CA2407930A1 - Input device for voice recognition and articulation using keystroke data. - Google Patents
Input device for voice recognition and articulation using keystroke data. Download PDFInfo
- Publication number
- CA2407930A1 CA2407930A1 CA002407930A CA2407930A CA2407930A1 CA 2407930 A1 CA2407930 A1 CA 2407930A1 CA 002407930 A CA002407930 A CA 002407930A CA 2407930 A CA2407930 A CA 2407930A CA 2407930 A1 CA2407930 A1 CA 2407930A1
- Authority
- CA
- Canada
- Prior art keywords
- voice
- input
- signal
- recognition
- keystroke
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Abstract
An input device is disclosed having an interface controller (12) which transmits both keystroke (13) and voice data (14) to a computer. The computer may split the data for separate processing and include vocal articulation processing for voice or speech recognition. The input device may be a voice recognition keyboard where voice recognition processing is local to the keyboard and the keyboard may remotely control multimedia electronic devices.
The spoken commands to the input device may initiate internet access. The invention further contemplates methods for providing keystroke and voice input (17) to a computer system over a single interface for voice or speech recognition, converting spoken words into text, providing access to the internet from a computer connected to the internet, or remotely controlling at least one electronic device with a spoken command.
The spoken commands to the input device may initiate internet access. The invention further contemplates methods for providing keystroke and voice input (17) to a computer system over a single interface for voice or speech recognition, converting spoken words into text, providing access to the internet from a computer connected to the internet, or remotely controlling at least one electronic device with a spoken command.
Description
INPUT DEVICE FOR VOICE RECOGNITION AND ARTICULATION USING KEYSTROKE DATA.
Field of the Invention This invention relates to input devices for interfacing with electronic devices. More specifically the invention relates to computer keyboards, voice and speech recognition systems, and control systems for electronic apparatus.
1o Background of the Invention It is known in the prior art that voice detection capability can be integrated with a keyboard. For example, U.S. Patent No. 5,659,665 to Whelpley, Jr.
("the Whelpley '665 Patent") discloses an external device inserted at the_data cable 15 between the keyboard and the computer system. The external device adds voice recognition capability to the computer by converting voice signals into keystroke data sent to the computer's keyboard port, while permitting ordinary signals generated at the keyboard itself to pass through the external device as usual to the computer.
The voice recognition system disclosed by the Whelpley '665 Patent is self contained in that the 2o voice input, and the voice recognition hardware is confined to the external device, as is the processing of the voice input signal. The voice commands are never transmitted to the computer except as their keyboard data equivalent, and computer processing,time is not consumed in carrying out the voice recognition function.
The Whelpley '665 Patent also discloses an embodiment wherein the 25 voice recognition device is contained within the keyboard housing. Similar to the external embodiment, the device functions by converting voice signals to keystroke data and inserting the data into the data stream coming from the keyboard. The combination disclosed in the Whelpley '665 Patent effectively disguises the-voice recognition function making it transparent to the computer. Accordingly, voice signals 30 are never transmitted over the keyboard cable.
Any prior art device that only "mimics" keyboard operation, such as the device disclosed in the Whelpley '665 Patent, is effectively limited in function to keyboard input and to the commands that can be executed by keystroke combinations.
This is a significant drawback because it is impossible for the computer to perform
Field of the Invention This invention relates to input devices for interfacing with electronic devices. More specifically the invention relates to computer keyboards, voice and speech recognition systems, and control systems for electronic apparatus.
1o Background of the Invention It is known in the prior art that voice detection capability can be integrated with a keyboard. For example, U.S. Patent No. 5,659,665 to Whelpley, Jr.
("the Whelpley '665 Patent") discloses an external device inserted at the_data cable 15 between the keyboard and the computer system. The external device adds voice recognition capability to the computer by converting voice signals into keystroke data sent to the computer's keyboard port, while permitting ordinary signals generated at the keyboard itself to pass through the external device as usual to the computer.
The voice recognition system disclosed by the Whelpley '665 Patent is self contained in that the 2o voice input, and the voice recognition hardware is confined to the external device, as is the processing of the voice input signal. The voice commands are never transmitted to the computer except as their keyboard data equivalent, and computer processing,time is not consumed in carrying out the voice recognition function.
The Whelpley '665 Patent also discloses an embodiment wherein the 25 voice recognition device is contained within the keyboard housing. Similar to the external embodiment, the device functions by converting voice signals to keystroke data and inserting the data into the data stream coming from the keyboard. The combination disclosed in the Whelpley '665 Patent effectively disguises the-voice recognition function making it transparent to the computer. Accordingly, voice signals 30 are never transmitted over the keyboard cable.
Any prior art device that only "mimics" keyboard operation, such as the device disclosed in the Whelpley '665 Patent, is effectively limited in function to keyboard input and to the commands that can be executed by keystroke combinations.
This is a significant drawback because it is impossible for the computer to perform
2 operations -on the voice signal itself without a redundant microphone/speaker combination, connected directly to the computer and independent of the voice recognition system.
It is also known that voice-recognition is an evolving technology.
Current implementations may be either "voice-dependent" wherein a system is designed to accurately recognize the voice of specific users, or "voice-independent"
wherein the system is designed to function accurately for any voice. Advances in the field have reduced inaccuracies caused by variations in individual pronunciation, speaking style and accent in the translation of speech to keystrokes. Because any self to contained implementation of voice recognition tends to be limited to the hardware within it, it is likely to be expensive tv upgrade as the technology evolves.
Furthermore, functions such as basic text entry, are significantly complicated by the need to "train" current voice recognition systems to accurately discern the voice of specific users. U.5. Patent No. 5,874,939 to Galvin ("the Galvin '939 Patent") discloses a voice-recognition keyboard with a display to facilitate training. As spoken words are translated to text by the system, the user can check them for accuracy on the display, and in this way improve the accuracy of the system over time. _ .. . . _ _ _.
