAX2 in step S670.
- a pattern is generated by the speech recognition circuit 50 when a voice command is detected in a step S665.
- the generated unknown pattern is queued into RAM 62 in a step S667.
- the value of the pattern counter is then compared with the value MAXP. If the pattern counter value is less than the value of MAXP, then the pattern counter value is incremented by one and the green light emitting diode 52b provides a visual prompt in a step S663 for the user to submit another voice command. This process continues to cycle through these steps S663 through S669 until either the pattern counter reaches the value MAXP in step S668, indicating the maximum number of patterns allowable have been generated, or until a time-out occurs as described previously. If a time-out does occur at a step S670, the value of the pattern counter is compared to the value zero in a step S671. If the pattern counter value is equal to zero, then the system returns to the default continuous listening mode as shown in a step S505 in FIG. 5. If the pattern counter value is not equal to zero, then patterns have been generated.
- Generated patterns are then submitted by the system for processing by the pattern recognition algorithm in a step S672, one pattern at a time, in reverse order from the pattern generation order.
- Suitable pattern recognition algorithms have been described above.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command and queues this operation instruction into RAM 62 in a step S674.
- the queue counter is then incremented by the value one in a step S675.
- the pattern counter is then decremented by the value one in a step S676.
- the pattern counter value is then compared to the value zero in a step S677 to determine if there are any unknown patterns queued in RAM 62 which have not been submitted for speech recognition processing. If the pattern counter value is not equal to zero, then the software submits the next unknown pattern for speech recognition processing in a step S678 and returns to step S672 to perform pattern recognition. The software continues to cycle through steps S672 through step S678 until the pattern counter value is equal to value zero in step S677. If a match for an acquired pattern is not identified in a step S673, the pattern counter value is decremented by one in a step S676 before proceeding to step S677.
- the software compares the queue counter value to the value zero in a step S680 in FIG. 10 to determine if there are any operation instructions queued in the RAM 62. If the value of the queue counter is not equal to the value zero, the software retrieves from RAM 62 the operation instruction associated with the current value of the queue counter in a step S681.
- the speech recognition circuit 50 executes the operation instruction in a step S682 by sending a signal through the input/outputs 68 pins to the infrared signal controlling circuit 70. The processing of said signal received by the infrared signal controlling circuit is described later.
- the speech recognition circuit 50 software then decrements the queue counter value by the value one in a step S683 and returns to step
- step S680 determines if all operation instructions have been retrieved from RAM 62.
- the software continues to cycle through steps S680 through step S683 until the queue counter value is equal to value zero in step S680 at which time the system returns to the default continuous listening mode as shown in a step S505 in FIG. 5.
- the operation instruction associated with the recognized command is processed by the speech recognition circuit controller 60 to detennine an output signal to the infrared controlling circuit 70, which is sent via the speech recognition circuit input/output 68 pins.
- the routine S690 identifies the processing steps performed within the infrared signal controlling circuit 70.
- the signal from the speech recognition circuit output 68 pins is received by inputs of the infrared signal controlling circuit 70 and processed to determine the associated remote control function in a step S691.
- the output from the speech recognition circuit output 68 pins provides a signal that is the informational equivalent to that of a signal generated when a button is depressed on a keypad of a conventional remote control transmitter.
- the input to the controller of the infrared signal controlling circuit 70 can be uniquely associated with a function similarly to the input received from a conventional keypad generated circuit connection.
- the controller of the infrared signal controlling circuit 70 interprets the signal received at its input pin(s) by identifying a memory location in a step S692 and retrieving the control code stored therein. This controller generates a signal based upon the control code in a step S693 and submits the signal to an infrared driver 74, which drives one or more infrared light emitting diodes 80 in a step S694.
- the infrared light emitting diode 80 converts the electrical signal into an infrared signal which is transmitted to one or more target appliances in a step S695.
- an interface is provided as part of the infrared signal controlling circuit 70.
- the interface simulates the function of a switch matrix, comiecting one or more inputs of the controller of the infrared signal controlling circuit 70 to one or more of its outputs as typically results when a keypad button is depressed.
- the interface allows electrical connections to be established, similar to a keypad button depression, between inputs and outputs of the controller of the infrared signal controlling circuit 70.
- One embodiment of the interface includes a programmable logic device as discussed above and is shown in FIG.2b, described above. The interface provides an advantage since it is programmable and thus can be easily modified for use with a variety of controllers for infrared signal controlling circuits 70.
- the recognition of a single voice command may generate a series of control signals to one or more target appliances.
- Such a sequence of control signals is hereafter refe ⁇ ed to as a macro.
- Each macro must be created by the user during a product setup process described below.
- Macros may contain operation instructions for appliance category selection, infrared signal codes and/or time delays. Macros are stored in the read/write memory 54 controlled by the speech recognition circuit 50 and may be associated with a user trained speaker dependent command.
- the speech recognition circuit 50 software retrieves the first instruction stored in the read/write 54 memory location associated with the recognized command. If the instruction retrieved is determined to be a time delay in a step S701, the software executes a time delay in a step S702 and returns to step S700 to retrieve the next instruction from memory. If the instruction is not a time delay, the speech recognition circuit 50 software sends a signal utilizing the speech recognition circuit input/output 68 pins to the infrared signal controlling circuit 70 in step S703.
- step S704 after a signal is sent to the infrared signal controlling circuit 70, the software returns to the read/write 54 memory location associated with the recognized command to determine if another instruction is to be retrieved and processed. If so, the system retrieves the instruction, returning to step S700. The system continues to cycle through steps S700 through step
- step S704 until an end marker is reached by the software in the memory location in a step S704, at which time the system returns to the default continuous listening mode as shown in step S505 in FIG. 5.
- the output from the speech recognition circuit input/output 68 pins provides sufficient information to the infrared signal controlling circuit 70 to generated a signal that is equivalent to that generated when a button is depressed on a keypad of a conventional remote control transmitter.
- the routine S710 identifies the processing steps performed within the infrared signal controlling circuit 70.
- the signal from the speech recognition circuit input/output 68 pins is received by inputs of the infrared signal controlling circuit 70. If the signal contains an instraction to select an appliance category in a step S711, the infrared signal controlling circuit 70 responds in a step S712 by making the memory locations associated with said appliance category active for subsequent access.
- the infrared signal controlling circuit 70 performs these processes as indicated in steps S713 through S717.
- the controller of the infrared signal controlling circuit 70 interprets the signal received at its input pins in a step S713 and identifies a memory location in a step S714, retrieving the control code stored therein.
- This controller generates a signal based upon the control code in a step S715 and submits the signal to an infrared driver 74, which drives an infrared light emitting diode 80 in a step S716.
- the infrared light emitting diode 80 converts the electrical signal into an infrared signal which is transmitted to one or more target appliances in a step S717.
- a mute operation sequencing feature may be selected, activated, and operated by a user in a completely hands-free manner. For example, a voice command such as "mute” may be added to a "Control" recognition vocabulary set, and each time “mute” is recognized by the system while the "Control" recognition vocabulary set is active, the software will sequence through different values of a muting mode variable MMN. Each value of MMN represents a submode with respect to an automated mute command sequencing feature. In a first mode OFF, the automated mute command sequencing feature is disabled and the system operates as described previously.
- a muting signal is generally issued to a controlled appliance when the unit is activated from sound activation mode and enters speech recognition mode to aid subsequent speech recognition by reducing background noise generated by a controlled appliance.
- a mute canceling signal may later be automatically issued to the controlled appliance following the recognition of one or more predetermined spoken commands or, for example, when certain conditions are met such as attainment of a predetermined time-out counter value and/or attainment of a predetermined recognition counter value.
- recognition error muting mode REM a muting signal is automatically issued to a controlled appliance upon the detection of one or more types of recognition errors.
- the recognition errors causing such action may be limited to only specific error types such as that generated when the continuous listening algorithm detects that environmental noise is loud enough to potentially diminish the accuracy of subsequent speech recognition.
- a mute canceling signal may be generated similarly to that of the AMM mode described above. Once a muting mode is selected, the software will remain in that mode until intentionally changed by the user. In addition to the variable MMN, the software may also utilize one or more variables to track the muted/non-muted status MS of the controlled appliance at any particular time.
- Values for the variable MS may represent a "no muting activated" status ⁇ MA that indicates the controlled appliance is not muted, an "automated muting activated” status AMA that indicates an automated mute signal has been sent to the controlled appliance and the appliance is currently muted, and a "command muting activated” status CMA that indicates that the user has issued a voice command such as "Sound” to intentionally mute the controlled appliance.
- the software is executing the default continuous listening recognition mode while MMV is set to mode AMM or mode REM, and MS indicates that a NMA status exists
- the successful recognition of predetermined voice commands associated with vocabulary recognition set "sub-menus” may also cause a muting signal to be issued, causing the controlled appliance to remain muted during the recognition processing of commands selected from said sub-menus and spoken by the user.
- a mute canceling signal is automatically sent to the controlled device.
- FIGURES 5 through 11 Reference is made to FIGURES 5 through 11 to further describe the automated mute sequencing feature. If the MMV is set to OFF mode the software performs as described in the previous explanations associated with these figures. If the MMV is set to mode AMM or mode REM, the software follows the processes shown in FIGURES 5 through
- the software checks the status of MS if the MMV is set to mode AMM, then in addition to the activities previously described for a step S505, the software also checks the status of MS if the MMV is set to mode AMM.
- MS is set to CMA status
- a voice command such as "Sound” has previously been recognized by the speech recognition software, which indicates a user desires that the controlled appliance remain muted.
- MS is set to CMA status
- no subsequent automatic muting signals will be issued until the user sets MS to a status other than CMA, which may be accomplished, for example, by the next recognition of the voice command "Sound.”
- MS is set to AMA status
- a muting signal is automatically sent to the controlled appliance, with the infrared signal generated in the manner described in previous explanations.
- the software executes a default continuous listening recognition mode as shown in steps S506 through S517 and described previously.
- the software periodically monitors the status of independent time-out and recognition error counters to determine when to return to sound activation mode. If a predetermined time value TMM elapses before a spoken command is detected, as shown in a step S509, then a mute canceling signal is sent to the controlled appliance and the software follows steps S620 through S626 shown in FIG. 6 to return to sound activation mode. Similarly, if a predetermined maximum number of recognition e ⁇ ors EMM is attained as shown in a step S517, then a mute canceling signal is sent to the controlled appliance and the software follows steps S620 through S626 shown in FIG. 6. If a match for a spoken command is identified in a step S514 shown in FIG.
- the software determines if the operation associated with the recognized command is an instraction to activate a different recognition vocabulary set or an instruction to output a signal to the infrared controlling circuit 70. If an instruction is to be sent to the infrared controlling circuit 70, then a mute canceling signal is automatically sent to the controlled appliance prior to said instraction being sent, unless the instraction is associated with a recognized command such as "Sound," which indicates the user desires the controlled device remain muted. In this case, recognition of the command "Sound" would cause variable MS to be set to CMA status as described above.
- the software determines that the operation associated with the recognized command is an instruction to activate a different recognition vocabulary set, the software then proceeds to a step S628 shown in FIG. 7 to determine the appropriate recognition mode and then proceeds appropriately to FIGURE 5, 8 or 9 as described in the previous explanations associated with these figures.
- the software continues to follqw the steps shown in FIGURES 5 through 11 until returning to the default continuous listening recognition mode as shown in a step S620 of FIG. 6, steps S634, S641 and S647 of FIG. 8; step S671 of FIG. 9; step S680 of FIG.
- a mute canceling signal is sent to the controlled appliance.
- An alternative mute canceling sequence may be employed for some recognition modes. For example, during pattern queuing recognition mode, it may be advantageous to issue a mute canceling signal prior to the software's return to the default continuous listening recognition mode. In this case, the mute canceling signal may be issued at a step S677 of FIG. 9 when the software has determined that all queued patterns have been recognized.
- This approach reduces the time the controlled appliance remains muted and prevents certain command functions, such as a volume increase function, from causing the MS variable to lose synchronization with the controlled appliance's mute status. Appliances in a muted condition are commonly removed from said muted condition upon receipt of certain signals such as a volume increasing signal.
- the software may issue the mute canceling signal and then issue the volume control commands to increase the volume of the controlled appliance by three level adjustments.
- the software returns to the default continuous listening recognition mode from another recognition mode and variable MS indicates a NMA status, subsequent recognition of voice commands associated with sub-menu recognition vocabulary sets may cause an automatic muting signal to be generated and sent to a controlled appliance.
- this capability allows recognition processing of subsequent spoken commands selected from the associated recognition vocabulary set to be performed in a noise-reduced environment, thus improving recognition accuracy. For example, upon recognition of a command "Change" contained within the default mode recognition vocabulary set, the software automatically issues a muting signal to the controlled appliance prior to entering the recognition mode associated with the "Change" recognition vocabulary set.
- a mute canceling signal may then be issued, automatically returning the controlled appliance to a non-muted condition.
- the recognition error detection automatic muting mode REM operates in the same fashion as the mode AMM except that a muting command is not automatically issued as the system transitions from sound activation mode to speech recognition. Instead, when the software is executing the default continuous listening recognition mode and a recognition error is detected, a muting signal is automatically sent to the controlled appliance. As indicated above, the recognition errors causing such action may be limited to only specific types such as that generated when the continuous listening algorithm detects that environmental noise is loud enough to potentially diminish the accuracy of subsequent speech recognition. A mute canceling signal may be generated using the same means as described above.
- one of the buttons present on keypad 51 controls the state of a power switch. If the power switch is open as shown in a step S202, the power source is not electrically connected to sections of the power supply circuit 90 which have electrical connections to certain circuit elements and therefore, these circuit elements do not receive electric energy. When this power switch is closed, the power source is electrically connected to sections of the power supply circuit 90 which have electrical comiections to certain circuit elements and therefore, these circuit elements do receive electric energy.
- Step S203 shows that when the power supply button is momentarily depressed and the power switch is placed into a closed state, the speech recognition controller 60 executes a reset, sets a time-out counter to value zero and starts the time-out counter, which increments as time elapses.
- controller 60 enters a waiting state where it monitors input 68 pins to determine if inputs are received from depressed buttons located on keypad 51.
- step S214 the controller 60 executes code stored in ROM 61 to enter an appliance category selection routine shown in step S220 in FIG. 12b, which is described later.
- FIG. 13a through FIG 13c show the sequence of steps involved in programming such appliance codes.
- FIG. 14a and FIG 14b show the sequence of steps involved in learning infrared codes.
- FIG. 15 shows the sequence of steps involved in user voice training for custom names. If the user desires to create a macro program as shown in a step S212, the user presses the macro button as shown in step S213.
- FIG. 16a and FIG. 16b show the sequence of steps involved in creating macro programs.
- a reset as shown in step S203 may also be initiated when the invention is powered up and operating by depressing the setup button as shown in step S204. This reset follows the same sequence as that resulting from an initial power up as shown in steps S203 through in FIG. 12a and FIG. 12b.
- the controller 60 executes code stored in ROM 61 to enter an appliance category selection routine shown in step S220 in FIG. 12b.
- a response prompting recognition mode for appliance category selection is shown in FIG. 12b.
- the speech recognition circuit 50 software executes a response prompting routine as shown in a step S221 and activates the appliance category name recognition vocabulary set as shown in step S222.
- a time-out counter is set to zero and started in a step S223 when the response prompting recognition mode is activated.
- the user is then expected to select a voice command from the appliance category name recognition set and respond when prompted by an illuminated green light emitting diode 52a as shown in a step S224.
- the appliance category name recognition set may be comprised of such voice command options as "television,” "video,” “satellite,” and "cable” among which the user may select.
- the system Following the prompting of the user by the illumination of a green light emitting diode 52a in a step S224, the system enters a pattern generating mode in a step S225, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXD is attained before a voice command is detected, the software will terminate the response prompting routine and enter the default continuous listening recognition mode as shown in a step S226. Until time TMAXD has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S225, S226 and S227. If a voice command is detected in a step S227, a pattern is generated in a step S228 and submitted for pattern recognition processing in a step S229.
- step S229 the acquired unknownpattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined tlireshold. The result of this comparison is identified in a step S230.
- the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified and the value of the recognition time-out counter is reset to the value zero and restarted as shown in a step S223.
- the green light-emitting diode 52a is then activated and remains illuminated as shown in step S224 and the speech recognition circuit 50 executes software to enter, apattem generating mode, returning to a step S225 and waiting for a voice command to be detected.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S225, S226 and S227rada
- the speech recogmtion circuit 50 software identifies the instruction associated with the matching recognition vocabulary set command, and issues a prompt, which may be a speech synthesis prompt, an audio sound or light-emitting diode indication, in a step S231 to identify the appliance category name recognized.
- the speech recognition circuit 50 then outputs a signal to the infrared controlling circuit 70, using output 68 pins to communicate the appliance category selection command in a step S232.
- the infrared controlling circuit 70 receives the signal and responds as shown in step S233 by making the memory section associated with the appliance category selected available for access.
- step S234 the speech recognition circuit controller 60 executes software stored in its ROM 61 to return to a default continuous listening recognition mode as shown in a step S234 and a step S505 in FIG. 5. If the appliance category name identified in step S231 is incorrect, step S234 also shows that the user may elect to press the setup button, returning to step S204 in FIG. 12a and begin the process again.
- buttons and speech recognition during some of the product setup processes
- functions performed by depressing such buttons as the code button, learn signal button, name command button and macro buttons may also be performed through the use of speech recognition means disclosed herein.
- the linked recognition vocabulary set structure disclosed may be used to accommodate hands-free setup of the product in addition to the hands-free activation and operation features.
- a command such as "Setup” may be added to a "Control" recognition vocabulary set sub-menu described later in this disclosure.
- a recognition vocabulary set specific to product setup commands may be activated and contain such command options as "Code,” “Learn Signal,” “Name Command,” and “Macro.”
- a response prompting recognition mode may be used to activate this recognition vocabulary in the same manner described previously.
- step S207 in FIG. 12a If the controller 60 detects an input corresponding to a depress of the code button shown in step S207 in FIG. 12a, a signal is sent to the infrared signal controlling circuit 70, using output 68 pins to instruct the infrared signal controlling circuit to enter aprogramming mode.
- the controller of the infrared controlling circuit executes aprogramming routine from software stored within its ROM, which includes setting to value zero and starting a programming time-out counter in a step S241.
- the programming routine prepares the controller of the infrared signal controlling circuit 70 for subsequent receipt of a series of instructions.