As in the Whelpley '665 Patent, the voice recognition system disclosed 2o in the Galvin '939 Patent is self contained, and does not transmit voice data to the computer. As a result, the training procedure is necessarily limited to an interface local to the keyboard, that as disclosed can be either sparse or expensive, and certainly is associated with the problem of providing a keyboard display as well as the display on the computer to which it is connected.
Although the self contained approaches disclosed by the Whelpley '665 Patent and the Galvin '939 Patent attempt to improve system efficiency by limiting the processing of speech to an outside processor isolated from the computer system, and may be suitable for older computer systems, they are not flexible enough for practical use with current computer systems and available high bit rate interfaces and do not compliment the use of other voice-related technology.
It is also known that voice-recognition is an evolving technology.
Current implementations may be either "voice-dependent" wherein a system is designed to accurately recognize the voice of specific users, or "voice-independent"
wherein the system is designed to function accurately for any voice. Advances in the field have reduced inaccuracies caused by variations in individual pronunciation, speaking style and accent in the translation of speech to keystrokes. Because any self to contained implementation of voice recognition tends to be limited to the hardware within it, it is likely to be expensive tv upgrade as the technology evolves.
Furthermore, functions such as basic text entry, are significantly complicated by the need to "train" current voice recognition systems to accurately discern the voice of specific users. U.5. Patent No. 5,874,939 to Galvin ("the Galvin '939 Patent") discloses a voice-recognition keyboard with a display to facilitate training. As spoken words are translated to text by the system, the user can check them for accuracy on the display, and in this way improve the accuracy of the system over time. _ .. . . _ _ _.
As in the Whelpley '665 Patent, the voice recognition system disclosed 2o in the Galvin '939 Patent is self contained, and does not transmit voice data to the computer. As a result, the training procedure is necessarily limited to an interface local to the keyboard, that as disclosed can be either sparse or expensive, and certainly is associated with the problem of providing a keyboard display as well as the display on the computer to which it is connected.
Although the self contained approaches disclosed by the Whelpley '665 Patent and the Galvin '939 Patent attempt to improve system efficiency by limiting the processing of speech to an outside processor isolated from the computer system, and may be suitable for older computer systems, they are not flexible enough for practical use with current computer systems and available high bit rate interfaces and do not compliment the use of other voice-related technology.
3 Summary of the Invention A need exists for a low cost apparatus that can simultaneously transmit voice and keyboard signals to a computer over the same interface. There is also a need for a vocal articulation recognition system that can both mimic keyboard signals as well as support other voice-processing functions such as digital telephony, and remote device control. There is a need for these functions in an environment that is not local to the keyboard. There is also a need for a vocal articulation recognition system that can function from within the keyboard or in conjunction with the computer system depending upon the application.
1o The invention is directed to integrating keystroke data from a computer keyboard and another peripheral interface such as a microphone or a telephone handset with voice data to a vocal articulation recognition system for text entry, controlling an electronic apparatus and for access to the Internet.
One embodiment of the present invention is to provide an input device 15 such as ari ordiriaiy' computer keyboard, that is adapted to share its interface controller with a input for voice signals and to permit the signals to be transmitted to a computer system over the same cable that carries keystroke data.
The transmission of both keyboard and voice signals over a single cable to a computer is achieved by using a keyboard interface controller of sufficiently high 2o bit-rate, such as a Universal Serial Bus ("USB") controller, and a voice processor connected to the controller to convert analog voice signals, from a microphone for example, to digital. In this way, the USB keyboard becomes a conduit for voice signals to and from the computer. As such, it can supplement or replace existing peripheral devices such as voice and sound cards currently used in computer systems to handle 25 sound.
The connection of a voice output such as a speaker to the voice processor enables duplex voice transmission compatible with telecommunications applications. Addition of memory to the voice processor extends the capability of the input device to voice messaging, voice print identification and voice recognition.
3o The objects of the invention are accomplished by providing an input device for a computer system, comprising an interface controller for providing communication signals for use in the computer system; and a keystroke input means
1o The invention is directed to integrating keystroke data from a computer keyboard and another peripheral interface such as a microphone or a telephone handset with voice data to a vocal articulation recognition system for text entry, controlling an electronic apparatus and for access to the Internet.
One embodiment of the present invention is to provide an input device 15 such as ari ordiriaiy' computer keyboard, that is adapted to share its interface controller with a input for voice signals and to permit the signals to be transmitted to a computer system over the same cable that carries keystroke data.
The transmission of both keyboard and voice signals over a single cable to a computer is achieved by using a keyboard interface controller of sufficiently high 2o bit-rate, such as a Universal Serial Bus ("USB") controller, and a voice processor connected to the controller to convert analog voice signals, from a microphone for example, to digital. In this way, the USB keyboard becomes a conduit for voice signals to and from the computer. As such, it can supplement or replace existing peripheral devices such as voice and sound cards currently used in computer systems to handle 25 sound.
The connection of a voice output such as a speaker to the voice processor enables duplex voice transmission compatible with telecommunications applications. Addition of memory to the voice processor extends the capability of the input device to voice messaging, voice print identification and voice recognition.
3o The objects of the invention are accomplished by providing an input device for a computer system, comprising an interface controller for providing communication signals for use in the computer system; and a keystroke input means
4 connected .to the interface controller; and a voice input means connected to the interface controller, the keystroke input means and the voice input means sharing the interface controller to transmit keyboard and voice data to the computer.
A further embodiment of the present invention is a voice recognition system wherein a computer, using a single input device to receive voice and keyboard information, processes the voice input using voice recognition technology, for output as text, or by executing corresponding operational instructions. As above, the input device may be a keyboard such as a USB keyboard and a voice processor may be interposed within it to accommodate analog voice input. Memory may be added to the to input device, or to the computer to facilitate voice print identification.
Encryption of the signal between the input device and the computer can be employed to prevent snooping the interface. Voice recognition can also be accomplished by the input device inparallel with the computer, either to distribute computational lead across the system, or to enhance the accuracy of the voice recognition function.
~ ... ~ .Further providedherein is a voice recognition system comprising: a computer system having a voice recognition means coupled to an input processing means and an output means; and an input device for transmitting voice and keystroke signals having a keystroke input means and a voice input means, coupled to and sharing - --at least one interface controller connected to the input processing means of the 2o computer; wherein the voice recognition means processes the voice signals and generates output to the output means.