- a first instruction identifies the intended appliance category, which is then followed by a series of instructions, where each instruction represents an identifier digit of an appliance code.
- the appliance code is comprised of a predetermined number of said identifier digits and uniquely identifies a specific control code set of the remote control command codes for a particular appliance.
- the controller of the infrared signal controlling circuit 70 receives instructions identifying all the identifier digits of an appliance code, it is capable of identifying the memory location within the universal appliance code library stored within its ROM where the remote control command codes for the intended appliance type are stored. The control codes are then made available for subsequent signal transmission and resulting control of the intended appliance.
- universal remote controls employing such universal appliance code libraries are well documented in prior art.
- the controller of the infrared controlling circuit 70 illuminates red light- emitting diode 52d during the programming mode period.
- the speech recognizing circuit controller 60 executes code stored in ROM 61 to enter a response prompting recognition mode for appliance category selection shown in step S242.
- the speech recognition circuit 50 software executes a response prompting routine and activates the appliance category name recognition vocabulary set as shown in step S243.
- a time-out counter is set to zero and started in a step S244 when the response prompting recognition mode is activated.
- the user is then expected to select a voice command from the appliance category name recognition set and respond when prompted by an illuminated green light emitting diode 52 a as shown in a step S245.
- the appliance category name recognition set may be comprised of such voice command options as "television,” "video,” “satellite,” and "cable” among which the user may select.
- the software Following the prompting of the user by the illumination of a green light emitting diode 52a in a step S245, the software enters a pattern generating mode in a step S246, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXD is attained before a voice command is detected, the software will terminate the response prompting routine, and the programming time-out counter is allowed to expire as shown in step S292. Until time TMAXD has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S246, S247 and S248. If a voice command is detected in a step S248, a pattern is generated in a step S249 and submitted for pattern recognition processing in a step S250.
- step S250 the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61 , to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold. The result of this comparison is identified in a step S251.
- the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified and the value of the recognition time-out counter is reset to the value zero and restarted as shown in a step S244.
- the green light-emitting diode 52a is then activated and remains illuminated as shown in step S245 and the speech recognition circuit 50 executes software to enter a pattern generating mode, returning to a step S246 and waiting for a voice command to be detected.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S246, S247 and S248.
- the speech recognition circuit 50 software identifies the instraction associated with the matching recognition vocabulary set command, and issues a prompt, which may be a speech synthesis prompt, an audio sound or light-emitting diode indication, in a step S252 to identify the appliance category name recognized.
- the speech recognition circuit 50 then outputs a signal to the infrared controlling circuit 70, using output 68 pins to communicate the appliance category selection command in a step S253.
- the infrared controlling circuit 70 receives the signal and responds by making the memory section associated with the appliance category selected available for access in a step S254.
- the infrared controlling circuit 70 then sets equal to value zero and restarts the programming time-out counter in a step S256.
- step S257 the speech recognition circuit controller 60 executes software stored in its ROM 61 to enter a pattern queuing recognition mode as shown in a step S257 and to activate the digits recognition set as shown in step S258. If the appliance category name identified in step S252 is incorrect, step S255 shows that the programming time-out counter is allowed to expire as shown in step S292, before returning to step S204 in FIG. 12a and beginning the process again.
- the speech recognition circuit software executes a pattern queuing routine and activates the digit name recognition vocabulary set.
- the digit name recognition set may be comprised of such voice command options as "zero,” “one,” “two,” ... "nine” among which the user may select.
- a time-out counter is set to value zero and started when the pattern queuing recognition mode is activated as shown in a step S260 in FIG.
- a pattern counter and a queue counter are set to value zero in a step S261.
- the user selects an appliance code from a listing of the universal library of code supplied with the system and issues a spoken command identifying the first digit of the code when prompted by an illuminated green light emitting diode 52b as shown in a step S262.
- the pattern counter value is incremented each time after a pattern is generated until a maximum pattern counter value MAXC is attained.
- each pattern counter number value is representative of a single generated pattern and the maximum number attained by said counter is equal to the number of patterns generated.
- the value MAXC represents the maximum number of patterns the routine will generate before terminating the pattern generation process and beginning a speech recognition process.
- the minimum value for the pattern counter before the routine will generate speech recognition processing is one. If no patterns are generated within the time allowed, then the software returns to the default continuous listening mode as described later.
- the queue counter is utilized in a similar manner to the pattern counter, except that it is used to track operation instractions identified during a speech recognition process. As a match is identified for an unknown pattern during the pattern recognition process, the operation instraction of the associated recognition vocabulary set command determined to be the best match is queued into memory until all generated patterns are processed through the speech recognition process. In this manner each queue counter number value is representative of an operation instraction now associated with a single generated pattern and is useful in retaining sequential order during the storage and retrieval of said instraction from memory. The maximum value attained by said queue counter is equal to the number of patterns generated. Unknown patterns for winch no match is identified during the speech recognition process are ignored, in which cases the queue counter is not incremented.
- the speech recognition circuit 50 software begins a listening routine (enters a state where it remains ready to generate a pattern) awaiting a voice command in a step S263. As shown in steps S263, S264 and S265, the speech recognition circuit 50 software remains within said routine until either a voice command is detected in a step S264 or the time-out counter value reaches the value TMAX2 in step S265. As shown in a step S266 a pattern is generated by the speech recognition circuit
- the value of the pattern counter is then compared with the value MAXC. If the pattern counter value is less than the value of MAXC, then the pattern counter value is incremented by one in a step S269 and the green light emitting diode 52b provides a visual prompt in a step S262 for the user to submit another voice command. This process continues to cycle through these steps S262 through S269 until either the pattern counter reaches the value MAXC in step S268, indicating the maximum number of patterns allowable have been generated, or until a time-out occurs as described previously. If a time-out does occur at a step S265, the user allows the programming time-out counter to expire as shown in step S292 in FIG. 13c, before returning to step S204 in FIG. 12a and beginning the process again or allowing the invention to automatically enter the default recognition mode.
- Generated patterns are then submitted by the software for processing by the pattern recognition algorithm in a step S270, one pattern at a time, in reverse order from the pattern generation order.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command and queues this operation instruction into RAM 62 in a step S272.
- the queue counter is then incremented by the value one in a step S273.
- the pattern counter is then decremented by the value one in a step S274.
- the pattern counter value is then compared to the value zero in a step S275 to determine if there are any unknown patterns queued in RAM 62 which have not been submitted for speech recognition processing. If the pattern counter value is not equal to zero, then the software submits the next unknown pattern for speech recognition processing in a step S276 and returns to step S270 to perform pattern recognition. The software continues to cycle through steps S270 through step S276 until the pattern counter value is equal to value zero in step S275. If a match for an acquired pattern is not identified in a step S271, the pattern counter value is decremented by one in a step S274 before proceeding to step S275.
- the software compares the queue counter value to the value zero in a step S280 in FIG. 13c to determine if there are any operation instractions queued in the RAM 62. If the value of the queue counter is not equal to the value zero, the software retrieves from RAM 62 the operation instraction associated with the current value of the queue counter in a step S282.
- the speech recognition circuit 50 executes said operation instraction in a step S283 by sending a signal through the outputs 68 pins to the infrared signal controlling circuit 70. The processing of said signal received by the infrared signal controlling circuit is described later.
- the speech recognition circuit 50 software then decrements the queue counter value by the value one in a step S284 and returns to step
- step S280 determines if all operation instractions have been retrieved from RAM 62.
- the software continues to cycle through steps S280 through step S284 until the queue counter value is equal to value zero in step S280 at which time the software issues a prompt, which may be a speech synthesis prompt, an audio sound or light-emitting diode indication, in a step S281 to identify the appliance code recognized, and then enters the default continuous listening mode as shown in a step S505 in FIG. 5.
- a prompt which may be a speech synthesis prompt, an audio sound or light-emitting diode indication
- the operation instraction associated with the recognized command is processed by the speech recognition circuit controller 60 to determine an output signal to the infrared controlling circuit 70, which is sent via the speech recognition circuit output 68 pins.
- the signal from the speech recognition circuit output 68 pins is received by inputs of the infrared signal controlling circuit 70 and processed to determine an identifier associated with a recognized digit name in a step S286.
- the output from the speech recognition circuit output 68 pins is equivalent to a signal generated when a button is depressed on a keypad of a conventional remote control transmitter.
- the controller of the infrared signal controlling circuit 70 stores the identifier associated with the signal received in a memory location in a step S287. Identifiers are determined and stored for each instruction received from the speech recognition circuit
- step S288 The set of identifiers are then analyzed by the controller of the infrared controlling circuit 70 to determine if a they collectively comprise a valid appliance code in a step S289. If a valid code exists, the remote control functions associated with that code are assigned to the previously identified appliance category in a step S293 and the programming mode is terminated in a step S294.
- step S290 If the code is not valid, the code is not accepted in a step S290 and any previously established code remains active. Light-emitting diode 52d illuminates in a step S291 and the programming time-out counter is allowed to expire in a step S292.
- FIG. 13c also shows that, as the programming time-out counter is allowed to expire, the time-out counter for the speech recognition circuit 50 is also allowed to expire, after which the speech recognition circuit 60 executes software stored in its ROM 61 to return to a default continuous listening recognition mode.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to return to a default continuous listening recognition mode as « shown in a steps S281 in FIG. 13c and a step S505 in FIG. 5. If the appliance category name identified in step S281 is incorrect, the user may elect to press the setup button, returning to step S204 in FIG. 12a and begin the process again.
- step S300 in FIG. 14a the controller of the infrared controlling circuit executes a learning program routine from software stored within its ROM, which includes setting to value zero and starting a programming time-out counter in a step S301.
- the signal learning program routine prepares the controller of the infrared signal controlling circuit 70 for subsequent receipt of a series of instructions.
- a first instruction identifies the intended appliance category, which is then followed by instractions to enter infrared signal learning mode.
- learning remote controls are well documented in prior art, for example as disclosed in U.S. Patent Nos. 4,905,279 and 5,959,751, hereby incorporated by reference.
- the controller of the infrared controlling circuit illuminates red light- emitting diode 52d in different manners to communicate the status of the signal learning process to the user during this programming mode.
- the speech recognizing circuit controller 60 executes code stored in ROM 61 to enter a response prompting recognition mode for appliance category selection shown in step S302.
- the speech recognition circuit 50 software executes a response prompting routine and activates the appliance category name recognition vocabulary set as shown in step S303.
- a time-out counter is set to zero and started in a step S304 when the response prompting recognition mode is activated.
- the user is then expected to select a voice command from the appliance category name recognition set and respond when prompted by a speech synthesis prompt, an audio sound and/or the illumination of a green light emitting diode 52a as shown in a step S305.
- the appliance category name recognition set may be comprised of such voice command options as "television,” “video,” “satellite,” and “cable” among which the user may select.
- the software enters a pattern generating mode in a step S306, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXD is attained before a voice command, is detected, the software will terminate the response prompting routine and return to a default continuous listening recognition mode, and the programming time-out counter is allowed to expire as shown in step S292 as shown in FIG. 13c.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S306, S307 and S308. If a voice command is detected in a step S308, a pattern is generated in a step S309 and submitted for pattern recognition processing in a step S310.
- the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to dete ⁇ nined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold. The result of this comparison is identified in a step S311.
- the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified and the value of the recognition time-out counter is reset to the value zero and restarted as shown in a step S304.
- the green light-emitting diode 52a is then activated and remains illuminated as shown in step S305 and the speech recognition circuit 50 executes software to enter a pattern generating mode, returning to a step S306 and waiting for a voice command to be detected.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S306, S307 and S308.
- the speech recognition circuit 50 software identifies the instruction associated with the matching recognition vocabulary set command, and issues a prompt, which may be a speech synthesis prompt, an audio sound or light-emitting diode indication, in a step S312 to identify the appliance category name recognized.
- the speech recognition circuit 50 then outputs a signal to the infrared controlling circuit 70, using output 68 pins to communicate the appliance category selection command in a step S313.
- the infrared controlling circuit 70 receives the signal and responds by making the memory section associated with the appliance category selected available for access in a step S314.
- the infrared controlling circuit 70 then sets equal to value zero and restarts the programming time-out counter in a step S317.
- step S316 shows that the programming time-out counter is allowed to expire as shown in step S292 shown in FIG. 13c, before returning to step S204 in FIG. 12a and beginning the process again.
- 13c also shows that, as the programming time-out counter is allowed to expire, the time-out counter for the speech recognition circuit 50 is also allowed to expire, by reaching the value TMAXD, after which the speech recognition circuit 60 executes software stored in its ROM 61 to return to a default continuous speech recognition mode.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to enter a default recognition mode and to activate a default recognition vocabulary set as shown in a step S320 in FIG. 14b.
- This default recognition vocabulary set is made available to enable the user to navigate the recognition vocabulary stracture via spoken commands to identify a command with which to associate the next infrared signal to be learned.
- a recognition time- out counter is set to zero and started in a step S321 when the default recognition mode is activated.
- the user is then expected to select a voice command from the default recognition vocabulary set and respond when a green light emitting diode 52a is illuminated as shown in a step S322.
- the default recognition vocabulary set may be comprised of such voice command options as "power,” “channel,” “change,” “volume,” “sound,” “control” and “private” among which the user may select.
- the software Following the prompting of the user by the illumination of a green light emitting diode 52a in a step S322, the software enters a mode where it is available for pattern generating in a step S323, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXL is attained before a voice command is detected, the software will terminate the speech recognition routine and return to a default continuous listening recognition mode, and the programming time-out counter is allowed to expire as shown in step S292 shown in FIG. 12c. Until time TMAXL has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S323, S324 and S325. If a voice command is detected in a step S325, a pattern is generated in a step S326.
- the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the default recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold.
- the result of this comparison is identified in a step S328.
- the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that ito ⁇ ratch was identified and the value of the recognition time-out counter is. reset to the value zero and restarted as shown in a step S321.
- the green light-emitting diode 52a is then activated and remains illuminated as shown in step S322 and the speech recognition circuit 50 executes software to enter apattem generating mode, returning to a step S323 and waiting for a voice command to be detected.
- the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S323, S324 and S325.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command in a step S329 and determines if the operation is to send an instraction to the speech recognition circuit controller 60 to activate a different recognition set vocabulary or to output a signal to the infrared controlling circuit 70 using the speech recognition circuit output 68 pins. If the instruction is to activate a different recognition vocabulary set, step S330 shows that the routine returns to a step S320. The user may continue to navigate through different linked, recognition vocabulary sets until a voice command is recognized that is associated with a remote control function that is associated with a read/write memory 72 location.
- the operation involves sending a signal to the infrared signal controlling circuit as shown in a step S331, said signal communicates an instraction for a remote control function type that is associated with a memory location within read/write memory 72, controlled by the infrared signal controlling circuit 70.
- the controller of the infrared signal controlling circuit 70 identifies said memory location and targets this memory location for storage of an infrared code to be received as shown in a step S332.
- the controller of the infrared signal controlling circuit 70 activates a red light-emitting diode 52d in a step S333 to prompt a user that it is ready to receive a transmitted infrared code and enables one or more of its input pins to detect and receive signals generated by the infrared receiver 71, which is electrically connected to one or more of said input pins.
- infrared receiver 71 is a commercially available photo IC capable of providing digital output to the controller of the infrared signal controlling circuit 70.
- Alternative schemes, utilizing other infrared light detecting devices with or without signal processing circuitry, may also be used as the IR receiver 71.
- the infrared signal is received from the TR receiver 71 of the present invention by the controller of the infrared signal controlling circuit 70 as digital data.
- the controller of the infrared signal controlling circuit 70 decodes and .converts the received digital data into a control code format and stores the resulting control code into a memory location within read/write memory 72, controlled by the infrared signal controlling circuit 70.
- the memory location is associated with the remote control function type associated with the recognized voice command spoken by the user.
- the controller of the infrared signal controlling circuit 70 activates a red light-emitting diode 52d in a step S335 to inform the user if the infrared signal learning process was capable of successfully receiving, formatting and storing the infrared signal or not.
- This red light-emitting diode 52d provides prompts in different manners to distinguish between a successful learning process and a process during which an error was encountered.
- a successfully learned and stored infrared signal may be later transmitted by the invention while in an operation mode upon recognition of the voice command with which the learned infrared signal is associated.
- the controller of the infrared signal controlling circuit executes software stored within its ROM to reset to value zero and start the programming time-out counter, returning to a step S317 shown in FIG. 14a. Also, following the submission of a signal to the infrared signal controlling circuit 70, the speech recognition circuit controller 60 executes software stored in its
- ROM 61 to return to the default recognition mode and reset the value TMAXL to zero as shown in steps S331 and S320.
- a user may elect to either return to the previous process steps to repeat a previously failing signal learning attempt or to attempt to learn additional infrared signals or the user may elect to allow the programming time-out counter of the infrared signal controlling circuit 70 to expire as shown in step S292 shown in FIG. 12c.
- the invention exits this setup programming mode and enters a default recognition mode, where it becomes available to receive spoken commands from the user and respond by transmitting infrared control signals to appliances, including any infrared signals learned during a infrared signal learning setup process as described above.
- a speaker dependent command voice training routine is initiated and executed by said controller as shown in a step S340 in FIG. 15.
- This training routine generates and stores into read/write memory 54 a user- specific reference pattern for each voice command to be included in a speaker dependent recognition vocabulary set.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to set to value zero and start a training program time-out counter as shown in a step S341.
- the software Following the prompting of the user by a speech synthesis prompt, an audio sound and/or the illumination of a green light emitting diode 52a in a step S342, the software enters a mode where it is available for pattern generating in a step S343, waiting for a voice command to be detected. If a maximum allowed time-out value
- TMAXV is attained before a voice command is detected, the software will terminate the voice training as shown in step S345 and enter a default speech recognition operation mode which is described previously. Until time TMAXV has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S343, S344, S345 and S346. If a voice command is detected t in a step S344, a pattern is generated in a step S346.
- One embodiment of the invention executes a speaker dependent reference pattern generation algorithm that is well l ⁇ iown to those familiar with speech recognition art.
- the algorithm involves the generation of a pattern each time a voice command is spoken by a user.
- a pattern is a compact representation of the significant acoustic information in a voice command word or phrase.
- a reference pattern may be, for example, created by averaging patterns generated as the voice command is spoken two or more times.
- the reference pattern is then stored in a read/write memory 54. As shown in a step S347 and S348, the first pattern generated is stored into a read/write memory 54 location.
- the user is then prompted in a step S349 to repeat the voice command, returning to step S341 and continuing through step S346 to perform the pattern generation process for the repeated voice command.
- the second pattern is then compared to the first pattern which is stored in read/write memory 54 to determine if the two patterns match sufficiently to satisfy a predetermined matching criteria as shown in a step S350. If the matching criteria is not satisfied, the two patterns are determined to not match, and the first pattern generated is replaced by storing the second pattern generated into the previously identified read/write memory 54 location, and thus overwriting the first pattern.
- the user is then prompted in a step S349 to repeat the voice command, returning to step S341 and continuing through step S346 to perform the pattern generation process for the repeated voice command. As shown by steps S341 through S350 this process cycle maybe continued until two patterns are generated which are capable of meeting said matching criteria.
- a reference pattern is generated as shown in step S351.
- a pattern recognition routine is then executed to compare the resulting reference pattern to any other previously generated reference patterns within the intended recognition vocabulary set which are stored in read/write memory 54 to determine if the new reference pattern is sufficiently different than said previously generated reference patterns. This comparison is performed to prevent the acceptance of similar voice commands, which may reduce the recognition accuracy rate.
- the comparison may calculate distance measurements of the fit of the newly generated reference pattern to the previously generated reference patterns within the intended recognition vocabulary set. The distance measurements between the newly generated reference pattern and the closest matching previously generated reference pattem(s) may then be compared to a predetermined comparison criteria to determine the degree of similarity.
- step S353 If the newly generated reference pattern is too similar to an existing reference pattern, the newly generated reference pattern is rejected, and the user is prompted in a step S353 to select a different voice command name, returning to step S341. If the newly generated reference pattern is not found to be too similar to an existing reference pattern, the newly generated reference pattern is compressed and stored into read/write memory 54 as shown in a step S354. In a step S355, the speech recognition circuit controller 60 executes software stored in its ROM 61 to determine if sufficient capacity remains in read/write memory 54 to allow additional voice commands to be trained. If there is sufficient capacity in the memory 54, the system returns to step
- step S341 where the user is prompted to enter another voice command by a speech synthesis prompt, an audio sound and/or the illumination of a green light emitting diode 52a. If the user desires to exit this voice training mode, the user allows the training program time-out counter to expire as shown in a step S356. If there is insufficient capacity in the memory 54, the user is informed accordingly by a speech synthesis prompt, an audio sound and/or the illumination of a red light emitting diode 52c and the training program terminates.
- the contents of the read/write memory 54 may be erased by depressing and simultaneously holding the name command button and the code button for a brief period of time. Depressing and momentarily holding two predetermined buttons on keypad 51 may cause the address pointer for the read/write memory 54 to be set to zero, allowing any data previously stored within said memory to be overwritten during subsequent write operations to said memory. This enables a user to effectively "erase” this memory and store different data in a form of speech command reference pattern data and macro program instraction data.
- the read/write memory 54 utilized in the preferred embodiment of the present invention may be a commercially available I 2 CTM Serial EEPROM, for example a model number 24LC64 available from Microchip Technology Inc. and described in a data sheet entitled; 24AA64/24LC64 64K I 2 CTM CMOS Serial EEPROM. document number DS21189C published by Microchip Technology Inc. copyright 1999, pages 1-
- buttons 12 available fromMicroChip Technology Inc., hereby incorporated by reference.
- two input pins 68 of IC 55 which are electrically connected to said buttons are brought to a logical low state.
- the software stored in ROM 61 of the speech recognition circuit 50 executes a program which detects this condition and responds by setting the address pointer for the next available address location for memory 54 to value zero and storing this value in the predetermined address pointer location of said memory 54.
- the next attempt by the speech recognition circuit software to store data to said memory 54 will retrieve the value of the address pointer for the next available location from said predetermined location within memory 54, and interpret the value zero as an instruction to begin storing data in the first address configured to accept data.
- step S361 the system executes an appliance category selection routine as described in step S220 in FIG. 12b to identify the appliance category from which the macro will be activated when the macro name is later recognized by the speech recognition circuit 50 as a voice command. If the appliance category name identified during the execution of the appliance category selection routine is inconect, step S362 shows that the user may elect to press the setup button, returning to step S204 in FIG. 12a and begin the process again.
- a step S362 shows that the software enters a speaker dependent recognition mode in a step S363 and a speaker dependent recognition vocabulary set is activated in a step S364.
- the speaker dependent recognition vocabulary set activated may contain one or more macro names, and possibly other speaker dependent voice commands for non-macro uses, previously trained by the user in accordance with the process steps described in FIG. 15.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to set to value zero and start a recognition time-out counter as shown in a step S365.
- the software Following the prompting of the user by a speech synthesis prompt, an audio sound and/or the illumination of a green light emitting diode 52a in a step S366, the software enters a mode where it is available for pattern generating in a step S367, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXM is attained before a voice command is detected, the software will terminate the macro programming routine as shown in step S368 and the user may elect to press the setup button, returning to step S204 in FIG. 12a and begin the process again. Until time TMAXM has expired, the speech recognition circuit remains available to generate a pattern when a voice command is detected as shown in steps S367, S368, and S369. If a voice command is detected in a step S369, a pattern is generated in a step S370 and submitted for pattern recognition processing in a step S371.
- step S371 the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of conectly recognizing the unknown pattern exceeds a predetermined threshold. The result of this comparison is identified in a step S372.
- a red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified in a step S373 and returns to step S365 to set to value zero and start a recognition time-out counter.
- the software then re-enters a mode where it is available for pattern generating, waiting for a voice command to be detected. As previously indicated, until time TMAXM has expired, the speech recognition circuit remains available to generate apattem when a voice command is detected as shown in steps S367, S368 and S369.
- the speech recognition circuit 50 software identifies aread/write memory 54 location associated with the matching recognition vocabulary set command in a step S374. Said memory 54 location is used to store the sequence of commands instractions to be associated with the macro name identified by the preceding voice command. As shown in a step S375, the software executed by the speech recognition circuit controller 60 then activates the default recognition mode associated with the appliance device type previously selected.
- the speech recognition circuit controller 60 executes software stored in its ROM 61 to enter a default recognition mode and to activate a default recognition vocabulary set as shown in a step S381 in FIG. 16b.
- This default recognition vocabulary set is made available to enable the user to navigate the recognition vocabulary stracture via spoken commands to identify a voice command for which the associated instruction is to be stored within the read/write memory 54 location associated with said macro name voice command.
- a recognition time- out counter is set to zero and started in a step S382 when a recognition mode is activated.
- the user is then expected to select a voice command from the default recognition vocabulary set and respond when prompted by a speech synthesis prompt, an audio sound and/or the illumination of a green light emitting diode 52a as shown in a step S383.
- the default recognition vocabulary set may be comprised of such voice command options as "power,” “channel,” “change,” “volume,” “sound,”
- the software Following the prompting of the user by the illumination of a green light emitting diode 52a in a step S383, the software enters a mode where it is available for pattern generating in a step S384, waiting for a voice command to be detected. If a maximum allowed time-out value TMAXM is attained before a voice command is detected, the software will return to a known default continuous listening recognition mode and the user may continue generating the macro as shown in step S385. Until the time TMAXM has expired, the speech recognition circuit remains available in the active recogmtion mode to generate a pattern when a voice command is detected as shown in steps S384, S385 and S386. If a voice command is detected in a step S386, a pattern is generated in a step S387.
- the acquired unknown pattern is analyzed by the speech recognition circuit controller 60, utilizing a recognition algorithm stored in its ROM 61, to determined if it can be classified as a match with any of the reference commands within the active recognition vocabulary set and if the likelihood of correctly recognizing the unknown pattern exceeds a predetermined threshold. The result of this comparison is identified in a step S389.
- the red light-emitting diode 52c illuminates briefly to provide a visual indicator to the operator that no match was identified as shown in a step S390 and the value of the recognition time-out counter is reset to the value zero and restarted as shown in a step S382.
- the green light-emitting diode 52a is then activated and remains illuminated as shown in step S383 and the speech recognition circuit 50 executes software to enter apattem generating mode, returning to a step S384 and waiting for a voice command to be detected.
- the speech recognition circuit remains in the active recognition mode available to generate a pattern when a voice command is detected as shown in steps S384, S385 and S386.
- the speech recognition circuit 50 software identifies the operation associated with the matching recognition vocabulary set command in a step S391 and detennines if the operation is to send an instraction to the speech recognition circuit controller 60 to activate a different recognition set vocabulary or to output a signal to the infrared controlling circuit 70 using the speech recognition circuit output 68 pins. If the instruction is to activate a different recognition vocabulary set, step S391 shows that the routine returns to a step S380 to enter the appropriate recognition mode and activate the recognition vocabulary set associated with the recognized voice command in step S381. The user may continue to navigate through different linked, recognition vocabulary sets until a voice command is recognized that is associated with an instraction to output a signal to the infrared controlling circuit 70.
- a voice command is recognized that is associated with an instruction to output a signal to the infrared controlling circuit 70
- the associated instruction is stored within the read/write memory 54 location associated with said macro name voice command as shown in a step S392.
- an end marker instraction may be automatically stored by the speech recognition circuit 50 software as shown in step S393. The user must then determine if this is the last instraction to be added to the macro program or not. If another instruction is to be added, the user must determine if it is desirable to insert a time delay between the execution of the cunently identified instruction and a following macro instraction to be selected.
- a keypad 51 designated as a time delay button one or more times, where each button depress increases the length of the time delay by a brief period (typically 0.5 seconds or less) by storing one or a series of time delay instructions within the read/write memory 54 location associated with said macro name voice command as shown in a step S395.
- the time delay instractions are stored into said memory 54 location in a section sequentially following the section of the instraction previously identified via voice command.
- the software returns to a step S375 shown in FIG. 16a, and the software executed by the speech recognition circuit controller 60 then activates the default recognition mode associated with the appliance device type previously selected.
- this default recognition vocabulary set is made available to enable the user to navigate the recognition vocabulary stracture via spoken commands to identify another voice command for which the associated instruction is also to be stored within the read/write memory 54 location associated with said macro name voice command.
- Each additional instruction added to a macro is stored in the same memory 54 location as that of the previously stored end marker instraction, which was stored by the software after the previous macro instruction was stored, thus over- writing the end markers .
- This process for adding instractions to said memory location 54 associated with said macro continues until the user determines the last instruction has been identified via voice command.
- the user depresses a keypad 51 button designated as a program completion button as shown in a step S397 to instruct the speech recognition circuit controller 60 to execute software stored in its ROM 61 terminate the macro programming routine and enter the default recognition mode associated with the previously identified appliance category as shown in step S398.
- the macro program resulting from this process is stored in a read/write memory 54 location comprised of multiple, sequential bytes of memory. Each byte may contain an instraction to output a signal to the infrared controlling circuit 70, an instruction to execute a time delay, or an instruction in the form of an end marker to instruct the speech recognition circuit controller 60 software that the last macro instruction has been retrieved.
- a macro name is spoken by a user and recognized by the speech recognition circuit controller 60 software, said software retrieves and sequentially executes each of the instructions stored within the read/write memory 54 location associated with said macro name in the same order which the instractions were stored.
- buttons other than the macro button such as the code button and signal learning button, may be used for such functions as time delay insertion and end marker insertion into the macro sequence.
- This approach allows for a reduction of the required button count, and is particularly useful for such relatively infrequently used functions as those identified above.
- FIG. 17 shows the power supply circuit 90 in greater detail than that shown in FIG. 1. This circuit is described previously in the section describing the process steps of FIG. 12a.
- the present invention typically remains in a sound activation mode until sound pressure exceeding a defined threshold (sound activation sensitivity setting) initiates a "wake up" event.
- a defined threshold sound activation sensitivity setting
- the system enters a continuous listening default recognition mode awaiting detection and recognition of one of the default menu words associated with a selected target appliance. Control functions for the target appliance can then be activated via voice commands.
- Once an appliance has been selected, its default menu remains the active recognition vocabulary set until changed by the user. Voice commands may then be selected from the available recognition vocabulary set.
- the vocabulary options made available by the default menu vary depending upon the category of the appliance selected (for example, a VCR may have different options available than a TV) .
- Voice commands may instruct the invention to initiate a control signal to the target appliance or activate a function sub-menu in the form of a different recognition vocabulary set (which may include access, for example, to different appliance control functions, macro functions, speaker dependent commands or device selection commands).
- the unit then remains in a continuous listening default recognition mode for a defined period of time or until a defined number of consecutive unsuccessful recognition attempts occur, whichever occurs first. If any default menu word is recognized, the invention executes the appropriate command. If no default menu words are recognized, the unit returns to sound activation mode.
- the software Upon returning to default recognition mode from sound activation mode, the software remains in default recognition mode until a defined period of time where no recognition (successful) activity has elapsed after the last recognized command (a "user settling period") or until a defined number of consecutive unsuccessful recognition attempts occur, whichever occurs first.
- a green LED When in a continuous listening default recognition mode, a green LED
- Default Menu Vocabulary for a Television As an example, Table 1 below identifies seven words comprising a default menu recognition vocabulary set available for a television. Fig. 5 shows the process steps associated with the software executed during this mode.
- the invention transmits the IR signal for the Power command, turning the currently controlled appliance on or off.
- Table 2 identifies words (digit names) comprising a channel number recognition vocabulary set. If the word "Channel” is recognized, a pattern queuing routine is initiated, as shown in FIG. 9, and makes the following speaker independent sub-menu available for recogmtion:
- the green LED 52a then prompts a user to say a digit name. After detecting the first digit, the invention's green LED 52b then quickly prompts the user for another digit name. In one embodiment of the invention, the routine prompts the user for up to 3 digit names. If a second digit (or third) is not detected within a predetermined period of time, the invention performs the speech recognition process and transmits the i IR signal(s) associated with any recognized channel number names and returns to the default recognition mode. Table 3 below identifies words comprising a directional channel changing recognition vocabulary set. If the word "Change" is recognized, the invention enters a response prompting recognition mode as shown in FIG. 8 and the following speaker independent sub-menu is made available for recognition:
- Up and Down are instructions to advance forward or in reverse order to the next sequentially avai lable channel number, respectively.
- "Back” is an instruction to return to the channel number established prior to the current channel number.
- the invention transmits the associated IR signal associated with the indicated channel directional change and awaits, for a predetermined period of time, for another Up/Down/Back command before returning to the default menu recognition mode. This sequence continues until no Up/Down/Back commands are recognized within said predetermined period of time of a previous command, at which time the software returns to the default menu recognition mode.
- Table 4 identifies words comprising the volume changing recognition vocabulary set. If the word "Volume" is recognized, the invention enters a response prompting recognition mode as shown in FIG. 8 and the following speaker independent sub-menu is made available for recognition:
- Table 5 below identifies a word in the default recognition vocabulary for the muting function. If the word "So « «rf" is recognized, the invention transmits the TR signal for the muting command and returns to default recognition mode.
- Table 6 identifies the words comprising the device selection/control recognition vocabulary set. If the word "Control is recognized, the invention enters a response prompting recognition mode as shown in FIG. 8 and the following speaker independent sub-menu is made available for recognition:
- the invention transmits an IR signal associated with the "TV/Nideo” switching function and returns to the default recognition mode. If the word "Power” is recognized, the software returns to response prompting recognition mode, awaiting a repeat of this command to ensure the invention is not accidentally powered down. If a second word "Power” is recognized, the invention utilizes a speech recognition circuit 50 input/output 68 pin to activate a switch 93 to disconnect the power source from the power supply circuit 90. Manually depressing a power button is required to re-activate the invention.
- Table 7 below indicates how a speaker dependent vocabulary recognition set sub-menu maybe accessed if speaker dependent vocabulary words have previously been trained. If the word "Private" is recognized, the software enters speaker dependent recognition mode and makes a recognition vocabulary set containing speaker dependent function names, device names and macro names available for recognition. It should be noted that this recognition vocabulary set remains empty until the user has entered speaker dependent names via the voice training setup process shown in FIG. 15. The recognition of any speaker dependent voice command causes the software to execute the instraction(s) associated with the recognized command, including the transmission of any associated IR signals, and remain in speaker dependent recognition mode awaiting another command from this recognition vocabulary set. If no words are detected for a predetermined period of time or if a predetermined number of consecutive recognition enor occur, the software automatically returns to a continuous listening default recognition mode, awaiting speaker independent commands.
- the device selection of "Video” may also make voice commands named "Play,” “Stop,” “Pause,” “Record,” “Rewind” and “Fast Forward” available. If any of these are recognized, the invention transmits the IR signal associated with the indicated function and returns to continuous listening default recognition mode.
- the voice command “Record”, however, is an exception. If the word “Record” is recognized, the software returns to recognition mode awaiting arepeat of this command to ensure there is no unintentional recording onto the media within the VCR or other such device. Macros:
- a user has the option of creating one or more macros, where a single speaker dependent word command may produce a series of infrared signal transmissions to one or more target appliances.
- a single speaker dependent word command may produce a series of infrared signal transmissions to one or more target appliances.
- the voice command "HBO” may generate infrared signals for digits "1,” "2,” and "3,” causing the
- FIG. 16a and FIG. 16b describe the macro programming process in detail.
- circuitry and related software disclosed herein may be otherwise integrated and/or combined differently than represented by the embodiments of this invention.
- one such alternate approach may involve providing direct electrical connections between predetermined speech recognition circuit IC output pins 68 and remote confrol controller IC 76 input pins.
- software executed by the speech recognition circuit 50 may emulate the signals output by the output by the output pins of a conventional remote confrol controller when one of its keypad buttons are depressed, whereby the remote control controller output pins are generally electrically connected to remote control controller input pins.
- Other approaches may integrate the features of this invention differently than disclosed therein into one or more microcontrollers, processors, digital signal processors (DSP), application-specific integrated circuits (ASIC) and the like.
- the hands-free voice-operated remote control transmitter software is not limited to executing a speaker independent, continuous listening default recognition mode.
- a setup process may be provided where a user is prompted to train speaker dependent words in a manner which would generate a speaker dependent vocabulary stracture similar to the speaker independent vocabulary stracture disclosed for the present invention.
- the software executed by the present invention may be adapted to guide a user through confrolled appliance setup processes, for example programming a VCR with or without VCR-PLUS ® capability to record a televised program, in a prompt -driven manner.