In a further embodiment, voice recognition is incorporated into a keyboard having a signaling means capable of transmitting data to a computer as well as input to one or more external devices. A typical treatment according to this embodiment would employ a USB technique for interface with the computer, and either infrared (IR), as might be used to control televisions, or radio frequency (RF) transmission in an application like a cordless phone. The necessary components for carrying out speech recognition are included in the keyboard to convert speech to text transmission to the computer via the keyboard interface and also to provide voice 3o operated remote control for any compatible electronic devices.
Also provided is a voice recognition keyboard for a computer system for generating keystroke input and operating instructions for controlling at least one electronic device comprising: a signaling means for transmitting signals capable of being of two types, a first type suitable for transmission to the computer system and a second type suitable for transmission to at least one electronic device; and a plurality of keys connected to the signaling means for providing keystroke input to the signaling means for transmission therethrough; and a voice input means; and a voice recognition means connected to the voice input means to convert spoken words into operating instructions for transmission through the signal means.
At least one voice input device is needed to provide voice input to the keyboard as well as voice processing circuitry to handle signal processing and voice l0 recognition. As in the previous embodiments, adding memory, encryption circuitry and a voice output means to the keyboard, enables voice-print comparison and two way voice communication suited to secure digital telephony and voice data entry.
- - -. ---. --.~ mother embodiment, .an input device such as a~eyboard is provided that when connected to a computer configured for Internet access, will initiate access to - -the intertlet upon receiving specific spoken cormmands: w- -w - - . -~ ww --There is provided a voice recognition input device for providing voice access to the Internet from a computer configured to be connected to the Internet, comprising: a voice-input-means; and-a voice-r-ecognition--means for identifying spoken commands, at least one of the commands defined to initiate Internet access;
arid a signal 2o means for triggering the execution of the command.
The invention further contemplates methods of providing keystroke and voice input to a computer system over a single interface, converting spoken words into text, providing access to the Internet from a computer connected to the Internet, and remotely controlling at least one electronic device with a spoken command.
The above, and other features, aspects, and advantages of the present invention will become apparent from the following description read in conjunction with the accompanying drawings, in which like reference numerals designate the same elements.
Brief Description of the Drawings The invention is illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references denote like or corresponding parts, and in which:
FIG. 1 is a block diagram depiction of an input device in accordance with the invention;
FIG. 2 is a block diagram of an embodiment of the integrated speech 1o input device according to the present invention in a USB keyboard;
FIG. 3 is a block diagram of an embodiment of the input device in accordance with.the invention connected to. a_computeraystem having .voice recognition means;
FIG. 4 is a block diagram of an embodiment of the input device in accordance with the invention connected to a computer system further connected to outside services; _ _ ~ _ . _ _ _ _ _ _ _ _ , _ . ___ . _ _ . _ _. _.. _ 2o FIG. 5 is a block diagram of an embodiment of the present invention wherein the integrated input device is a voice recognition keyboard with remote control capability; and I
FIG. 6 is a block diagram of an embodiment of the present invention connected to a computer with access to the Internet.
Description of the Preferred Embodiments Referring now to FIG. 1, there is shown an electrical block diagram of a preferred embodiment of the speech input device according to the present invention 3o generally designated by the numeral 10. A case 11 for the speech input device 10 is indicated diagrammatically. A computer system is represented generally by the numeral 20. The computer 20 has an input processor 21 connected for bi-directional communication to interface controller 12 of speech input device 10. Interface controller 12 is connected to receive signals from keystroke input 13 and voice input 17.
A voice processor 14 is connected between voice input 17 and interface controller 12. A bi-directional connection exists between voice processor 14 and interface controller 12. The interface controller 12 and the voice processor 14 may be combined into a single chip. The functionality would be the same. Voice output and memory 16 are connected to voice processor 14. It is understood that although voice input 17 and voice output 18 are shown in FIG. 1 within case 11, they may exist l0 outside the case without affecting the function or spirit of the present invention.
In operation, signals received from voice input 17 are digitized by voice processor 14 and the voice data is sent to interface controller 12. Interface controller 12 combines the voice-data,with.keystroke data received from keystroke input 13, and transmits them as a single data signal to input processor 21 of computer system 20. In 15 wthe present device incorporating ZJSB~ the keyboard and microphone use two differ-ent USB endpoints as a compound USB device, so the keyboard data and the voice data would not necessarily be simultaneous. The voice data may be either isochronous or non-isochronous..lf the=dataas :isochronous, it-wilLhave priority on the USB
bus over all other types of data. The audio data may also be non-isochronous and emulate 2o another USB device. Regardless of what interface method is used, the voice data and keystroke data may be transmitted simultaneously or one or the other rnay be transmitted at a time. The voice data and keystroke data are transmitted over a single cable to the computer system.
Similarly, signals containing voice data received by interface controller 2s 12 from computer 20 are sent to the voice processor for conversion to analog signals suitable for voice output 18. In the simplest case, the voice processor functions_as an analog-to-digital (ADC) converter for input and as a digital-to-analog converter for output of voice data.
Signals received from the voice input 17 may be processed for any type 30 of vocal articulation recognition such as speech recognition which translates human speech into text and voice recognition which processes human speech into commands or performs verification.
Memory 16 may contain a voice print sample or voice recognition data enabling voice processor 14 to perform voice-print comparison of voice signals incoming from voice input 17 or to perform voice recognition functions thereon.
FIG. 2 is an electrical block diagram of the present invention similar to FIG. 1 wherein speech input device 10 is based on a USB keyboard. The standard components of a USB keyboard are arranged in a typical fashion, including the interface controller 12, connected to keystroke input 13 and to signal LEDs 15, and having a USB output 19.
Several classes of USB devices exist. A USB keyboard itself is in the to Human Interface Device (HID) class. Other classes include Audio Device, Communications Device, Display Device and Mass Storage Device classes. The Audio Device class has defined a device descriptor for a USB microphone. Using the USB
Audio Device class descriptor is a standard way to support a USB~nicrophone, and requires a full-speed 12 megabit per second USB interface chip that supports 15 isochronous transfers. Such a chip is more expensive than a low-speed chip, but it would ensure compatibility with a wider range of USB system drivers for microphones.
However, because the present invention contemplates both isochronous and non-isochronous data transmission, any interface can be substituted for these USB
device classes without changing its basic functionality.
20 The present invention adds to the USB keyboard a voice processor 14 connected to interface controller 12, and to voice input 17 and voice output represented as a microphone and a speaker, respectively. The voice inputs 17 may be an on-board microphone (i.e. integral with the keyboard) or a microphone plugged into a jack connector. Memory 16 is also connected to voice processor 14.
25 Operation of speech input device 10 is similar to that described in FIG.
1, with the interface controller 12 combining data received from the keystroke input 13 with voice data received from voice input 17 and digitized by voice processor 14. The digital signals enter the interface controller 12 which acts as a USB
processor which packetizes the signals. The resulting signal is transmitted over USB cable 19 as voice 3o packets according to a standard USB technique compatible with any computer system having a similar USB interface. One possible format for the packets is the USB
Microphone Audio Data Format of 16 bits 8Khz PCM; however, there are many other possible audio formats. Incoming voice signals through USB cable 19 are routed by interface controller 12 to voice processor 14 for output through voice output 18. Voice processor 14 and interface controller I2 may be combined into a single chip without affecting functionality. LEDs 15 are typically used for keyboard indicator lights such as Num Lock or Caps Lock, but may be used to indicate functioning of other aspects of voice input device 10 as well.
In this configuration, voice input device 10 functions exactly as a standard USB keyboard, and also as a two-way conduit for voice signals without adding additional interfaces to a USB compliant computer. Furthermore, voice input 17 and voice output 18 could be combined into a receiver unit for use as a telephone handset. The addition of memory 16 to voice processor 14 further enables the system to check the identity of a user or to limit access to voice input device 10 to specific authorized users by comparing an incomingaignal to signals stor~d in.memory l6. It is also possible in this configuration to add any vocal articulation recognition 'functionality to voice processor-14; while-retaining~the~elegance of a single input device.
Referring now to FIG. 3, a block diagram is shown of a preferred _embodiment-of a vocal ar-ti-culati-an-r-ecognition system.-emp-loyin~input_device.l0 in which computer system 20 has an input processor 21 connected to a vocal subsystem 2o means 22 which is connected to an output means 23. Input device 10 has the same basic components as in FIG. 1 and operates similarly to provide computer system 20 with keystroke and voice data over a singe interface to input processor 21.
The voice data is isolated by the input processor 21 for transmission to the vocal subsystem means 22. According to this embodiment, the vocal subsystem means may comprise the native processing means of the computer system executing software in the form of a set of instructions, or it may consist of specialized hardware or a combination of both.
The output means 23 may provide direct output of the vocal subsystem means 22, such as spoken words converted to text displayed on a monitor, or it may be more indirect as in voice dictation to a word processor and output to a printer. As in 3o the previous embodiments, interface controller 12 of input device 10 may be adapted to generate signals in accordance with a USB technique. Similarly voice processor may be connected between voice input 17 and interface controller 12 to provide analog to digital conversion. A voice output 1 ~ may be provided, in which case the voice processor 14 converts digital voice signals received via the interface controller 12 to analog signals suitable for output to a speaker.
As in the previous embodiment, the function of the voice processor 14 need not be limited to signal mode conversion. The addition of memory 16 permits voice processing locally to input device 10 such as voice print comparison and speech recognition. Voice print comparison can be used to compare incoming voice signals with voice prints recorded in memory 16. Local vocal articulation recognition through voice processor 14 can be used in conjunction with the vocal subsystem means 22 in 1o which case the input device 10 functions as a coprocessor to computer system 20.
The user interface displayed on output means 23 can be Windows-based, and may be driven by pull-down menus in which voice commands are shown.
Accordingly, the-user does.not need_to memorize commands recog3~ized by the system.
This approach can make the vocal articulation recognition system more user-friendly.
Of-course, any displayinterface~may be used or an interface may be customized to perform specific functions without altering the functionality of the present invention.
FIG. 4 depicts a modified embodiment of the vocal articulation recognition. system-of-F-IG -3 wherein_input -device-.10,_having a case 1.1 represented diagrammatically, has interface controller 12 connected to receive keystroke data from keystroke input 13 and connected to send and receive voice input from said voice processor. The interface controller 12 packetizes digital voice signals to send them over a cable to the computer system 20. Voice input 17 and voice output 1 ~
respectively send and receive analog voice data from the voice processor 14 through interface controller 12 over the same cable to computer system 20. As in the previous embodiments, memory 16 is used by voice processor 14 to store data for voice print comparison and voice recognition.
In the current embodiment, signal encryption means 19 has been added to input device 10 to encrypt/decode the data transmitted between input device 10 and computer system 20. Similarly, encryption means 25 has been added to computer 3o system 20 for the same reason. The encryption means 19 and 25 may be any known type of encryption circuit or processor under software control. The encryption means 19 may be integrated with interface controller 12 thereby both packetizing and encrypting the data using interface controller 12.
In computer system 20, the input processor receives voice and keyboard data from input device 10 and hands off the voice signal to voice recognition means 22.
Memory 24 is shown connected to vocal subsystem means 22 serving as a storage circuit therefor. Output means 23 may be a display means of computer system 20 used to display output of vocal subsystem means 22. I/O controller 26 is shown in this embodiment as a gateway interface between computer system 20 and data sources outside computer system 20 such as Internet connections, telephone service and 1o peripherals.
In this configuration, voice input 17 and voice output 18 could be combined into a receiver unit for use in online telephony. In this regard, voice over Internet provider (VOID) is enabled. Furthermore, the functions yip controller 26 may be accomplished by using a interface card such as a Local Area Network (LAIC
card.