- sound-activation circuitry utilized by the present invention is not limited to use of inverting Schmitt trigger circuits. Similar circuitry capable of performing amplification and comparator operations, such as that based upon one or more operational amplifiers, may also be used. Furthermore, the mode of activation of the present invention is not limited to sound activation. Similar schemes, for example, such at those utilizing light detection circuitry or motion detection circuitry may also be used.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Acoustics & Sound (AREA)
- Selective Calling Equipment (AREA)
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU22902/01A AU2290201A (en) | 1999-12-22 | 2000-12-21 | Hands-free, voice-operated remote control transmitter |
US10/168,935 US7080014B2 (en) | 1999-12-22 | 2000-12-21 | Hands-free, voice-operated remote control transmitter |
CA002395856A CA2395856A1 (en) | 1999-12-22 | 2000-12-21 | Hands-free, voice-operated remote control transmitter |
EP00986713A EP1240643A4 (en) | 1999-12-22 | 2000-12-21 | Hands-free, voice-operated remote control transmitter |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/469,707 US6397186B1 (en) | 1999-12-22 | 1999-12-22 | Hands-free, voice-operated remote control transmitter |
US09/469,707 | 1999-12-22 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2001046946A1 true WO2001046946A1 (en) | 2001-06-28 |
Family
ID=23864785
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2000/035107 WO2001046946A1 (en) | 1999-12-22 | 2000-12-21 | Hands-free, voice-operated remote control transmitter |
Country Status (5)
Country | Link |
---|---|
US (2) | US6397186B1 (en) |
EP (1) | EP1240643A4 (en) |
AU (1) | AU2290201A (en) |
CA (1) | CA2395856A1 (en) |
WO (1) | WO2001046946A1 (en) |
Cited By (119)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2003083801A2 (en) | 2002-03-29 | 2003-10-09 | Koninklijke Philips Electronics N.V. | Programmable remote control and method for programming a programmable remote control, a readable memory and a program |
WO2011088038A1 (en) | 2010-01-13 | 2011-07-21 | Apple Inc. | Processing of voice inputs |
WO2014182458A1 (en) * | 2013-05-07 | 2014-11-13 | Qualcomm Incorporated | Method and apparatus for controlling voice activation |
US8892446B2 (en) | 2010-01-18 | 2014-11-18 | Apple Inc. | Service orchestration for intelligent automated assistant |
WO2015164047A1 (en) * | 2014-04-21 | 2015-10-29 | Qualcomm Incorporated | Method and apparatus for activating application by speech input |
US9262612B2 (en) | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
US9300784B2 (en) | 2013-06-13 | 2016-03-29 | Apple Inc. | System and method for emergency calls initiated by voice command |
US9330720B2 (en) | 2008-01-03 | 2016-05-03 | Apple Inc. | Methods and apparatus for altering audio output signals |
US9338493B2 (en) | 2014-06-30 | 2016-05-10 | Apple Inc. | Intelligent automated assistant for TV user interactions |
US9368114B2 (en) | 2013-03-14 | 2016-06-14 | Apple Inc. | Context-sensitive handling of interruptions |
US9430463B2 (en) | 2014-05-30 | 2016-08-30 | Apple Inc. | Exemplar-based natural language processing |
US9483461B2 (en) | 2012-03-06 | 2016-11-01 | Apple Inc. | Handling speech synthesis of content for multiple languages |
US9495129B2 (en) | 2012-06-29 | 2016-11-15 | Apple Inc. | Device, method, and user interface for voice-activated navigation and browsing of a document |
US9502031B2 (en) | 2014-05-27 | 2016-11-22 | Apple Inc. | Method for supporting dynamic grammars in WFST-based ASR |
US9535906B2 (en) | 2008-07-31 | 2017-01-03 | Apple Inc. | Mobile device having human language translation capability with positional feedback |
US9576574B2 (en) | 2012-09-10 | 2017-02-21 | Apple Inc. | Context-sensitive handling of interruptions by intelligent digital assistant |
US9582608B2 (en) | 2013-06-07 | 2017-02-28 | Apple Inc. | Unified ranking with entropy-weighted information for phrase-based semantic auto-completion |
US9620105B2 (en) | 2014-05-15 | 2017-04-11 | Apple Inc. | Analyzing audio input for efficient speech and music recognition |
US9620104B2 (en) | 2013-06-07 | 2017-04-11 | Apple Inc. | System and method for user-specified pronunciation of words for speech synthesis and recognition |
US9626955B2 (en) | 2008-04-05 | 2017-04-18 | Apple Inc. | Intelligent text-to-speech conversion |
US9633004B2 (en) | 2014-05-30 | 2017-04-25 | Apple Inc. | Better resolution when referencing to concepts |
US9633660B2 (en) | 2010-02-25 | 2017-04-25 | Apple Inc. | User profiling for voice input processing |
US9633674B2 (en) | 2013-06-07 | 2017-04-25 | Apple Inc. | System and method for detecting errors in interactions with a voice-based digital assistant |
AU2015203169B2 (en) * | 2010-01-13 | 2017-04-27 | Apple Inc. | Processing of voice inputs |
US9646609B2 (en) | 2014-09-30 | 2017-05-09 | Apple Inc. | Caching apparatus for serving phonetic pronunciations |
US9646614B2 (en) | 2000-03-16 | 2017-05-09 | Apple Inc. | Fast, language-independent method for user authentication by voice |
US9668121B2 (en) | 2014-09-30 | 2017-05-30 | Apple Inc. | Social reminders |
US9697822B1 (en) | 2013-03-15 | 2017-07-04 | Apple Inc. | System and method for updating an adaptive speech recognition model |
US9697820B2 (en) | 2015-09-24 | 2017-07-04 | Apple Inc. | Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks |
US9711141B2 (en) | 2014-12-09 | 2017-07-18 | Apple Inc. | Disambiguating heteronyms in speech synthesis |
US9715875B2 (en) | 2014-05-30 | 2017-07-25 | Apple Inc. | Reducing the need for manual start/end-pointing and trigger phrases |
US9721566B2 (en) | 2015-03-08 | 2017-08-01 | Apple Inc. | Competing devices responding to voice triggers |
US9734193B2 (en) | 2014-05-30 | 2017-08-15 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
US9760559B2 (en) | 2014-05-30 | 2017-09-12 | Apple Inc. | Predictive text input |
US9785630B2 (en) | 2014-05-30 | 2017-10-10 | Apple Inc. | Text prediction using combined word N-gram and unigram language models |
US9798393B2 (en) | 2011-08-29 | 2017-10-24 | Apple Inc. | Text correction processing |
US9818400B2 (en) | 2014-09-11 | 2017-11-14 | Apple Inc. | Method and apparatus for discovering trending terms in speech requests |
US9842101B2 (en) | 2014-05-30 | 2017-12-12 | Apple Inc. | Predictive conversion of language input |
US9842105B2 (en) | 2015-04-16 | 2017-12-12 | Apple Inc. | Parsimonious continuous-space phrase representations for natural language processing |
US9858925B2 (en) | 2009-06-05 | 2018-01-02 | Apple Inc. | Using context information to facilitate processing of commands in a virtual assistant |
US9865280B2 (en) | 2015-03-06 | 2018-01-09 | Apple Inc. | Structured dictation using intelligent automated assistants |
EP3162085A4 (en) * | 2014-06-30 | 2018-01-24 | Samsung Electronics Co., Ltd. | Operating method for microphones and electronic device supporting the same |
US9886432B2 (en) | 2014-09-30 | 2018-02-06 | Apple Inc. | Parsimonious handling of word inflection via categorical stem + suffix N-gram language models |
US9886953B2 (en) | 2015-03-08 | 2018-02-06 | Apple Inc. | Virtual assistant activation |
US9899019B2 (en) | 2015-03-18 | 2018-02-20 | Apple Inc. | Systems and methods for structured stem and suffix language models |
US9922642B2 (en) | 2013-03-15 | 2018-03-20 | Apple Inc. | Training an at least partial voice command system |
US9934775B2 (en) | 2016-05-26 | 2018-04-03 | Apple Inc. | Unit-selection text-to-speech synthesis based on predicted concatenation parameters |
US9953088B2 (en) | 2012-05-14 | 2018-04-24 | Apple Inc. | Crowd sourcing information to fulfill user requests |
US9959870B2 (en) | 2008-12-11 | 2018-05-01 | Apple Inc. | Speech recognition involving a mobile device |
US9966065B2 (en) | 2014-05-30 | 2018-05-08 | Apple Inc. | Multi-command single utterance input method |
US9966068B2 (en) | 2013-06-08 | 2018-05-08 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US9971774B2 (en) | 2012-09-19 | 2018-05-15 | Apple Inc. | Voice-based media searching |
US9972304B2 (en) | 2016-06-03 | 2018-05-15 | Apple Inc. | Privacy preserving distributed evaluation framework for embedded personalized systems |
US10043516B2 (en) | 2016-09-23 | 2018-08-07 | Apple Inc. | Intelligent automated assistant |
US10049663B2 (en) | 2016-06-08 | 2018-08-14 | Apple, Inc. | Intelligent automated assistant for media exploration |
US10049668B2 (en) | 2015-12-02 | 2018-08-14 | Apple Inc. | Applying neural network language models to weighted finite state transducers for automatic speech recognition |
US10057736B2 (en) | 2011-06-03 | 2018-08-21 | Apple Inc. | Active transport based notifications |
US10067938B2 (en) | 2016-06-10 | 2018-09-04 | Apple Inc. | Multilingual word prediction |
US10074360B2 (en) | 2014-09-30 | 2018-09-11 | Apple Inc. | Providing an indication of the suitability of speech recognition |
US10079014B2 (en) | 2012-06-08 | 2018-09-18 | Apple Inc. | Name recognition system |
US10078631B2 (en) | 2014-05-30 | 2018-09-18 | Apple Inc. | Entropy-guided text prediction using combined word and character n-gram language models |
US10083688B2 (en) | 2015-05-27 | 2018-09-25 | Apple Inc. | Device voice control for selecting a displayed affordance |
US10089072B2 (en) | 2016-06-11 | 2018-10-02 | Apple Inc. | Intelligent device arbitration and control |
US10101822B2 (en) | 2015-06-05 | 2018-10-16 | Apple Inc. | Language input correction |
US10127220B2 (en) | 2015-06-04 | 2018-11-13 | Apple Inc. | Language identification from short strings |
US10127911B2 (en) | 2014-09-30 | 2018-11-13 | Apple Inc. | Speaker identification and unsupervised speaker adaptation techniques |
US10134385B2 (en) | 2012-03-02 | 2018-11-20 | Apple Inc. | Systems and methods for name pronunciation |
US10170123B2 (en) | 2014-05-30 | 2019-01-01 | Apple Inc. | Intelligent assistant for home automation |
US10176167B2 (en) | 2013-06-09 | 2019-01-08 | Apple Inc. | System and method for inferring user intent from speech inputs |
US10186254B2 (en) | 2015-06-07 | 2019-01-22 | Apple Inc. | Context-based endpoint detection |
US10185542B2 (en) | 2013-06-09 | 2019-01-22 | Apple Inc. | Device, method, and graphical user interface for enabling conversation persistence across two or more instances of a digital assistant |
US10192552B2 (en) | 2016-06-10 | 2019-01-29 | Apple Inc. | Digital assistant providing whispered speech |
US10199051B2 (en) | 2013-02-07 | 2019-02-05 | Apple Inc. | Voice trigger for a digital assistant |
US10223066B2 (en) | 2015-12-23 | 2019-03-05 | Apple Inc. | Proactive assistance based on dialog communication between devices |
US10241644B2 (en) | 2011-06-03 | 2019-03-26 | Apple Inc. | Actionable reminder entries |
US10241752B2 (en) | 2011-09-30 | 2019-03-26 | Apple Inc. | Interface for a virtual digital assistant |
US10249300B2 (en) | 2016-06-06 | 2019-04-02 | Apple Inc. | Intelligent list reading |
US10255907B2 (en) | 2015-06-07 | 2019-04-09 | Apple Inc. | Automatic accent detection using acoustic models |
US10269345B2 (en) | 2016-06-11 | 2019-04-23 | Apple Inc. | Intelligent task discovery |
US10276170B2 (en) | 2010-01-18 | 2019-04-30 | Apple Inc. | Intelligent automated assistant |
US10283110B2 (en) | 2009-07-02 | 2019-05-07 | Apple Inc. | Methods and apparatuses for automatic speech recognition |
US10289433B2 (en) | 2014-05-30 | 2019-05-14 | Apple Inc. | Domain specific language for encoding assistant dialog |
US10297253B2 (en) | 2016-06-11 | 2019-05-21 | Apple Inc. | Application integration with a digital assistant |
US10318871B2 (en) | 2005-09-08 | 2019-06-11 | Apple Inc. | Method and apparatus for building an intelligent automated assistant |
US10356243B2 (en) | 2015-06-05 | 2019-07-16 | Apple Inc. | Virtual assistant aided communication with 3rd party service in a communication session |
US10354011B2 (en) | 2016-06-09 | 2019-07-16 | Apple Inc. | Intelligent automated assistant in a home environment |
US10366158B2 (en) | 2015-09-29 | 2019-07-30 | Apple Inc. | Efficient word encoding for recurrent neural network language models |
US10410637B2 (en) | 2017-05-12 | 2019-09-10 | Apple Inc. | User-specific acoustic models |
US10446143B2 (en) | 2016-03-14 | 2019-10-15 | Apple Inc. | Identification of voice inputs providing credentials |
US10446141B2 (en) | 2014-08-28 | 2019-10-15 | Apple Inc. | Automatic speech recognition based on user feedback |
US10482874B2 (en) | 2017-05-15 | 2019-11-19 | Apple Inc. | Hierarchical belief states for digital assistants |
US10490187B2 (en) | 2016-06-10 | 2019-11-26 | Apple Inc. | Digital assistant providing automated status report |
US10496753B2 (en) | 2010-01-18 | 2019-12-03 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
US10509862B2 (en) | 2016-06-10 | 2019-12-17 | Apple Inc. | Dynamic phrase expansion of language input |
US10521466B2 (en) | 2016-06-11 | 2019-12-31 | Apple Inc. | Data driven natural language event detection and classification |
US10552013B2 (en) | 2014-12-02 | 2020-02-04 | Apple Inc. | Data detection |
US10553209B2 (en) | 2010-01-18 | 2020-02-04 | Apple Inc. | Systems and methods for hands-free notification summaries |
US10568032B2 (en) | 2007-04-03 | 2020-02-18 | Apple Inc. | Method and system for operating a multi-function portable electronic device using voice-activation |
US10567477B2 (en) | 2015-03-08 | 2020-02-18 | Apple Inc. | Virtual assistant continuity |
US10593346B2 (en) | 2016-12-22 | 2020-03-17 | Apple Inc. | Rank-reduced token representation for automatic speech recognition |
US10592095B2 (en) | 2014-05-23 | 2020-03-17 | Apple Inc. | Instantaneous speaking of content on touch devices |
US10607141B2 (en) | 2010-01-25 | 2020-03-31 | Newvaluexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US10659851B2 (en) | 2014-06-30 | 2020-05-19 | Apple Inc. | Real-time digital assistant knowledge updates |
US10671428B2 (en) | 2015-09-08 | 2020-06-02 | Apple Inc. | Distributed personal assistant |
US10679605B2 (en) | 2010-01-18 | 2020-06-09 | Apple Inc. | Hands-free list-reading by intelligent automated assistant |
US10691473B2 (en) | 2015-11-06 | 2020-06-23 | Apple Inc. | Intelligent automated assistant in a messaging environment |
US10706373B2 (en) | 2011-06-03 | 2020-07-07 | Apple Inc. | Performing actions associated with task items that represent tasks to perform |
US10705794B2 (en) | 2010-01-18 | 2020-07-07 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
US10733993B2 (en) | 2016-06-10 | 2020-08-04 | Apple Inc. | Intelligent digital assistant in a multi-tasking environment |
US10747498B2 (en) | 2015-09-08 | 2020-08-18 | Apple Inc. | Zero latency digital assistant |
US10755703B2 (en) | 2017-05-11 | 2020-08-25 | Apple Inc. | Offline personal assistant |
US10762293B2 (en) | 2010-12-22 | 2020-09-01 | Apple Inc. | Using parts-of-speech tagging and named entity recognition for spelling correction |
US10791176B2 (en) | 2017-05-12 | 2020-09-29 | Apple Inc. | Synchronization and task delegation of a digital assistant |
US10791216B2 (en) | 2013-08-06 | 2020-09-29 | Apple Inc. | Auto-activating smart responses based on activities from remote devices |
US10810274B2 (en) | 2017-05-15 | 2020-10-20 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
US11010550B2 (en) | 2015-09-29 | 2021-05-18 | Apple Inc. | Unified language modeling framework for word prediction, auto-completion and auto-correction |
US11025565B2 (en) | 2015-06-07 | 2021-06-01 | Apple Inc. | Personalized prediction of responses for instant messaging |
US11217255B2 (en) | 2017-05-16 | 2022-01-04 | Apple Inc. | Far-field extension for digital assistant services |
US11587559B2 (en) | 2015-09-30 | 2023-02-21 | Apple Inc. | Intelligent device identification |
Families Citing this family (291)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
USD822716S1 (en) | 2016-05-13 | 2018-07-10 | Google Llc | Voice interface device |
US6978159B2 (en) * | 1996-06-19 | 2005-12-20 | Board Of Trustees Of The University Of Illinois | Binaural signal processing using multiple acoustic sensors and digital filtering |
US7831930B2 (en) * | 2001-11-20 | 2010-11-09 | Universal Electronics Inc. | System and method for displaying a user interface for a remote control application |
US7684570B2 (en) * | 1998-11-17 | 2010-03-23 | Aamp Of America | Vehicle remote control interface for controlling multiple electronic devices |
US7020289B1 (en) * | 1998-11-17 | 2006-03-28 | P. B. Clarke & Associates | Remote control interface for replacement vehicle stereos |
US6956952B1 (en) | 1998-11-17 | 2005-10-18 | P.B. Clarke & Assoc. | Remote control interface for replacement vehicle stereos |