-- 'In this~embodiment; the~vocal articulatiomrecognition system functions to provide a secure means for communication of voice and keystroke signals from input device 10 to computer system 20. Any attempts to snoop the interface between in er~ac~cantroller_1,2_and_inpu~prr-ocessor-21-is_subj-ect-to~he-oper-atioxn of encryption means 19, 25.
Referring now to FIG. S, a block diagram is shown of an embodiment of the present invention in which the input device is a voice recognition keyboard 10. The case of voice recognition keyboard 10 is represented diagrammatically 11, having within interface controller 12 which receives data from keystroke input 13 and voice _e processor 14. Voice processor 14 receives voice signals from voice input 17 and is connected to memory 16.
Voice processor 14 receives incoming speech as voice signals from voice input 17, converts spoken words into commands suitable for transmission to computer system 20 or electronic device 30 through interface controller 12.
Interface controller 12 combines data from keystroke input 13 and voice processor 14 and transmits them selectively to computer system 20 and electronic device 30.
According to this embodiment, voice recognition keyboard 10 can be used as an ordinary keyboard, having an interface such as LTSB for providing keystroke input to the computer system 20. In addition, however, input from the keystroke input may be control data and further may also be directed to an electronic device such-as a DVD or CD player, stereo, VCR, set box or a television, interface controller 12 being equipped with an interface such as radio frequency (RF) or infra red (IR), or a USB
cable as may be compatible with the device 30 being controlled.
Additionally, spoken commands received through voice input 17 are processed into their keystroke equivalents and sent to interface controller 12. The interface controller handles the translated input from voice processor 14 just as it would data from keystroke input 13, transmitting it via a computer interface such as a USB
1o interface or an RF or IR link to the computer system 20 or to an electronic device 30 through any other appropriate interface as needed. Accordingly, spoken commands can remotely control any type of multimedia electronic device such as a DVD or CD
player, stereo, VCR, set box or a television.
The set of possible keyboard commands and inputs is a subset of all the 15 possible voice commands and inputs. A keyboard always has an established limited number of keys and key combinations, whereas voice commands and input are not physically limited. There can be thousands of voice commands whereas keyboard input is generally -limited to a few hundred codas.
A key feature of the invention is that voice packets are sent over the 2o USB cable, as opposed to translating the voice commands into keyboard codes and then sending keyboard codes over the cable. The voice command set is not limited to the keyboard codes, as it was in the past. The number of voice commands supported is only limited by the system memory and the number of commands that have been pre-recorded. The number of voice commands can grow without limit, since the number of 25 pre-recorded voice commands can be updated by downloading new code via the Internet. A distinct set of voice commands can be auto-downloaded when the user accesses web site voice commands that are supported by that particular web site.
FIG. 6 shows an alternate embodiment of the present invention directed toward providing voice access to the Internet. In this embodiment, input device 10 has 3o interface controller 12 connected to voice processor 14 connected to memory 16 and voice input 17 within a case 11 represented diagrammatically. In this embodiment, spoken commands are converted into corresponding data by voice processor 14 and sent to the computer system 20 via an interface. Computer system 20 is configured for connection to the Internet. Thus, Internet access may be voice actuated. The input device 10 may be a keyboard with voice initiation of Internet access replacing or supplementing hot keys on the keyboard. This embodiment permits voice commands to be converted to commands recognized by computer system 20 for use in navigating the Internet. A world wide network of computers is accessible with this embodiment of the invention.
The invention further contemplates a method using a single interface for voice and keystroke data. A computer splits the combined signal into a digital voice to signal component and a keystroke signal component for separate processing.
Voice print comparison may be made. The invention includes the method of initiating Internet access by voice commands. Such voice commands may be input to a keyboard. A method is also contemplated for remotely controllir~-an electronic device from a keyboard with spoken commands.
15 Although the invention has been described with reference to the preferred embodiments, it will be apparent to one skilled in the art that variations and modifications are contemplated within the spirit and scope of the invention.
The drawings and description of the preferred embodiments are made by way of example-rather than to limit the scope of the invention, and it is intended to cover within the 2o spirit and scope of the invention all such changes and modifications.
A further embodiment of the present invention is a voice recognition system wherein a computer, using a single input device to receive voice and keyboard information, processes the voice input using voice recognition technology, for output as text, or by executing corresponding operational instructions. As above, the input device may be a keyboard such as a USB keyboard and a voice processor may be interposed within it to accommodate analog voice input. Memory may be added to the to input device, or to the computer to facilitate voice print identification.
Encryption of the signal between the input device and the computer can be employed to prevent snooping the interface. Voice recognition can also be accomplished by the input device inparallel with the computer, either to distribute computational lead across the system, or to enhance the accuracy of the voice recognition function.
~ ... ~ .Further providedherein is a voice recognition system comprising: a computer system having a voice recognition means coupled to an input processing means and an output means; and an input device for transmitting voice and keystroke signals having a keystroke input means and a voice input means, coupled to and sharing - --at least one interface controller connected to the input processing means of the 2o computer; wherein the voice recognition means processes the voice signals and generates output to the output means.
In a further embodiment, voice recognition is incorporated into a keyboard having a signaling means capable of transmitting data to a computer as well as input to one or more external devices. A typical treatment according to this embodiment would employ a USB technique for interface with the computer, and either infrared (IR), as might be used to control televisions, or radio frequency (RF) transmission in an application like a cordless phone. The necessary components for carrying out speech recognition are included in the keyboard to convert speech to text transmission to the computer via the keyboard interface and also to provide voice 3o operated remote control for any compatible electronic devices.
Also provided is a voice recognition keyboard for a computer system for generating keystroke input and operating instructions for controlling at least one electronic device comprising: a signaling means for transmitting signals capable of being of two types, a first type suitable for transmission to the computer system and a second type suitable for transmission to at least one electronic device; and a plurality of keys connected to the signaling means for providing keystroke input to the signaling means for transmission therethrough; and a voice input means; and a voice recognition means connected to the voice input means to convert spoken words into operating instructions for transmission through the signal means.
At least one voice input device is needed to provide voice input to the keyboard as well as voice processing circuitry to handle signal processing and voice l0 recognition. As in the previous embodiments, adding memory, encryption circuitry and a voice output means to the keyboard, enables voice-print comparison and two way voice communication suited to secure digital telephony and voice data entry.