FR2788615B1 (en) * | 1999-01-18 | 2001-02-16 | Thomson Multimedia Sa | APPARATUS COMPRISING A VOICE OR MANUAL USER INTERFACE AND METHOD FOR ASSISTING IN LEARNING VOICE COMMANDS FROM SUCH AN APPARATUS |
US6584439B1 (en) * | 1999-05-21 | 2003-06-24 | Winbond Electronics Corporation | Method and apparatus for controlling voice controlled devices |
US6600497B1 (en) * | 1999-11-15 | 2003-07-29 | Elliot A. Gottfurcht | Apparatus and method to navigate interactive television using unique inputs with a remote control |
US6397186B1 (en) * | 1999-12-22 | 2002-05-28 | Ambush Interactive, Inc. | Hands-free, voice-operated remote control transmitter |
SE9904782D0 (en) * | 1999-12-22 | 1999-12-22 | Gambro Lundia Ab | Remote control for extracorporeal blood processing machines |
DE10021389A1 (en) * | 2000-05-03 | 2001-11-08 | Nokia Mobile Phones Ltd | Electronic system setting modification method e.g. for radio receiver, involves interpreting user input with respect to each electronic device and confirming the input before regulation |
AU2001261344A1 (en) * | 2000-05-10 | 2001-11-20 | The Board Of Trustees Of The University Of Illinois | Interference suppression techniques |
US7206423B1 (en) | 2000-05-10 | 2007-04-17 | Board Of Trustees Of University Of Illinois | Intrabody communication for a hearing aid |
EP1162602B1 (en) * | 2000-06-07 | 2004-12-15 | Sony International (Europe) GmbH | Two pass speech recognition with active vocabulary restriction |
US7978219B1 (en) * | 2000-08-30 | 2011-07-12 | Kevin Reid Imes | Device, network, server, and methods for providing digital images and associated processing information |
EP1184841A1 (en) * | 2000-08-31 | 2002-03-06 | Siemens Aktiengesellschaft | Speech controlled apparatus and method for speech input and speech recognition |
US8132105B1 (en) * | 2000-10-10 | 2012-03-06 | Koninklijke Philips Electronics, N.V. | Control codes for programmable remote supplied in XML format |
US6832194B1 (en) * | 2000-10-26 | 2004-12-14 | Sensory, Incorporated | Audio recognition peripheral system |
US6629077B1 (en) * | 2000-11-22 | 2003-09-30 | Universal Electronics Inc. | Universal remote control adapted to receive voice input |
US6476845B2 (en) * | 2000-12-13 | 2002-11-05 | Hewlett-Packard Co. | Electrophotographic printer, and method of controlling light emitting elements in an electrophotographic print head |
US7010490B2 (en) * | 2001-01-26 | 2006-03-07 | International Business Machines Corporation | Method, system, and apparatus for limiting available selections in a speech recognition system |
US20020128832A1 (en) * | 2001-02-20 | 2002-09-12 | International Business Machines Corporation | Compact speech module |
US20020123896A1 (en) * | 2001-02-28 | 2002-09-05 | Tomas Diez | Control module for HVAC systems |
US6766290B2 (en) * | 2001-03-30 | 2004-07-20 | Intel Corporation | Voice responsive audio system |
US7194412B2 (en) * | 2001-07-19 | 2007-03-20 | Overhead Door Corporation | Speech activated door operator system |
US6975994B2 (en) * | 2001-09-12 | 2005-12-13 | Technology Innovations, Llc | Device for providing speech driven control of a media presentation |
US7158499B2 (en) * | 2001-09-19 | 2007-01-02 | Mitsubishi Electric Research Laboratories, Inc. | Voice-operated two-way asynchronous radio |
US7324947B2 (en) | 2001-10-03 | 2008-01-29 | Promptu Systems Corporation | Global speech user interface |
US7996232B2 (en) * | 2001-12-03 | 2011-08-09 | Rodriguez Arturo A | Recognition of voice-activated commands |
US6889191B2 (en) * | 2001-12-03 | 2005-05-03 | Scientific-Atlanta, Inc. | Systems and methods for TV navigation with compressed voice-activated commands |
DE60222852D1 (en) * | 2001-12-18 | 2007-11-22 | Matsushita Electric Ind Co Ltd | TV with voice recognition function |
US20040054538A1 (en) * | 2002-01-03 | 2004-03-18 | Peter Kotsinadelis | My voice voice agent for use with voice portals and related products |
US7260538B2 (en) * | 2002-01-08 | 2007-08-21 | Promptu Systems Corporation | Method and apparatus for voice control of a television control device |
US20030206491A1 (en) * | 2002-05-06 | 2003-11-06 | Pacheco Arcilio S. | Voice-activated lens shading |
CA2484226A1 (en) * | 2002-05-10 | 2003-11-20 | Thomson Licensing S.A., | Remote control device for television signal receiver capable of receiving emergency alert signals |
US7072686B1 (en) | 2002-08-09 | 2006-07-04 | Avon Associates, Inc. | Voice controlled multimedia and communications device |
US8068881B2 (en) * | 2002-08-09 | 2011-11-29 | Avon Associates, Inc. | Voice controlled multimedia and communications system |
DE10251209A1 (en) * | 2002-10-31 | 2004-05-19 | Sennheiser Electronic Gmbh & Co. Kg | Intelligent wireless microphone system, analyses speech signals and carries out appropriate control function on recognizing spoken concepts, words or content |
US7154566B2 (en) * | 2002-12-05 | 2006-12-26 | Koninklijke Philips Electronics N.V. | Programmable universal remote control unit and method of programming same |
US20040143437A1 (en) * | 2003-01-06 | 2004-07-22 | Jbs Technologies, Llc | Sound-activated system for remotely operating vehicular or other functions |
US7512448B2 (en) | 2003-01-10 | 2009-03-31 | Phonak Ag | Electrode placement for wireless intrabody communication between components of a hearing system |
US20040260561A1 (en) * | 2003-01-10 | 2004-12-23 | Joseph Enterprises, Inc. | Voice-activated programmable remote control |
US7779482B1 (en) | 2003-02-07 | 2010-08-17 | iGware Inc | Delivery of license information using a short messaging system protocol in a closed content distribution system |
US8131649B2 (en) * | 2003-02-07 | 2012-03-06 | Igware, Inc. | Static-or-dynamic and limited-or-unlimited content rights |
US20100017627A1 (en) | 2003-02-07 | 2010-01-21 | Broadon Communications Corp. | Ensuring authenticity in a closed content distribution system |
US7103750B2 (en) * | 2003-03-20 | 2006-09-05 | International Business Machines Corporation | Method and apparatus for finding repeated substrings in pattern recognition |
US7181203B2 (en) * | 2003-07-21 | 2007-02-20 | The Chamberlain Group, Inc. | Barrier movement operator human interface method and apparatus |
US20050027539A1 (en) * | 2003-07-30 | 2005-02-03 | Weber Dean C. | Media center controller system and method |
MXPA06002241A (en) * | 2003-08-26 | 2006-08-31 | Clearplay Inc | Method and apparatus for controlling play of an audio signal. |
US7418392B1 (en) * | 2003-09-25 | 2008-08-26 | Sensory, Inc. | System and method for controlling the operation of a device by voice commands |
TWI235358B (en) * | 2003-11-21 | 2005-07-01 | Acer Inc | Interactive speech method and system thereof |
US7379975B2 (en) * | 2004-04-16 | 2008-05-27 | Nokia Corporation | Electric device, computer program, system and method of setting up user applications |
US8494861B2 (en) * | 2004-05-11 | 2013-07-23 | The Chamberlain Group, Inc. | Movable barrier control system component with audible speech output apparatus and method |
US7750890B2 (en) * | 2004-05-11 | 2010-07-06 | The Chamberlain Group, Inc. | Movable barrier operator system display method and apparatus |
US20050256720A1 (en) * | 2004-05-12 | 2005-11-17 | Iorio Laura M | Voice-activated audio/visual locator with voice recognition |
US20050256719A1 (en) * | 2004-05-12 | 2005-11-17 | Vanorman Stacy L | Voice-activated remote control |
TWI334703B (en) * | 2004-09-02 | 2010-12-11 | Inventec Multimedia & Telecom | Voice-activated remote control system |
US9632665B2 (en) | 2004-09-08 | 2017-04-25 | Universal Electronics Inc. | System and method for flexible configuration of a controlling device |
US11687217B2 (en) | 2004-09-08 | 2023-06-27 | Universal Electronics Inc. | System and method for flexible configuration of a controlling device |
KR100695127B1 (en) | 2004-10-08 | 2007-03-14 | 삼성전자주식회사 | Multi-Layered speech recognition apparatus and method |
GB0426448D0 (en) * | 2004-12-02 | 2005-01-05 | Koninkl Philips Electronics Nv | Position sensing using loudspeakers as microphones |
US20060123220A1 (en) * | 2004-12-02 | 2006-06-08 | International Business Machines Corporation | Speech recognition in BIOS |
KR100703696B1 (en) * | 2005-02-07 | 2007-04-05 | 삼성전자주식회사 | Method for recognizing control command and apparatus using the same |
US20060229881A1 (en) * | 2005-04-11 | 2006-10-12 | Global Target Enterprise Inc. | Voice recognition gateway apparatus |
TWI278762B (en) * | 2005-08-22 | 2007-04-11 | Delta Electronics Inc | Method and apparatus for speech input |
US7697827B2 (en) | 2005-10-17 | 2010-04-13 | Konicek Jeffrey C | User-friendlier interfaces for a camera |
TWI298844B (en) * | 2005-11-30 | 2008-07-11 | Delta Electronics Inc | User-defines speech-controlled shortcut module and method |
JP4846735B2 (en) | 2005-12-14 | 2011-12-28 | 三菱電機株式会社 | Voice recognition device |
US8161289B2 (en) * | 2005-12-21 | 2012-04-17 | SanDisk Technologies, Inc. | Voice controlled portable memory storage device |
US7917949B2 (en) * | 2005-12-21 | 2011-03-29 | Sandisk Corporation | Voice controlled portable memory storage device |
US20070143111A1 (en) * | 2005-12-21 | 2007-06-21 | Conley Kevin M | Voice controlled portable memory storage device |
US20070143117A1 (en) * | 2005-12-21 | 2007-06-21 | Conley Kevin M | Voice controlled portable memory storage device |
US20070171196A1 (en) * | 2006-01-23 | 2007-07-26 | Thomas Robert Pfingsten | Controller user interface and method |
US8000667B2 (en) * | 2006-02-03 | 2011-08-16 | Johnson Controls Technology Company | System and method for compensating for modulation induced frequency shift during transmission of a radio frequency signal |
US7929679B2 (en) * | 2006-03-21 | 2011-04-19 | Alcatel-Lucent Usa Inc. | Muting conference call hold music |
US7995713B2 (en) * | 2006-04-03 | 2011-08-09 | Agere Systems Inc. | Voice-identification-based signal processing for multiple-talker applications |
US20070242065A1 (en) * | 2006-04-18 | 2007-10-18 | O'flynn Brian M | Target acquisition training system and method |
WO2007130554A2 (en) * | 2006-05-02 | 2007-11-15 | Broadon Communications Corp. | Content management system and method |
JP2007324866A (en) * | 2006-05-31 | 2007-12-13 | Funai Electric Co Ltd | Electronic apparatus and television receiver |
US7984003B2 (en) * | 2006-07-21 | 2011-07-19 | Nathaniel Williams | Method and system for automated learning through repetition |
JP2008032834A (en) * | 2006-07-26 | 2008-02-14 | Toshiba Corp | Speech translation apparatus and method therefor |
MX2009001087A (en) * | 2006-08-04 | 2009-04-28 | Jps Communications Inc | Voice modulation recognition in a radio-to-sip adapter. |
US9319741B2 (en) | 2006-09-07 | 2016-04-19 | Rateze Remote Mgmt Llc | Finding devices in an entertainment system |
US8607281B2 (en) * | 2006-09-07 | 2013-12-10 | Porto Vinci Ltd. Limited Liability Company | Control of data presentation in multiple zones using a wireless home entertainment hub |
US8452427B2 (en) * | 2006-09-13 | 2013-05-28 | Savant Systems, Llc | Signal path using general-purpose computer for audio processing and audio-driven graphics |
US9514746B2 (en) * | 2006-09-26 | 2016-12-06 | Storz Endoskop Produktions Gmbh | System and method for hazard mitigation in voice-driven control applications |
US7769593B2 (en) * | 2006-09-28 | 2010-08-03 | Sri International | Method and apparatus for active noise cancellation |
US8930002B2 (en) * | 2006-10-11 | 2015-01-06 | Core Wireless Licensing S.A.R.L. | Mobile communication terminal and method therefor |
US7624276B2 (en) * | 2006-10-16 | 2009-11-24 | Broadon Communications Corp. | Secure device authentication system and method |
US9311394B2 (en) * | 2006-10-31 | 2016-04-12 | Sony Corporation | Speech recognition for internet video search and navigation |
US20080106370A1 (en) * | 2006-11-02 | 2008-05-08 | Viking Access Systems, Llc | System and method for speech-recognition facilitated communication to monitor and control access to premises |
US7613915B2 (en) * | 2006-11-09 | 2009-11-03 | BroadOn Communications Corp | Method for programming on-chip non-volatile memory in a secure processor, and a device so programmed |
US8165478B2 (en) * | 2006-12-21 | 2012-04-24 | Mitsubishi Electric Corporation | Optical receiver |
US7926118B2 (en) * | 2006-12-27 | 2011-04-19 | Illinois Tool Works Inc. | Voice control welding/cutting helmet functions and settings |
ATE454692T1 (en) * | 2007-02-02 | 2010-01-15 | Harman Becker Automotive Sys | VOICE CONTROL SYSTEM AND METHOD |
KR100759003B1 (en) * | 2007-02-09 | 2007-09-14 | 주식회사 서비전자 | Universal remote controller and controller code setup method thereof |
US8396331B2 (en) * | 2007-02-26 | 2013-03-12 | Microsoft Corporation | Generating a multi-use vocabulary based on image data |
US20110054900A1 (en) * | 2007-03-07 | 2011-03-03 | Phillips Michael S | Hybrid command and control between resident and remote speech recognition facilities in a mobile voice-to-speech application |
US20090030691A1 (en) * | 2007-03-07 | 2009-01-29 | Cerra Joseph P | Using an unstructured language model associated with an application of a mobile communication facility |
US8838457B2 (en) | 2007-03-07 | 2014-09-16 | Vlingo Corporation | Using results of unstructured language model based speech recognition to control a system-level function of a mobile communications facility |
US10056077B2 (en) | 2007-03-07 | 2018-08-21 | Nuance Communications, Inc. | Using speech recognition results based on an unstructured language model with a music system |
US20090030687A1 (en) * | 2007-03-07 | 2009-01-29 | Cerra Joseph P | Adapting an unstructured language model speech recognition system based on usage |
US8949130B2 (en) * | 2007-03-07 | 2015-02-03 | Vlingo Corporation | Internal and external speech recognition use with a mobile communication facility |
US8635243B2 (en) | 2007-03-07 | 2014-01-21 | Research In Motion Limited | Sending a communications header with voice recording to send metadata for use in speech recognition, formatting, and search mobile search application |
US20090030688A1 (en) * | 2007-03-07 | 2009-01-29 | Cerra Joseph P | Tagging speech recognition results based on an unstructured language model for use in a mobile communication facility application |
US20110054899A1 (en) * | 2007-03-07 | 2011-03-03 | Phillips Michael S | Command and control utilizing content information in a mobile voice-to-speech application |
US8886545B2 (en) | 2007-03-07 | 2014-11-11 | Vlingo Corporation | Dealing with switch latency in speech recognition |
US20080288252A1 (en) * | 2007-03-07 | 2008-11-20 | Cerra Joseph P | Speech recognition of speech recorded by a mobile communication facility |
US8949266B2 (en) | 2007-03-07 | 2015-02-03 | Vlingo Corporation | Multiple web-based content category searching in mobile search application |
US20110054896A1 (en) * | 2007-03-07 | 2011-03-03 | Phillips Michael S | Sending a communications header with voice recording to send metadata for use in speech recognition and formatting in mobile dictation application |
US20090030685A1 (en) * | 2007-03-07 | 2009-01-29 | Cerra Joseph P | Using speech recognition results based on an unstructured language model with a navigation system |
US20110060587A1 (en) * | 2007-03-07 | 2011-03-10 | Phillips Michael S | Command and control utilizing ancillary information in a mobile voice-to-speech application |
US20080312934A1 (en) * | 2007-03-07 | 2008-12-18 | Cerra Joseph P | Using results of unstructured language model based speech recognition to perform an action on a mobile communications facility |
US20080221899A1 (en) * | 2007-03-07 | 2008-09-11 | Cerra Joseph P | Mobile messaging environment speech processing facility |
US20110054897A1 (en) * | 2007-03-07 | 2011-03-03 | Phillips Michael S | Transmitting signal quality information in mobile dictation application |
US20080221884A1 (en) | 2007-03-07 | 2008-09-11 | Cerra Joseph P | Mobile environment speech processing facility |
US8886540B2 (en) | 2007-03-07 | 2014-11-11 | Vlingo Corporation | Using speech recognition results based on an unstructured language model in a mobile communication facility application |
US20080312935A1 (en) * | 2007-06-18 | 2008-12-18 | Mau Ii Frederick W | Media device with speech recognition and method for using same |
KR100878473B1 (en) * | 2007-08-09 | 2009-01-14 | 삼성전자주식회사 | Multi-function remote controller and method thereof |
WO2009027980A1 (en) * | 2007-08-28 | 2009-03-05 | Yissum Research Development Company Of The Hebrew University Of Jerusalem | Method, device and system for speech recognition |
CN101493987B (en) * | 2008-01-24 | 2011-08-31 | 深圳富泰宏精密工业有限公司 | Sound control remote-control system and method for mobile phone |
TWI414174B (en) * | 2008-02-29 | 2013-11-01 | Chi Mei Comm Systems Inc | System and method for sound controlling through a mobile phone |
US20100050270A1 (en) * | 2008-08-20 | 2010-02-25 | AT&T InteIlectual Property I, L.P. | Control of Access to Content Received from a Multimedia Content Distribution Network |
US9483959B2 (en) | 2008-08-21 | 2016-11-01 | Lincoln Global, Inc. | Welding simulator |
US9196169B2 (en) | 2008-08-21 | 2015-11-24 | Lincoln Global, Inc. | Importing and analyzing external data using a virtual reality welding system |
US8599625B2 (en) * | 2008-10-23 | 2013-12-03 | Marvell World Trade Ltd. | Switch pin multiplexing |
US8494140B2 (en) * | 2008-10-30 | 2013-07-23 | Centurylink Intellectual Property Llc | System and method for voice activated provisioning of telecommunication services |
WO2010078386A1 (en) * | 2008-12-30 | 2010-07-08 | Raymond Koverzin | Power-optimized wireless communications device |
US8327048B2 (en) * | 2009-01-07 | 2012-12-04 | Sony Computer Entertainment Inc. | Using USB suspend/resume to communicate information through a USB device |
US8352652B2 (en) * | 2009-01-07 | 2013-01-08 | Sony Computer Entertainment Inc. | Using analog signals to communicate through an A/D converter and USB interface |
US20100226512A1 (en) * | 2009-03-06 | 2010-09-09 | Mitek Corp. Inc. | Presentation audio system |
JP4809454B2 (en) * | 2009-05-17 | 2011-11-09 | 株式会社半導体理工学研究センター | Circuit activation method and circuit activation apparatus by speech estimation |
US11012732B2 (en) * | 2009-06-25 | 2021-05-18 | DISH Technologies L.L.C. | Voice enabled media presentation systems and methods |
US8285446B2 (en) | 2009-08-21 | 2012-10-09 | Circuit Works, Inc. | Methods and systems for providing accessory steering wheel controls |
US8214105B2 (en) | 2009-08-21 | 2012-07-03 | Metra Electronics Corporation | Methods and systems for automatic detection of steering wheel control signals |
US8014920B2 (en) * | 2009-08-21 | 2011-09-06 | Metra Electronics Corporation | Methods and systems for providing accessory steering wheel controls |
US8569655B2 (en) | 2009-10-13 | 2013-10-29 | Lincoln Global, Inc. | Welding helmet with integral user interface |
US8433579B1 (en) | 2010-01-25 | 2013-04-30 | Roberto Duran | Voice-activated motorized remote control device |
US8886541B2 (en) * | 2010-02-04 | 2014-11-11 | Sony Corporation | Remote controller with position actuatated voice transmission |
US9183560B2 (en) | 2010-05-28 | 2015-11-10 | Daniel H. Abelow | Reality alternate |
US8600763B2 (en) * | 2010-06-04 | 2013-12-03 | Microsoft Corporation | System-initiated speech interaction |
US20120158238A1 (en) * | 2010-07-14 | 2012-06-21 | Marcus Isaac Daley | Location based automobile inspection |
US9921803B2 (en) | 2010-08-23 | 2018-03-20 | Nokia Technologies Oy | Audio user interface apparatus and method |
US20120131466A1 (en) | 2010-11-23 | 2012-05-24 | Embarq Holdings Company, Llc | User-Based Monitoring and Control |
US9953643B2 (en) * | 2010-12-23 | 2018-04-24 | Lenovo (Singapore) Pte. Ltd. | Selective transmission of voice data |
US20150106089A1 (en) * | 2010-12-30 | 2015-04-16 | Evan H. Parker | Name Based Initiation of Speech Recognition |
US8914287B2 (en) * | 2010-12-31 | 2014-12-16 | Echostar Technologies L.L.C. | Remote control audio link |
JP5039214B2 (en) * | 2011-02-17 | 2012-10-03 | 株式会社東芝 | Voice recognition operation device and voice recognition operation method |
US20120260287A1 (en) * | 2011-04-07 | 2012-10-11 | Sony Corporation | Personalized user interface for audio video display device such as tv |
US20120310642A1 (en) | 2011-06-03 | 2012-12-06 | Apple Inc. | Automatically creating a mapping between text data and audio data |
US20130041662A1 (en) * | 2011-08-08 | 2013-02-14 | Sony Corporation | System and method of controlling services on a device using voice data |
US8768707B2 (en) | 2011-09-27 | 2014-07-01 | Sensory Incorporated | Background speech recognition assistant using speaker verification |
US8996381B2 (en) * | 2011-09-27 | 2015-03-31 | Sensory, Incorporated | Background speech recognition assistant |
US8340975B1 (en) * | 2011-10-04 | 2012-12-25 | Theodore Alfred Rosenberger | Interactive speech recognition device and system for hands-free building control |
US9031847B2 (en) * | 2011-11-15 | 2015-05-12 | Microsoft Technology Licensing, Llc | Voice-controlled camera operations |
US9847083B2 (en) | 2011-11-17 | 2017-12-19 | Universal Electronics Inc. | System and method for voice actuated configuration of a controlling device |
EP2860726B1 (en) | 2011-12-30 | 2017-12-06 | Samsung Electronics Co., Ltd | Electronic apparatus and method of controlling electronic apparatus |
ES2416582B1 (en) | 2012-01-30 | 2014-05-21 | Telefónica, S.A. | SYSTEM AND METHOD OF MEASUREMENT OF MUSCLE CONTRACTION FOR REMOTE INTERACTION WITH A COMPUTER APPLICATION AND USE OF A MANOMETER IN SUCH SYSTEM AND METHOD |
US9418658B1 (en) * | 2012-02-08 | 2016-08-16 | Amazon Technologies, Inc. | Configuration of voice controlled assistant |
US9117449B2 (en) | 2012-04-26 | 2015-08-25 | Nuance Communications, Inc. | Embedded system for construction of small footprint speech recognition with user-definable constraints |
US9619114B2 (en) | 2012-06-11 | 2017-04-11 | Automotive Data Solutions, Inc. | Method and system to configure an aftermarket interface module using a graphical user interface |
US9142215B2 (en) | 2012-06-15 | 2015-09-22 | Cypress Semiconductor Corporation | Power-efficient voice activation |
US9497515B2 (en) | 2012-08-16 | 2016-11-15 | Nuance Communications, Inc. | User interface for entertainment systems |
US8799959B2 (en) | 2012-08-16 | 2014-08-05 | Hoi L. Young | User interface for entertainment systems |
US9106957B2 (en) | 2012-08-16 | 2015-08-11 | Nuance Communications, Inc. | Method and apparatus for searching data sources for entertainment systems |
US9031848B2 (en) | 2012-08-16 | 2015-05-12 | Nuance Communications, Inc. | User interface for searching a bundled service content data source |
US9026448B2 (en) * | 2012-08-16 | 2015-05-05 | Nuance Communications, Inc. | User interface for entertainment systems |
US9691377B2 (en) | 2013-07-23 | 2017-06-27 | Google Technology Holdings LLC | Method and device for voice recognition training |
US10304465B2 (en) * | 2012-10-30 | 2019-05-28 | Google Technology Holdings LLC | Voice control user interface for low power mode |
US10438591B1 (en) * | 2012-10-30 | 2019-10-08 | Google Llc | Hotword-based speaker recognition |
KR102117841B1 (en) | 2012-10-30 | 2020-06-02 | 삼성전자주식회사 | Electronic device and control method thereof |
US10381002B2 (en) * | 2012-10-30 | 2019-08-13 | Google Technology Holdings LLC | Voice control user interface during low-power mode |
US9584642B2 (en) * | 2013-03-12 | 2017-02-28 | Google Technology Holdings LLC | Apparatus with adaptive acoustic echo control for speakerphone mode |
US10373615B2 (en) * | 2012-10-30 | 2019-08-06 | Google Technology Holdings LLC | Voice control user interface during low power mode |
US20140122078A1 (en) * | 2012-11-01 | 2014-05-01 | 3iLogic-Designs Private Limited | Low Power Mechanism for Keyword Based Hands-Free Wake Up in Always ON-Domain |
KR20140060040A (en) | 2012-11-09 | 2014-05-19 | 삼성전자주식회사 | Display apparatus, voice acquiring apparatus and voice recognition method thereof |
US8862476B2 (en) * | 2012-11-16 | 2014-10-14 | Zanavox | Voice-activated signal generator |
US9704486B2 (en) * | 2012-12-11 | 2017-07-11 | Amazon Technologies, Inc. | Speech recognition power management |
KR101732137B1 (en) * | 2013-01-07 | 2017-05-02 | 삼성전자주식회사 | Remote control apparatus and method for controlling power |
CN103116402B (en) * | 2013-02-05 | 2016-01-20 | 威盛电子股份有限公司 | There is computer system and the sound control method of voice control function |
US9256269B2 (en) * | 2013-02-20 | 2016-02-09 | Sony Computer Entertainment Inc. | Speech recognition system for performing analysis to a non-tactile inputs and generating confidence scores and based on the confidence scores transitioning the system from a first power state to a second power state |
US8994781B2 (en) | 2013-03-01 | 2015-03-31 | Citrix Systems, Inc. | Controlling an electronic conference based on detection of intended versus unintended sound |
US9361885B2 (en) | 2013-03-12 | 2016-06-07 | Nuance Communications, Inc. | Methods and apparatus for detecting a voice command |
US11393461B2 (en) | 2013-03-12 | 2022-07-19 | Cerence Operating Company | Methods and apparatus for detecting a voice command |
US9112984B2 (en) | 2013-03-12 | 2015-08-18 | Nuance Communications, Inc. | Methods and apparatus for detecting a voice command |
US9313440B2 (en) | 2013-03-14 | 2016-04-12 | Comcast Cable Communications, Llc | Remote control activation based on predicted events |
US10652394B2 (en) | 2013-03-14 | 2020-05-12 | Apple Inc. | System and method for processing voicemail |
US9467785B2 (en) | 2013-03-28 | 2016-10-11 | Knowles Electronics, Llc | MEMS apparatus with increased back volume |
US9503814B2 (en) | 2013-04-10 | 2016-11-22 | Knowles Electronics, Llc | Differential outputs in multiple motor MEMS devices |
US20140343949A1 (en) * | 2013-05-17 | 2014-11-20 | Fortemedia, Inc. | Smart microphone device |
EP3575924B1 (en) | 2013-05-23 | 2022-10-19 | Knowles Electronics, LLC | Vad detection microphone |
US10020008B2 (en) | 2013-05-23 | 2018-07-10 | Knowles Electronics, Llc | Microphone and corresponding digital interface |
US10028054B2 (en) | 2013-10-21 | 2018-07-17 | Knowles Electronics, Llc | Apparatus and method for frequency detection |
US9711166B2 (en) | 2013-05-23 | 2017-07-18 | Knowles Electronics, Llc | Decimation synchronization in a microphone |
US20180317019A1 (en) | 2013-05-23 | 2018-11-01 | Knowles Electronics, Llc | Acoustic activity detecting microphone |
US9633655B1 (en) | 2013-05-23 | 2017-04-25 | Knowles Electronics, Llc | Voice sensing and keyword analysis |
US20140358535A1 (en) * | 2013-05-28 | 2014-12-04 | Samsung Electronics Co., Ltd. | Method of executing voice recognition of electronic device and electronic device using the same |
US20140365225A1 (en) * | 2013-06-05 | 2014-12-11 | DSP Group | Ultra-low-power adaptive, user independent, voice triggering schemes |
US9548047B2 (en) | 2013-07-31 | 2017-01-17 | Google Technology Holdings LLC | Method and apparatus for evaluating trigger phrase enrollment |
CN104378723A (en) * | 2013-08-16 | 2015-02-25 | 上海耐普微电子有限公司 | Microphone with voice wake-up function |
US9386370B2 (en) | 2013-09-04 | 2016-07-05 | Knowles Electronics, Llc | Slew rate control apparatus for digital microphones |
US9502028B2 (en) | 2013-10-18 | 2016-11-22 | Knowles Electronics, Llc | Acoustic activity detection apparatus and method |
US9147397B2 (en) | 2013-10-29 | 2015-09-29 | Knowles Electronics, Llc | VAD detection apparatus and method of operating the same |
US9698999B2 (en) * | 2013-12-02 | 2017-07-04 | Amazon Technologies, Inc. | Natural language control of secondary device |
US9741343B1 (en) * | 2013-12-19 | 2017-08-22 | Amazon Technologies, Inc. | Voice interaction application selection |
KR102179506B1 (en) | 2013-12-23 | 2020-11-17 | 삼성전자 주식회사 | Electronic apparatus and control method thereof |
US20150188982A1 (en) * | 2013-12-26 | 2015-07-02 | Seenath Punnakkal | Method and apparatus for remote control of devices over network |
CN105096946B (en) * | 2014-05-08 | 2020-09-29 | 钰太芯微电子科技(上海)有限公司 | Awakening device and method based on voice activation detection |
US9368105B1 (en) * | 2014-06-26 | 2016-06-14 | Amazon Technologies, Inc. | Preventing false wake word detections with a voice-controlled device |
US10789041B2 (en) | 2014-09-12 | 2020-09-29 | Apple Inc. | Dynamic thresholds for always listening speech trigger |
US9831844B2 (en) | 2014-09-19 | 2017-11-28 | Knowles Electronics, Llc | Digital microphone with adjustable gain control |
US20160094868A1 (en) * | 2014-09-30 | 2016-03-31 | Samsung Electronics Co., Ltd. | Method and system for automatic selection of channel line up, set top box (stb) ir codes, and pay tv operator for televisions controlling an stb |
US9699550B2 (en) | 2014-11-12 | 2017-07-04 | Qualcomm Incorporated | Reduced microphone power-up latency |
US9712915B2 (en) | 2014-11-25 | 2017-07-18 | Knowles Electronics, Llc | Reference microphone for non-linear and time variant echo cancellation |
FR3030177B1 (en) * | 2014-12-16 | 2016-12-30 | Stmicroelectronics Rousset | ELECTRONIC DEVICE COMPRISING A WAKE MODULE OF AN ELECTRONIC APPARATUS DISTINCT FROM A PROCESSING HEART |
US9811312B2 (en) * | 2014-12-22 | 2017-11-07 | Intel Corporation | Connected device voice command support |
GB201509483D0 (en) * | 2014-12-23 | 2015-07-15 | Cirrus Logic Internat Uk Ltd | Feature extraction |
US10045140B2 (en) | 2015-01-07 | 2018-08-07 | Knowles Electronics, Llc | Utilizing digital microphones for low power keyword detection and noise suppression |
US9830080B2 (en) | 2015-01-21 | 2017-11-28 | Knowles Electronics, Llc | Low power voice trigger for acoustic apparatus and method |
US10121472B2 (en) | 2015-02-13 | 2018-11-06 | Knowles Electronics, Llc | Audio buffer catch-up apparatus and method with two microphones |
JP6501217B2 (en) * | 2015-02-16 | 2019-04-17 | アルパイン株式会社 | Information terminal system |
US9866938B2 (en) | 2015-02-19 | 2018-01-09 | Knowles Electronics, Llc | Interface for microphone-to-microphone communications |
US9685156B2 (en) * | 2015-03-12 | 2017-06-20 | Sony Mobile Communications Inc. | Low-power voice command detector |
US10291973B2 (en) | 2015-05-14 | 2019-05-14 | Knowles Electronics, Llc | Sensor device with ingress protection |
US9635164B2 (en) | 2015-05-14 | 2017-04-25 | Otter Products, Llc | Remote control for electronic device |
CN107534818B (en) | 2015-05-14 | 2020-06-23 | 美商楼氏电子有限公司 | Microphone (CN) |
US20160372112A1 (en) * | 2015-06-18 | 2016-12-22 | Amgine Technologies (Us), Inc. | Managing Interactions between Users and Applications |
US9478234B1 (en) | 2015-07-13 | 2016-10-25 | Knowles Electronics, Llc | Microphone apparatus and method with catch-up buffer |
US10045104B2 (en) | 2015-08-24 | 2018-08-07 | Knowles Electronics, Llc | Audio calibration using a microphone |
USD793347S1 (en) * | 2015-09-03 | 2017-08-01 | Interactive Voice, Inc. | Voice controlled automation assistant |
US10089070B1 (en) * | 2015-09-09 | 2018-10-02 | Cisco Technology, Inc. | Voice activated network interface |
US9678954B1 (en) * | 2015-10-29 | 2017-06-13 | Google Inc. | Techniques for providing lexicon data for translation of a single word speech input |
CN106814639A (en) * | 2015-11-27 | 2017-06-09 | 富泰华工业(深圳)有限公司 | Speech control system and method |
US10311862B2 (en) * | 2015-12-23 | 2019-06-04 | Rovi Guides, Inc. | Systems and methods for conversations with devices about media using interruptions and changes of subjects |
US9894437B2 (en) * | 2016-02-09 | 2018-02-13 | Knowles Electronics, Llc | Microphone assembly with pulse density modulated signal |
EP3414759B1 (en) | 2016-02-10 | 2020-07-01 | Cerence Operating Company | Techniques for spatially selective wake-up word recognition and related systems and methods |
CN105744394B (en) * | 2016-04-29 | 2019-02-15 | 福建海媚数码科技有限公司 | A kind of wireless microphone |
US10535343B2 (en) | 2016-05-10 | 2020-01-14 | Google Llc | Implementations for voice assistant on devices |
KR102177786B1 (en) | 2016-05-13 | 2020-11-12 | 구글 엘엘씨 | Media transfer between media output devices |
EP3754653A1 (en) | 2016-06-15 | 2020-12-23 | Cerence Operating Company | Techniques for wake-up word recognition and related systems and methods |
WO2018006225A1 (en) * | 2016-07-04 | 2018-01-11 | 王楚 | Acoustic control system for smart home appliance and device thereof |
US10499150B2 (en) | 2016-07-05 | 2019-12-03 | Knowles Electronics, Llc | Microphone assembly with digital feedback loop |
US20180025731A1 (en) * | 2016-07-21 | 2018-01-25 | Andrew Lovitt | Cascading Specialized Recognition Engines Based on a Recognition Policy |
US10257616B2 (en) | 2016-07-22 | 2019-04-09 | Knowles Electronics, Llc | Digital microphone assembly with improved frequency response and noise characteristics |
KR102515996B1 (en) * | 2016-08-26 | 2023-03-31 | 삼성전자주식회사 | Electronic Apparatus for Speech Recognition and Controlling Method thereof |
GB2554815B (en) | 2016-10-03 | 2021-03-31 | Google Llc | Voice-activated electronic device assembly with separable base |
US10448520B2 (en) | 2016-10-03 | 2019-10-15 | Google Llc | Voice-activated electronic device assembly with separable base |
US10535966B2 (en) | 2016-10-03 | 2020-01-14 | Google Llc | Planar electrical connector for an electronic device |
US20180124901A1 (en) * | 2016-10-12 | 2018-05-03 | Sampath Sripathy | Speech-activated dimmable led |
CN110024281B (en) | 2016-10-28 | 2024-05-07 | 三星电子株式会社 | Transducer assembly and method |