- - -. ---. --.~ mother embodiment, .an input device such as a~eyboard is provided that when connected to a computer configured for Internet access, will initiate access to - -the intertlet upon receiving specific spoken cormmands: w- -w - - . -~ ww --There is provided a voice recognition input device for providing voice access to the Internet from a computer configured to be connected to the Internet, comprising: a voice-input-means; and-a voice-r-ecognition--means for identifying spoken commands, at least one of the commands defined to initiate Internet access;
arid a signal 2o means for triggering the execution of the command.
The invention further contemplates methods of providing keystroke and voice input to a computer system over a single interface, converting spoken words into text, providing access to the Internet from a computer connected to the Internet, and remotely controlling at least one electronic device with a spoken command.
The above, and other features, aspects, and advantages of the present invention will become apparent from the following description read in conjunction with the accompanying drawings, in which like reference numerals designate the same elements.
Brief Description of the Drawings The invention is illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references denote like or corresponding parts, and in which:
FIG. 1 is a block diagram depiction of an input device in accordance with the invention;
FIG. 2 is a block diagram of an embodiment of the integrated speech 1o input device according to the present invention in a USB keyboard;
FIG. 3 is a block diagram of an embodiment of the input device in accordance with.the invention connected to. a_computeraystem having .voice recognition means;
FIG. 4 is a block diagram of an embodiment of the input device in accordance with the invention connected to a computer system further connected to outside services; _ _ ~ _ . _ _ _ _ _ _ _ _ , _ . ___ . _ _ . _ _. _.. _ 2o FIG. 5 is a block diagram of an embodiment of the present invention wherein the integrated input device is a voice recognition keyboard with remote control capability; and I
FIG. 6 is a block diagram of an embodiment of the present invention connected to a computer with access to the Internet.
Description of the Preferred Embodiments Referring now to FIG. 1, there is shown an electrical block diagram of a preferred embodiment of the speech input device according to the present invention 3o generally designated by the numeral 10. A case 11 for the speech input device 10 is indicated diagrammatically. A computer system is represented generally by the numeral 20. The computer 20 has an input processor 21 connected for bi-directional communication to interface controller 12 of speech input device 10. Interface controller 12 is connected to receive signals from keystroke input 13 and voice input 17.
A voice processor 14 is connected between voice input 17 and interface controller 12. A bi-directional connection exists between voice processor 14 and interface controller 12. The interface controller 12 and the voice processor 14 may be combined into a single chip. The functionality would be the same. Voice output and memory 16 are connected to voice processor 14. It is understood that although voice input 17 and voice output 18 are shown in FIG. 1 within case 11, they may exist l0 outside the case without affecting the function or spirit of the present invention.
In operation, signals received from voice input 17 are digitized by voice processor 14 and the voice data is sent to interface controller 12. Interface controller 12 combines the voice-data,with.keystroke data received from keystroke input 13, and transmits them as a single data signal to input processor 21 of computer system 20. In 15 wthe present device incorporating ZJSB~ the keyboard and microphone use two differ-ent USB endpoints as a compound USB device, so the keyboard data and the voice data would not necessarily be simultaneous. The voice data may be either isochronous or non-isochronous..lf the=dataas :isochronous, it-wilLhave priority on the USB
bus over all other types of data. The audio data may also be non-isochronous and emulate 2o another USB device. Regardless of what interface method is used, the voice data and keystroke data may be transmitted simultaneously or one or the other rnay be transmitted at a time. The voice data and keystroke data are transmitted over a single cable to the computer system.
Similarly, signals containing voice data received by interface controller 2s 12 from computer 20 are sent to the voice processor for conversion to analog signals suitable for voice output 18. In the simplest case, the voice processor functions_as an analog-to-digital (ADC) converter for input and as a digital-to-analog converter for output of voice data.
Signals received from the voice input 17 may be processed for any type 30 of vocal articulation recognition such as speech recognition which translates human speech into text and voice recognition which processes human speech into commands or performs verification.
Memory 16 may contain a voice print sample or voice recognition data enabling voice processor 14 to perform voice-print comparison of voice signals incoming from voice input 17 or to perform voice recognition functions thereon.
FIG. 2 is an electrical block diagram of the present invention similar to FIG. 1 wherein speech input device 10 is based on a USB keyboard. The standard components of a USB keyboard are arranged in a typical fashion, including the interface controller 12, connected to keystroke input 13 and to signal LEDs 15, and having a USB output 19.
Several classes of USB devices exist. A USB keyboard itself is in the to Human Interface Device (HID) class. Other classes include Audio Device, Communications Device, Display Device and Mass Storage Device classes. The Audio Device class has defined a device descriptor for a USB microphone. Using the USB
Audio Device class descriptor is a standard way to support a USB~nicrophone, and requires a full-speed 12 megabit per second USB interface chip that supports 15 isochronous transfers. Such a chip is more expensive than a low-speed chip, but it would ensure compatibility with a wider range of USB system drivers for microphones.
However, because the present invention contemplates both isochronous and non-isochronous data transmission, any interface can be substituted for these USB
device classes without changing its basic functionality.
20 The present invention adds to the USB keyboard a voice processor 14 connected to interface controller 12, and to voice input 17 and voice output represented as a microphone and a speaker, respectively. The voice inputs 17 may be an on-board microphone (i.e. integral with the keyboard) or a microphone plugged into a jack connector. Memory 16 is also connected to voice processor 14.
25 Operation of speech input device 10 is similar to that described in FIG.
1, with the interface controller 12 combining data received from the keystroke input 13 with voice data received from voice input 17 and digitized by voice processor 14. The digital signals enter the interface controller 12 which acts as a USB
processor which packetizes the signals. The resulting signal is transmitted over USB cable 19 as voice 3o packets according to a standard USB technique compatible with any computer system having a similar USB interface. One possible format for the packets is the USB
Microphone Audio Data Format of 16 bits 8Khz PCM; however, there are many other possible audio formats. Incoming voice signals through USB cable 19 are routed by interface controller 12 to voice processor 14 for output through voice output 18. Voice processor 14 and interface controller I2 may be combined into a single chip without affecting functionality. LEDs 15 are typically used for keyboard indicator lights such as Num Lock or Caps Lock, but may be used to indicate functioning of other aspects of voice input device 10 as well.
In this configuration, voice input device 10 functions exactly as a standard USB keyboard, and also as a two-way conduit for voice signals without adding additional interfaces to a USB compliant computer. Furthermore, voice input 17 and voice output 18 could be combined into a receiver unit for use as a telephone handset. The addition of memory 16 to voice processor 14 further enables the system to check the identity of a user or to limit access to voice input device 10 to specific authorized users by comparing an incomingaignal to signals stor~d in.memory l6. It is also possible in this configuration to add any vocal articulation recognition 'functionality to voice processor-14; while-retaining~the~elegance of a single input device.
Referring now to FIG. 3, a block diagram is shown of a preferred _embodiment-of a vocal ar-ti-culati-an-r-ecognition system.-emp-loyin~input_device.l0 in which computer system 20 has an input processor 21 connected to a vocal subsystem 2o means 22 which is connected to an output means 23. Input device 10 has the same basic components as in FIG. 1 and operates similarly to provide computer system 20 with keystroke and voice data over a singe interface to input processor 21.
The voice data is isolated by the input processor 21 for transmission to the vocal subsystem means 22. According to this embodiment, the vocal subsystem means may comprise the native processing means of the computer system executing software in the form of a set of instructions, or it may consist of specialized hardware or a combination of both.
The output means 23 may provide direct output of the vocal subsystem means 22, such as spoken words converted to text displayed on a monitor, or it may be more indirect as in voice dictation to a word processor and output to a printer. As in 3o the previous embodiments, interface controller 12 of input device 10 may be adapted to generate signals in accordance with a USB technique. Similarly voice processor may be connected between voice input 17 and interface controller 12 to provide analog to digital conversion. A voice output 1 ~ may be provided, in which case the voice processor 14 converts digital voice signals received via the interface controller 12 to analog signals suitable for output to a speaker.
As in the previous embodiment, the function of the voice processor 14 need not be limited to signal mode conversion. The addition of memory 16 permits voice processing locally to input device 10 such as voice print comparison and speech recognition. Voice print comparison can be used to compare incoming voice signals with voice prints recorded in memory 16. Local vocal articulation recognition through voice processor 14 can be used in conjunction with the vocal subsystem means 22 in 1o which case the input device 10 functions as a coprocessor to computer system 20.
The user interface displayed on output means 23 can be Windows-based, and may be driven by pull-down menus in which voice commands are shown.
Accordingly, the-user does.not need_to memorize commands recog3~ized by the system.
This approach can make the vocal articulation recognition system more user-friendly.
Of-course, any displayinterface~may be used or an interface may be customized to perform specific functions without altering the functionality of the present invention.
FIG. 4 depicts a modified embodiment of the vocal articulation recognition. system-of-F-IG -3 wherein_input -device-.10,_having a case 1.1 represented diagrammatically, has interface controller 12 connected to receive keystroke data from keystroke input 13 and connected to send and receive voice input from said voice processor. The interface controller 12 packetizes digital voice signals to send them over a cable to the computer system 20. Voice input 17 and voice output 1 ~
respectively send and receive analog voice data from the voice processor 14 through interface controller 12 over the same cable to computer system 20. As in the previous embodiments, memory 16 is used by voice processor 14 to store data for voice print comparison and voice recognition.
In the current embodiment, signal encryption means 19 has been added to input device 10 to encrypt/decode the data transmitted between input device 10 and computer system 20. Similarly, encryption means 25 has been added to computer 3o system 20 for the same reason. The encryption means 19 and 25 may be any known type of encryption circuit or processor under software control. The encryption means 19 may be integrated with interface controller 12 thereby both packetizing and encrypting the data using interface controller 12.
In computer system 20, the input processor receives voice and keyboard data from input device 10 and hands off the voice signal to voice recognition means 22.
Memory 24 is shown connected to vocal subsystem means 22 serving as a storage circuit therefor. Output means 23 may be a display means of computer system 20 used to display output of vocal subsystem means 22. I/O controller 26 is shown in this embodiment as a gateway interface between computer system 20 and data sources outside computer system 20 such as Internet connections, telephone service and 1o peripherals.
In this configuration, voice input 17 and voice output 18 could be combined into a receiver unit for use in online telephony. In this regard, voice over Internet provider (VOID) is enabled. Furthermore, the functions yip controller 26 may be accomplished by using a interface card such as a Local Area Network (LAIC
card.
-- 'In this~embodiment; the~vocal articulatiomrecognition system functions to provide a secure means for communication of voice and keystroke signals from input device 10 to computer system 20. Any attempts to snoop the interface between in er~ac~cantroller_1,2_and_inpu~prr-ocessor-21-is_subj-ect-to~he-oper-atioxn of encryption means 19, 25.
Referring now to FIG. S, a block diagram is shown of an embodiment of the present invention in which the input device is a voice recognition keyboard 10. The case of voice recognition keyboard 10 is represented diagrammatically 11, having within interface controller 12 which receives data from keystroke input 13 and voice _e processor 14. Voice processor 14 receives voice signals from voice input 17 and is connected to memory 16.
Voice processor 14 receives incoming speech as voice signals from voice input 17, converts spoken words into commands suitable for transmission to computer system 20 or electronic device 30 through interface controller 12.
Interface controller 12 combines data from keystroke input 13 and voice processor 14 and transmits them selectively to computer system 20 and electronic device 30.
According to this embodiment, voice recognition keyboard 10 can be used as an ordinary keyboard, having an interface such as LTSB for providing keystroke input to the computer system 20. In addition, however, input from the keystroke input may be control data and further may also be directed to an electronic device such-as a DVD or CD player, stereo, VCR, set box or a television, interface controller 12 being equipped with an interface such as radio frequency (RF) or infra red (IR), or a USB
cable as may be compatible with the device 30 being controlled.