US10878591B2 (en) | 2016-11-07 | 2020-12-29 | Lincoln Global, Inc. | Welding trainer utilizing a head up display to display simulated and real-world objects |
US10913125B2 (en) | 2016-11-07 | 2021-02-09 | Lincoln Global, Inc. | Welding system providing visual and audio cues to a welding helmet with a display |
EP3535751A4 (en) | 2016-11-10 | 2020-05-20 | Nuance Communications, Inc. | Techniques for language independent wake-up word detection |
US10515632B2 (en) | 2016-11-15 | 2019-12-24 | At&T Intellectual Property I, L.P. | Asynchronous virtual assistant |
DE112017006684T5 (en) | 2016-12-30 | 2019-10-17 | Knowles Electronics, Llc | MICROPHONE ASSEMBLY WITH AUTHENTICATION |
US11164570B2 (en) | 2017-01-17 | 2021-11-02 | Ford Global Technologies, Llc | Voice assistant tracking and activation |
CN108447472B (en) * | 2017-02-16 | 2022-04-05 | 腾讯科技(深圳)有限公司 | Voice wake-up method and device |
JP6642808B2 (en) * | 2017-03-29 | 2020-02-12 | 京セラドキュメントソリューションズ株式会社 | Voice input system, voice input device, and voice input program |
US10748531B2 (en) * | 2017-04-13 | 2020-08-18 | Harman International Industries, Incorporated | Management layer for multiple intelligent personal assistant services |
US10380460B2 (en) * | 2017-05-24 | 2019-08-13 | Lenovo (Singapore) Pte. Ltd. | Description of content image |
US11489691B2 (en) | 2017-07-12 | 2022-11-01 | Universal Electronics Inc. | Apparatus, system and method for directing voice input in a controlling device |
US10930276B2 (en) | 2017-07-12 | 2021-02-23 | Universal Electronics Inc. | Apparatus, system and method for directing voice input in a controlling device |
WO2019016135A1 (en) * | 2017-07-19 | 2019-01-24 | Philips Lighting Holding B.V. | Speech control |
CN107307696A (en) * | 2017-08-07 | 2017-11-03 | 深圳市崧森智能科技有限公司 | A kind of Intelligent Recognition pillow and preparation method thereof |
US11025356B2 (en) | 2017-09-08 | 2021-06-01 | Knowles Electronics, Llc | Clock synchronization in a master-slave communication system |
US10887125B2 (en) | 2017-09-15 | 2021-01-05 | Kohler Co. | Bathroom speaker |
US11099540B2 (en) | 2017-09-15 | 2021-08-24 | Kohler Co. | User identity in household appliances |
US11093554B2 (en) | 2017-09-15 | 2021-08-17 | Kohler Co. | Feedback for water consuming appliance |
US11314214B2 (en) | 2017-09-15 | 2022-04-26 | Kohler Co. | Geographic analysis of water conditions |
US10448762B2 (en) | 2017-09-15 | 2019-10-22 | Kohler Co. | Mirror |
US11061642B2 (en) | 2017-09-29 | 2021-07-13 | Knowles Electronics, Llc | Multi-core audio processor with flexible memory allocation |
US11164408B2 (en) * | 2017-10-31 | 2021-11-02 | Sargent Manufacturing Company | Lock systems and methods |
CN108093350B (en) * | 2017-12-21 | 2020-12-15 | 广东小天才科技有限公司 | Microphone control method and microphone |
JP7374099B2 (en) * | 2018-01-03 | 2023-11-06 | ユニバーサル エレクトロニクス インコーポレイテッド | Apparatus, system and method for instructing voice input in a control device |
EP3564949A1 (en) | 2018-04-23 | 2019-11-06 | Spotify AB | Activation trigger processing |
KR20190139489A (en) * | 2018-06-08 | 2019-12-18 | 삼성전자주식회사 | method for operating speech recognition service and electronic device supporting the same |
CN108962240B (en) * | 2018-06-14 | 2021-09-21 | 百度在线网络技术(北京)有限公司 | Voice control method and system based on earphone |
US10659855B2 (en) * | 2018-06-20 | 2020-05-19 | Amazon Technologies, Inc. | Voice activated device with integrated heatsink and speaker |
CN108986812A (en) * | 2018-08-31 | 2018-12-11 | 傅小燕 | The control method and its controller and electronic product of repetition individual character voice-controlled electronic product |
TWI682322B (en) * | 2018-09-06 | 2020-01-11 | 廣達電腦股份有限公司 | Command processing device and method |
WO2020055923A1 (en) | 2018-09-11 | 2020-03-19 | Knowles Electronics, Llc | Digital microphone with reduced processing noise |
US10908880B2 (en) | 2018-10-19 | 2021-02-02 | Knowles Electronics, Llc | Audio signal circuit with in-place bit-reversal |
KR20200084730A (en) * | 2019-01-03 | 2020-07-13 | 삼성전자주식회사 | Electronic device and control method thereof |
CN110220589A (en) * | 2019-06-20 | 2019-09-10 | 华电重工股份有限公司 | A kind of noise on-line measuring device and system |
KR102246661B1 (en) * | 2019-06-25 | 2021-05-03 | 엘지전자 주식회사 | Method and apparatus for selecting voice enable device |
US10977909B2 (en) | 2019-07-10 | 2021-04-13 | Motorola Mobility Llc | Synchronizing notifications with media playback |
CN110473542B (en) * | 2019-09-06 | 2022-04-15 | 北京安云世纪科技有限公司 | Awakening method and device for voice instruction execution function and electronic equipment |
KR20210147678A (en) * | 2020-05-29 | 2021-12-07 | 엘지전자 주식회사 | Artificial intelligence device |
US11995297B2 (en) * | 2021-03-08 | 2024-05-28 | Samsung Electronics Co., Ltd. | Enhanced user interface (UI) button control for mobile applications |
USD1025062S1 (en) | 2022-12-30 | 2024-04-30 | Aurora Multimedia Corp. | Touch panel control interface |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4725827A (en) * | 1986-06-23 | 1988-02-16 | Pulsar Manufacturing, Inc. | Hand held remote control device |
US4771283A (en) * | 1985-01-16 | 1988-09-13 | Alpine Electronics Inc. | Remote control device |
US5199080A (en) * | 1989-12-29 | 1993-03-30 | Pioneer Electronic Corporation | Voice-operated remote control system |
US5444673A (en) * | 1994-07-12 | 1995-08-22 | Mathurin; Trevor S. | Audio controlled and activated wristwatch memory aid device |
US6012029A (en) * | 1995-09-29 | 2000-01-04 | Cirino; Sepideh S. | Voice activated system for locating misplaced items |
Family Cites Families (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4322718A (en) | 1980-05-19 | 1982-03-30 | Paul Faierstain | Sound-activated rotary device |
US4774511A (en) | 1985-05-30 | 1988-09-27 | Nap Consumer Electronics Corp. | Universal remote control unit |
JPS63171071A (en) * | 1987-01-08 | 1988-07-14 | Matsushita Commun Ind Co Ltd | Speech controller |
US4959810A (en) | 1987-10-14 | 1990-09-25 | Universal Electronics, Inc. | Universal remote control device |
JPH01218296A (en) | 1988-02-26 | 1989-08-31 | Nec Home Electron Ltd | Remote control receiver with study function |
US5008954A (en) * | 1989-04-06 | 1991-04-16 | Carl Oppendahl | Voice-activated radio transceiver |
US5142398A (en) | 1989-07-11 | 1992-08-25 | Tandy Corporation | Timer system for learning and replaying of infrared signals |
US5247580A (en) | 1989-12-29 | 1993-09-21 | Pioneer Electronic Corporation | Voice-operated remote control system |
US5267323A (en) | 1989-12-29 | 1993-11-30 | Pioneer Electronic Corporation | Voice-operated remote control system |
US5226090A (en) | 1989-12-29 | 1993-07-06 | Pioneer Electronic Corporation | Voice-operated remote control system |
JPH07109560B2 (en) | 1990-11-30 | 1995-11-22 | 富士通テン株式会社 | Voice recognizer |
KR100202425B1 (en) | 1992-08-27 | 1999-06-15 | 정호선 | Voice recognition system for recognizing the remote controller command of electronic equipment |
US5715321A (en) * | 1992-10-29 | 1998-02-03 | Andrea Electronics Coporation | Noise cancellation headset for use with stand or worn on ear |
US5691710A (en) | 1992-11-02 | 1997-11-25 | Zenith Electronics Corporation | Self learning IR remote control transmitter |
US5603036A (en) * | 1993-02-19 | 1997-02-11 | Intel Corporation | Power management system for components used in battery powered applications |
CH689410A5 (en) | 1994-04-21 | 1999-03-31 | Info Byte Ag | Method and apparatus for voice-activated remote control of electrical loads. |
US5452274A (en) | 1994-06-09 | 1995-09-19 | Thompson; Barbara J. | Sound-activated playback device |
US5790754A (en) | 1994-10-21 | 1998-08-04 | Sensory Circuits, Inc. | Speech recognition apparatus for consumer electronic applications |
US5774859A (en) | 1995-01-03 | 1998-06-30 | Scientific-Atlanta, Inc. | Information system having a speech interface |
US6070140A (en) * | 1995-06-05 | 2000-05-30 | Tran; Bao Q. | Speech recognizer |
JP3674990B2 (en) | 1995-08-21 | 2005-07-27 | セイコーエプソン株式会社 | Speech recognition dialogue apparatus and speech recognition dialogue processing method |
US6052666A (en) * | 1995-11-06 | 2000-04-18 | Thomson Multimedia S.A. | Vocal identification of devices in a home environment |
US5905279A (en) * | 1996-04-09 | 1999-05-18 | Kabushiki Kaisha Toshiba | Low resistant trench fill for a semiconductor device |
US5777571A (en) | 1996-10-02 | 1998-07-07 | Holtek Microelectronics, Inc. | Remote control device for voice recognition and user identification restrictions |
US6188985B1 (en) * | 1997-01-06 | 2001-02-13 | Texas Instruments Incorporated | Wireless voice-activated device for control of a processor-based host system |
DE19740406C2 (en) | 1997-09-09 | 1999-08-05 | Helling Michael Dipl Ing Fh | Infinitely adjustable gear |
DE19740706A1 (en) * | 1997-09-16 | 1999-04-01 | Michael Kaiser | Speech-controlled remote operating device for electronic device remote control |
US6119088A (en) | 1998-03-03 | 2000-09-12 | Ciluffo; Gary | Appliance control programmer using voice recognition |
US6606280B1 (en) * | 1999-02-22 | 2003-08-12 | Hewlett-Packard Development Company | Voice-operated remote control |
US6397186B1 (en) * | 1999-12-22 | 2002-05-28 | Ambush Interactive, Inc. | Hands-free, voice-operated remote control transmitter |
-
1999
- 1999-12-22 US US09/469,707 patent/US6397186B1/en not_active Expired - Lifetime
-
2000
- 2000-12-21 US US10/168,935 patent/US7080014B2/en not_active Expired - Fee Related
- 2000-12-21 CA CA002395856A patent/CA2395856A1/en not_active Abandoned
- 2000-12-21 WO PCT/US2000/035107 patent/WO2001046946A1/en active Application Filing
- 2000-12-21 EP EP00986713A patent/EP1240643A4/en not_active Withdrawn
- 2000-12-21 AU AU22902/01A patent/AU2290201A/en not_active Abandoned
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4771283A (en) * | 1985-01-16 | 1988-09-13 | Alpine Electronics Inc. | Remote control device |
US4725827A (en) * | 1986-06-23 | 1988-02-16 | Pulsar Manufacturing, Inc. | Hand held remote control device |
US5199080A (en) * | 1989-12-29 | 1993-03-30 | Pioneer Electronic Corporation | Voice-operated remote control system |
US5444673A (en) * | 1994-07-12 | 1995-08-22 | Mathurin; Trevor S. | Audio controlled and activated wristwatch memory aid device |
US6012029A (en) * | 1995-09-29 | 2000-01-04 | Cirino; Sepideh S. | Voice activated system for locating misplaced items |
Non-Patent Citations (1)
Title |
---|
See also references of EP1240643A4 * |
Cited By (175)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9646614B2 (en) | 2000-03-16 | 2017-05-09 | Apple Inc. | Fast, language-independent method for user authentication by voice |
WO2003083801A2 (en) | 2002-03-29 | 2003-10-09 | Koninklijke Philips Electronics N.V. | Programmable remote control and method for programming a programmable remote control, a readable memory and a program |
WO2003083801A3 (en) * | 2002-03-29 | 2004-07-22 | Koninkl Philips Electronics Nv | Programmable remote control and method for programming a programmable remote control, a readable memory and a program |
US10318871B2 (en) | 2005-09-08 | 2019-06-11 | Apple Inc. | Method and apparatus for building an intelligent automated assistant |
US9117447B2 (en) | 2006-09-08 | 2015-08-25 | Apple Inc. | Using event alert text as input to an automated assistant |
US8942986B2 (en) | 2006-09-08 | 2015-01-27 | Apple Inc. | Determining user intent based on ontologies of domains |
US8930191B2 (en) | 2006-09-08 | 2015-01-06 | Apple Inc. | Paraphrasing of user requests and results by automated digital assistant |
US10568032B2 (en) | 2007-04-03 | 2020-02-18 | Apple Inc. | Method and system for operating a multi-function portable electronic device using voice-activation |
US9330720B2 (en) | 2008-01-03 | 2016-05-03 | Apple Inc. | Methods and apparatus for altering audio output signals |
US10381016B2 (en) | 2008-01-03 | 2019-08-13 | Apple Inc. | Methods and apparatus for altering audio output signals |
US9626955B2 (en) | 2008-04-05 | 2017-04-18 | Apple Inc. | Intelligent text-to-speech conversion |
US9865248B2 (en) | 2008-04-05 | 2018-01-09 | Apple Inc. | Intelligent text-to-speech conversion |
US10108612B2 (en) | 2008-07-31 | 2018-10-23 | Apple Inc. | Mobile device having human language translation capability with positional feedback |
US9535906B2 (en) | 2008-07-31 | 2017-01-03 | Apple Inc. | Mobile device having human language translation capability with positional feedback |
US9959870B2 (en) | 2008-12-11 | 2018-05-01 | Apple Inc. | Speech recognition involving a mobile device |
US9858925B2 (en) | 2009-06-05 | 2018-01-02 | Apple Inc. | Using context information to facilitate processing of commands in a virtual assistant |
US10795541B2 (en) | 2009-06-05 | 2020-10-06 | Apple Inc. | Intelligent organization of tasks items |
US10475446B2 (en) | 2009-06-05 | 2019-11-12 | Apple Inc. | Using context information to facilitate processing of commands in a virtual assistant |
US11080012B2 (en) | 2009-06-05 | 2021-08-03 | Apple Inc. | Interface for a virtual digital assistant |
US10283110B2 (en) | 2009-07-02 | 2019-05-07 | Apple Inc. | Methods and apparatuses for automatic speech recognition |
CN104020978A (en) * | 2010-01-13 | 2014-09-03 | 苹果公司 | Processing of voice inputs |
AU2015203169B2 (en) * | 2010-01-13 | 2017-04-27 | Apple Inc. | Processing of voice inputs |
AU2011205411B2 (en) * | 2010-01-13 | 2015-03-05 | Apple Inc. | Processing of voice inputs |
KR101393816B1 (en) * | 2010-01-13 | 2014-05-12 | 애플 인크. | Processing of voice inputs |
US8670985B2 (en) | 2010-01-13 | 2014-03-11 | Apple Inc. | Devices and methods for identifying a prompt corresponding to a voice input in a sequence of prompts |
CN102763159A (en) * | 2010-01-13 | 2012-10-31 | 苹果公司 | Processing of voice inputs |
WO2011088038A1 (en) | 2010-01-13 | 2011-07-21 | Apple Inc. | Processing of voice inputs |
US10276170B2 (en) | 2010-01-18 | 2019-04-30 | Apple Inc. | Intelligent automated assistant |
US8903716B2 (en) | 2010-01-18 | 2014-12-02 | Apple Inc. | Personalized vocabulary for digital assistant |
US9318108B2 (en) | 2010-01-18 | 2016-04-19 | Apple Inc. | Intelligent automated assistant |
US9548050B2 (en) | 2010-01-18 | 2017-01-17 | Apple Inc. | Intelligent automated assistant |
US12087308B2 (en) | 2010-01-18 | 2024-09-10 | Apple Inc. | Intelligent automated assistant |
US10705794B2 (en) | 2010-01-18 | 2020-07-07 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
US10706841B2 (en) | 2010-01-18 | 2020-07-07 | Apple Inc. | Task flow identification based on user intent |
US10496753B2 (en) | 2010-01-18 | 2019-12-03 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
US11423886B2 (en) | 2010-01-18 | 2022-08-23 | Apple Inc. | Task flow identification based on user intent |
US8892446B2 (en) | 2010-01-18 | 2014-11-18 | Apple Inc. | Service orchestration for intelligent automated assistant |
US10679605B2 (en) | 2010-01-18 | 2020-06-09 | Apple Inc. | Hands-free list-reading by intelligent automated assistant |
US10553209B2 (en) | 2010-01-18 | 2020-02-04 | Apple Inc. | Systems and methods for hands-free notification summaries |
US10984326B2 (en) | 2010-01-25 | 2021-04-20 | Newvaluexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US10984327B2 (en) | 2010-01-25 | 2021-04-20 | New Valuexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US11410053B2 (en) | 2010-01-25 | 2022-08-09 | Newvaluexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US10607140B2 (en) | 2010-01-25 | 2020-03-31 | Newvaluexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US10607141B2 (en) | 2010-01-25 | 2020-03-31 | Newvaluexchange Ltd. | Apparatuses, methods and systems for a digital conversation management platform |
US9633660B2 (en) | 2010-02-25 | 2017-04-25 | Apple Inc. | User profiling for voice input processing |
US10049675B2 (en) | 2010-02-25 | 2018-08-14 | Apple Inc. | User profiling for voice input processing |
US10762293B2 (en) | 2010-12-22 | 2020-09-01 | Apple Inc. | Using parts-of-speech tagging and named entity recognition for spelling correction |
US9262612B2 (en) | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
US10102359B2 (en) | 2011-03-21 | 2018-10-16 | Apple Inc. | Device access using voice authentication |
US10057736B2 (en) | 2011-06-03 | 2018-08-21 | Apple Inc. | Active transport based notifications |
US10706373B2 (en) | 2011-06-03 | 2020-07-07 | Apple Inc. | Performing actions associated with task items that represent tasks to perform |
US11120372B2 (en) | 2011-06-03 | 2021-09-14 | Apple Inc. | Performing actions associated with task items that represent tasks to perform |
US10241644B2 (en) | 2011-06-03 | 2019-03-26 | Apple Inc. | Actionable reminder entries |
US9798393B2 (en) | 2011-08-29 | 2017-10-24 | Apple Inc. | Text correction processing |
US10241752B2 (en) | 2011-09-30 | 2019-03-26 | Apple Inc. | Interface for a virtual digital assistant |
US10134385B2 (en) | 2012-03-02 | 2018-11-20 | Apple Inc. | Systems and methods for name pronunciation |
US9483461B2 (en) | 2012-03-06 | 2016-11-01 | Apple Inc. | Handling speech synthesis of content for multiple languages |
US9953088B2 (en) | 2012-05-14 | 2018-04-24 | Apple Inc. | Crowd sourcing information to fulfill user requests |
US10079014B2 (en) | 2012-06-08 | 2018-09-18 | Apple Inc. | Name recognition system |
US9495129B2 (en) | 2012-06-29 | 2016-11-15 | Apple Inc. | Device, method, and user interface for voice-activated navigation and browsing of a document |
US9576574B2 (en) | 2012-09-10 | 2017-02-21 | Apple Inc. | Context-sensitive handling of interruptions by intelligent digital assistant |
US9971774B2 (en) | 2012-09-19 | 2018-05-15 | Apple Inc. | Voice-based media searching |
US10978090B2 (en) | 2013-02-07 | 2021-04-13 | Apple Inc. | Voice trigger for a digital assistant |
US10199051B2 (en) | 2013-02-07 | 2019-02-05 | Apple Inc. | Voice trigger for a digital assistant |
US9368114B2 (en) | 2013-03-14 | 2016-06-14 | Apple Inc. | Context-sensitive handling of interruptions |
US9697822B1 (en) | 2013-03-15 | 2017-07-04 | Apple Inc. | System and method for updating an adaptive speech recognition model |
US9922642B2 (en) | 2013-03-15 | 2018-03-20 | Apple Inc. | Training an at least partial voice command system |
CN105210146A (en) * | 2013-05-07 | 2015-12-30 | 高通股份有限公司 | Method and apparatus for controlling voice activation |
US9892729B2 (en) | 2013-05-07 | 2018-02-13 | Qualcomm Incorporated | Method and apparatus for controlling voice activation |
WO2014182458A1 (en) * | 2013-05-07 | 2014-11-13 | Qualcomm Incorporated | Method and apparatus for controlling voice activation |
US9620104B2 (en) | 2013-06-07 | 2017-04-11 | Apple Inc. | System and method for user-specified pronunciation of words for speech synthesis and recognition |
US9633674B2 (en) | 2013-06-07 | 2017-04-25 | Apple Inc. | System and method for detecting errors in interactions with a voice-based digital assistant |
US9966060B2 (en) | 2013-06-07 | 2018-05-08 | Apple Inc. | System and method for user-specified pronunciation of words for speech synthesis and recognition |
US9582608B2 (en) | 2013-06-07 | 2017-02-28 | Apple Inc. | Unified ranking with entropy-weighted information for phrase-based semantic auto-completion |
US9966068B2 (en) | 2013-06-08 | 2018-05-08 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US10657961B2 (en) | 2013-06-08 | 2020-05-19 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US10176167B2 (en) | 2013-06-09 | 2019-01-08 | Apple Inc. | System and method for inferring user intent from speech inputs |
US10185542B2 (en) | 2013-06-09 | 2019-01-22 | Apple Inc. | Device, method, and graphical user interface for enabling conversation persistence across two or more instances of a digital assistant |
US9300784B2 (en) | 2013-06-13 | 2016-03-29 | Apple Inc. | System and method for emergency calls initiated by voice command |
US10791216B2 (en) | 2013-08-06 | 2020-09-29 | Apple Inc. | Auto-activating smart responses based on activities from remote devices |
WO2015164047A1 (en) * | 2014-04-21 | 2015-10-29 | Qualcomm Incorporated | Method and apparatus for activating application by speech input |
US10770075B2 (en) | 2014-04-21 | 2020-09-08 | Qualcomm Incorporated | Method and apparatus for activating application by speech input |
US9620105B2 (en) | 2014-05-15 | 2017-04-11 | Apple Inc. | Analyzing audio input for efficient speech and music recognition |
US10592095B2 (en) | 2014-05-23 | 2020-03-17 | Apple Inc. | Instantaneous speaking of content on touch devices |
US9502031B2 (en) | 2014-05-27 | 2016-11-22 | Apple Inc. | Method for supporting dynamic grammars in WFST-based ASR |
US9734193B2 (en) | 2014-05-30 | 2017-08-15 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
US9842101B2 (en) | 2014-05-30 | 2017-12-12 | Apple Inc. | Predictive conversion of language input |
US9966065B2 (en) | 2014-05-30 | 2018-05-08 | Apple Inc. | Multi-command single utterance input method |
US11133008B2 (en) | 2014-05-30 | 2021-09-28 | Apple Inc. | Reducing the need for manual start/end-pointing and trigger phrases |
US9785630B2 (en) | 2014-05-30 | 2017-10-10 | Apple Inc. | Text prediction using combined word N-gram and unigram language models |
US10169329B2 (en) | 2014-05-30 | 2019-01-01 | Apple Inc. | Exemplar-based natural language processing |
US10170123B2 (en) | 2014-05-30 | 2019-01-01 | Apple Inc. | Intelligent assistant for home automation |
US9430463B2 (en) | 2014-05-30 | 2016-08-30 | Apple Inc. | Exemplar-based natural language processing |
US9760559B2 (en) | 2014-05-30 | 2017-09-12 | Apple Inc. | Predictive text input |
US10083690B2 (en) | 2014-05-30 | 2018-09-25 | Apple Inc. | Better resolution when referencing to concepts |
US11257504B2 (en) | 2014-05-30 | 2022-02-22 | Apple Inc. | Intelligent assistant for home automation |
US10497365B2 (en) | 2014-05-30 | 2019-12-03 | Apple Inc. | Multi-command single utterance input method |
US9715875B2 (en) | 2014-05-30 | 2017-07-25 | Apple Inc. | Reducing the need for manual start/end-pointing and trigger phrases |
US10289433B2 (en) | 2014-05-30 | 2019-05-14 | Apple Inc. | Domain specific language for encoding assistant dialog |
US9633004B2 (en) | 2014-05-30 | 2017-04-25 | Apple Inc. | Better resolution when referencing to concepts |
US10078631B2 (en) | 2014-05-30 | 2018-09-18 | Apple Inc. | Entropy-guided text prediction using combined word and character n-gram language models |
US10659851B2 (en) | 2014-06-30 | 2020-05-19 | Apple Inc. | Real-time digital assistant knowledge updates |
US10904611B2 (en) | 2014-06-30 | 2021-01-26 | Apple Inc. | Intelligent automated assistant for TV user interactions |
EP3576085A1 (en) * | 2014-06-30 | 2019-12-04 | Samsung Electronics Co., Ltd. | Operating method for microphones and electronic device supporting the same |
US9338493B2 (en) | 2014-06-30 | 2016-05-10 | Apple Inc. | Intelligent automated assistant for TV user interactions |
US9668024B2 (en) | 2014-06-30 | 2017-05-30 | Apple Inc. | Intelligent automated assistant for TV user interactions |
US10643613B2 (en) | 2014-06-30 | 2020-05-05 | Samsung Electronics Co., Ltd. | Operating method for microphones and electronic device supporting the same |
EP3162085A4 (en) * | 2014-06-30 | 2018-01-24 | Samsung Electronics Co., Ltd. | Operating method for microphones and electronic device supporting the same |
US10062382B2 (en) | 2014-06-30 | 2018-08-28 | Samsung Electronics Co., Ltd. | Operating method for microphones and electronic device supporting the same |
US10446141B2 (en) | 2014-08-28 | 2019-10-15 | Apple Inc. | Automatic speech recognition based on user feedback |
US10431204B2 (en) | 2014-09-11 | 2019-10-01 | Apple Inc. | Method and apparatus for discovering trending terms in speech requests |
US9818400B2 (en) | 2014-09-11 | 2017-11-14 | Apple Inc. | Method and apparatus for discovering trending terms in speech requests |
US10074360B2 (en) | 2014-09-30 | 2018-09-11 | Apple Inc. | Providing an indication of the suitability of speech recognition |
US9886432B2 (en) | 2014-09-30 | 2018-02-06 | Apple Inc. | Parsimonious handling of word inflection via categorical stem + suffix N-gram language models |
US9986419B2 (en) | 2014-09-30 | 2018-05-29 | Apple Inc. | Social reminders |
US9668121B2 (en) | 2014-09-30 | 2017-05-30 | Apple Inc. | Social reminders |
US10127911B2 (en) | 2014-09-30 | 2018-11-13 | Apple Inc. | Speaker identification and unsupervised speaker adaptation techniques |
US9646609B2 (en) | 2014-09-30 | 2017-05-09 | Apple Inc. | Caching apparatus for serving phonetic pronunciations |
US11556230B2 (en) | 2014-12-02 | 2023-01-17 | Apple Inc. | Data detection |
US10552013B2 (en) | 2014-12-02 | 2020-02-04 | Apple Inc. | Data detection |
US9711141B2 (en) | 2014-12-09 | 2017-07-18 | Apple Inc. | Disambiguating heteronyms in speech synthesis |
US9865280B2 (en) | 2015-03-06 | 2018-01-09 | Apple Inc. | Structured dictation using intelligent automated assistants |
US10311871B2 (en) | 2015-03-08 | 2019-06-04 | Apple Inc. | Competing devices responding to voice triggers |
US9721566B2 (en) | 2015-03-08 | 2017-08-01 | Apple Inc. | Competing devices responding to voice triggers |
US11087759B2 (en) | 2015-03-08 | 2021-08-10 | Apple Inc. | Virtual assistant activation |
US9886953B2 (en) | 2015-03-08 | 2018-02-06 | Apple Inc. | Virtual assistant activation |
US10567477B2 (en) | 2015-03-08 | 2020-02-18 | Apple Inc. | Virtual assistant continuity |
US9899019B2 (en) | 2015-03-18 | 2018-02-20 | Apple Inc. | Systems and methods for structured stem and suffix language models |
US9842105B2 (en) | 2015-04-16 | 2017-12-12 | Apple Inc. | Parsimonious continuous-space phrase representations for natural language processing |
US10083688B2 (en) | 2015-05-27 | 2018-09-25 | Apple Inc. | Device voice control for selecting a displayed affordance |
US10127220B2 (en) | 2015-06-04 | 2018-11-13 | Apple Inc. | Language identification from short strings |
US10101822B2 (en) | 2015-06-05 | 2018-10-16 | Apple Inc. | Language input correction |
US10356243B2 (en) | 2015-06-05 | 2019-07-16 | Apple Inc. | Virtual assistant aided communication with 3rd party service in a communication session |
US10186254B2 (en) | 2015-06-07 | 2019-01-22 | Apple Inc. | Context-based endpoint detection |
US10255907B2 (en) | 2015-06-07 | 2019-04-09 | Apple Inc. | Automatic accent detection using acoustic models |
US11025565B2 (en) | 2015-06-07 | 2021-06-01 | Apple Inc. | Personalized prediction of responses for instant messaging |
US10671428B2 (en) | 2015-09-08 | 2020-06-02 | Apple Inc. | Distributed personal assistant |
US11500672B2 (en) | 2015-09-08 | 2022-11-15 | Apple Inc. | Distributed personal assistant |
US10747498B2 (en) | 2015-09-08 | 2020-08-18 | Apple Inc. | Zero latency digital assistant |
US9697820B2 (en) | 2015-09-24 | 2017-07-04 | Apple Inc. | Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks |
US10366158B2 (en) | 2015-09-29 | 2019-07-30 | Apple Inc. | Efficient word encoding for recurrent neural network language models |
US11010550B2 (en) | 2015-09-29 | 2021-05-18 | Apple Inc. | Unified language modeling framework for word prediction, auto-completion and auto-correction |
US11587559B2 (en) | 2015-09-30 | 2023-02-21 | Apple Inc. | Intelligent device identification |
US10691473B2 (en) | 2015-11-06 | 2020-06-23 | Apple Inc. | Intelligent automated assistant in a messaging environment |
US11526368B2 (en) | 2015-11-06 | 2022-12-13 | Apple Inc. | Intelligent automated assistant in a messaging environment |
US10049668B2 (en) | 2015-12-02 | 2018-08-14 | Apple Inc. | Applying neural network language models to weighted finite state transducers for automatic speech recognition |
US10223066B2 (en) | 2015-12-23 | 2019-03-05 | Apple Inc. | Proactive assistance based on dialog communication between devices |
US10446143B2 (en) | 2016-03-14 | 2019-10-15 | Apple Inc. | Identification of voice inputs providing credentials |
US9934775B2 (en) | 2016-05-26 | 2018-04-03 | Apple Inc. | Unit-selection text-to-speech synthesis based on predicted concatenation parameters |
US9972304B2 (en) | 2016-06-03 | 2018-05-15 | Apple Inc. | Privacy preserving distributed evaluation framework for embedded personalized systems |
US10249300B2 (en) | 2016-06-06 | 2019-04-02 | Apple Inc. | Intelligent list reading |
US10049663B2 (en) | 2016-06-08 | 2018-08-14 | Apple, Inc. | Intelligent automated assistant for media exploration |
US11069347B2 (en) | 2016-06-08 | 2021-07-20 | Apple Inc. | Intelligent automated assistant for media exploration |
US10354011B2 (en) | 2016-06-09 | 2019-07-16 | Apple Inc. | Intelligent automated assistant in a home environment |
US10490187B2 (en) | 2016-06-10 | 2019-11-26 | Apple Inc. | Digital assistant providing automated status report |
US10509862B2 (en) | 2016-06-10 | 2019-12-17 | Apple Inc. | Dynamic phrase expansion of language input |
US10192552B2 (en) | 2016-06-10 | 2019-01-29 | Apple Inc. | Digital assistant providing whispered speech |
US10733993B2 (en) | 2016-06-10 | 2020-08-04 | Apple Inc. | Intelligent digital assistant in a multi-tasking environment |
US11037565B2 (en) | 2016-06-10 | 2021-06-15 | Apple Inc. | Intelligent digital assistant in a multi-tasking environment |
US10067938B2 (en) | 2016-06-10 | 2018-09-04 | Apple Inc. | Multilingual word prediction |
US11152002B2 (en) | 2016-06-11 | 2021-10-19 | Apple Inc. | Application integration with a digital assistant |
US10269345B2 (en) | 2016-06-11 | 2019-04-23 | Apple Inc. | Intelligent task discovery |
US10521466B2 (en) | 2016-06-11 | 2019-12-31 | Apple Inc. | Data driven natural language event detection and classification |
US10297253B2 (en) | 2016-06-11 | 2019-05-21 | Apple Inc. | Application integration with a digital assistant |
US10089072B2 (en) | 2016-06-11 | 2018-10-02 | Apple Inc. | Intelligent device arbitration and control |
US10043516B2 (en) | 2016-09-23 | 2018-08-07 | Apple Inc. | Intelligent automated assistant |
US10553215B2 (en) | 2016-09-23 | 2020-02-04 | Apple Inc. | Intelligent automated assistant |
US10593346B2 (en) | 2016-12-22 | 2020-03-17 | Apple Inc. | Rank-reduced token representation for automatic speech recognition |
US10755703B2 (en) | 2017-05-11 | 2020-08-25 | Apple Inc. | Offline personal assistant |
US11405466B2 (en) | 2017-05-12 | 2022-08-02 | Apple Inc. | Synchronization and task delegation of a digital assistant |
US10410637B2 (en) | 2017-05-12 | 2019-09-10 | Apple Inc. | User-specific acoustic models |
US10791176B2 (en) | 2017-05-12 | 2020-09-29 | Apple Inc. | Synchronization and task delegation of a digital assistant |
US10810274B2 (en) | 2017-05-15 | 2020-10-20 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
US10482874B2 (en) | 2017-05-15 | 2019-11-19 | Apple Inc. | Hierarchical belief states for digital assistants |
US11217255B2 (en) | 2017-05-16 | 2022-01-04 | Apple Inc. | Far-field extension for digital assistant services |
Also Published As
Publication number | Publication date |
---|---|
US6397186B1 (en) | 2002-05-28 |
US7080014B2 (en) | 2006-07-18 |
AU2290201A (en) | 2001-07-03 |
EP1240643A4 (en) | 2005-09-07 |
EP1240643A1 (en) | 2002-09-18 |
CA2395856A1 (en) | 2001-06-28 |
US20040128137A1 (en) | 2004-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2001046946A1 (en) | Hands-free, voice-operated remote control transmitter | |
US8797149B2 (en) | State-based control systems and methods | |
US8026789B2 (en) | State-based remote control system | |
US8271287B1 (en) | Voice command remote control system | |
US7333025B2 (en) | Remote control apparatus, electronic apparatus, and available-button indicating method | |
US20050212685A1 (en) | Talking remote appliance-controller for the blind | |
US4716576A (en) | Apparatus for controlling transmitter-receiver | |
JP3683502B2 (en) | Remote control device | |
JP2973311B1 (en) | Remote control device | |
WO1994003017A1 (en) | Universal remote control device | |
JPH05219575A (en) | Remote controller | |
JP2002345054A (en) | Remote control device, electric/electronic equipment and electric/electronic equipment system | |
JP2007228520A (en) | Remote control unit and program | |
JP2003228390A (en) | Voice controller | |
JPH0652664A (en) | Control device | |
JP2004207799A (en) | Remote control method, remote controller, server apparatus, and program | |
JP3092372U (en) | Remote control system | |
JPH062383Y2 (en) | Audio equipment with remote control transmitter | |
JP2003151248A (en) | Portable audio playback unit | |
JP2001069579A (en) | Electrical household appliance good with remote controller | |
JPH03241555A (en) | Remote controller | |
JPH0298299A (en) | Wireless remote controller | |
JPH10327476A (en) | Remote control system, remote controller and electric equipment | |
JPH05244672A (en) | Remote control transmitter | |
JPH03163962A (en) | Remote control transmitter for television receiver |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CU CZ DE DK DZ EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MD MG MK MN MW MX MZ NO NZ PL PT RO RU SD SE SG SI SK SL TJ TM TR TT UA UG US UZ VN YU ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2395856 Country of ref document: CA |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2000986713 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 2000986713 Country of ref document: EP |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 10168935 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: JP |