Additionally, spoken commands received through voice input 17 are processed into their keystroke equivalents and sent to interface controller 12. The interface controller handles the translated input from voice processor 14 just as it would data from keystroke input 13, transmitting it via a computer interface such as a USB
1o interface or an RF or IR link to the computer system 20 or to an electronic device 30 through any other appropriate interface as needed. Accordingly, spoken commands can remotely control any type of multimedia electronic device such as a DVD or CD
player, stereo, VCR, set box or a television.
The set of possible keyboard commands and inputs is a subset of all the 15 possible voice commands and inputs. A keyboard always has an established limited number of keys and key combinations, whereas voice commands and input are not physically limited. There can be thousands of voice commands whereas keyboard input is generally -limited to a few hundred codas.
A key feature of the invention is that voice packets are sent over the 2o USB cable, as opposed to translating the voice commands into keyboard codes and then sending keyboard codes over the cable. The voice command set is not limited to the keyboard codes, as it was in the past. The number of voice commands supported is only limited by the system memory and the number of commands that have been pre-recorded. The number of voice commands can grow without limit, since the number of 25 pre-recorded voice commands can be updated by downloading new code via the Internet. A distinct set of voice commands can be auto-downloaded when the user accesses web site voice commands that are supported by that particular web site.
FIG. 6 shows an alternate embodiment of the present invention directed toward providing voice access to the Internet. In this embodiment, input device 10 has 3o interface controller 12 connected to voice processor 14 connected to memory 16 and voice input 17 within a case 11 represented diagrammatically. In this embodiment, spoken commands are converted into corresponding data by voice processor 14 and sent to the computer system 20 via an interface. Computer system 20 is configured for connection to the Internet. Thus, Internet access may be voice actuated. The input device 10 may be a keyboard with voice initiation of Internet access replacing or supplementing hot keys on the keyboard. This embodiment permits voice commands to be converted to commands recognized by computer system 20 for use in navigating the Internet. A world wide network of computers is accessible with this embodiment of the invention.
The invention further contemplates a method using a single interface for voice and keystroke data. A computer splits the combined signal into a digital voice to signal component and a keystroke signal component for separate processing.
Voice print comparison may be made. The invention includes the method of initiating Internet access by voice commands. Such voice commands may be input to a keyboard. A method is also contemplated for remotely controllir~-an electronic device from a keyboard with spoken commands.
15 Although the invention has been described with reference to the preferred embodiments, it will be apparent to one skilled in the art that variations and modifications are contemplated within the spirit and scope of the invention.
The drawings and description of the preferred embodiments are made by way of example-rather than to limit the scope of the invention, and it is intended to cover within the 2o spirit and scope of the invention all such changes and modifications.
Claims (40)
1. An input device for a computer system, comprising:
an interface controller for providing communication signals for use in said computer system; and a keystroke input means connected to said interface controller; and a voice input means connected to said interface controller, said keystroke input means and said voice input means sharing the interface controller to transmit keyboard and voice data to the computer.
an interface controller for providing communication signals for use in said computer system; and a keystroke input means connected to said interface controller; and a voice input means connected to said interface controller, said keystroke input means and said voice input means sharing the interface controller to transmit keyboard and voice data to the computer.
2. The input device according to claim 1, further comprising a voice output means coupled to said interface controller and sharing the controller with the voice input means and the keyboard.
3. The input device according to. claim 1, wherein said interface controller provides signals for use in said computer system in accordance with a Universal Serial Bus technique.
4. The input device according to claim 1, further comprising a voice processor disposed between said voice input means and said interface controller to digitize an analog input to the interface controller from the voice input.
5. The input device according to claim 4 wherein said voice processor also translates spoken words into keystroke data.
6. The input device according to claim 5 further comprising a memory means connected to said voice processor.
7. The input device according to claim 6 wherein said memory means contains the voice print of at least one authorized user for comparison to voice data from said voice input means.
8. The input device according to claim 2 wherein said input and output means are combined into a single receiver unit suitable for use in telephony.
9. A vocal articulation recognition system comprising:
a computer system having a vocal articulation recognition means coupled to an input processing means and an output means; and an input device for transmitting voice and keystroke signals having a keystroke input means and a voice input means, coupled to and sharing at least one interface controller connected to the input processing means of said computer;
wherein the vocal articulation recognition means processes said voice signals and generates output to the output means.
a computer system having a vocal articulation recognition means coupled to an input processing means and an output means; and an input device for transmitting voice and keystroke signals having a keystroke input means and a voice input means, coupled to and sharing at least one interface controller connected to the input processing means of said computer;
wherein the vocal articulation recognition means processes said voice signals and generates output to the output means.
10. The vocal articulation recognition system according to claim 9 wherein said interface controller and said input processing means communicate using signals generated in accordance with a Universal Serial Bus technique.
11. The vocal articulation recognition system according to claim 10 further comprising a voice processor disposed between said voice input means and said interface controller to digitize analog signals from the voice input means to said interface controller.
12. The vocal articulation recognition system according to claim 11 further comprising a memory means connected to said voice processor;
wherein said memory means contains the voice print of at least one authorized user for comparison to voice data from said input means.
wherein said memory means contains the voice print of at least one authorized user for comparison to voice data from said input means.
13. The vocal articulation recognition system of claim 9 further comprising a memory means connected to said vocal articulation recognition means;
wherein said memory means contains the voice print of at least one authorized user for comparison to voice data from said input means.
wherein said memory means contains the voice print of at least one authorized user for comparison to voice data from said input means.
14. The vocal articulation recognition system of claim 9 further comprising a first encryption means connected to said interface controller and a second encryption means connected to said input processor to provide encrypted transmission of said voice and keystroke signals.
15. The vocal articulation recognition system of claim 9 further comprising a voice processor for performing voice recognition.
16. A voice recognition keyboard for a computer system for generating keystroke input and operating instructions for controlling at least one electronic device comprising:
a signaling means for transmitting signals capable of being of two types, a first type suitable for transmission to said computer system and a second type suitable for transmission to at least one electronic device; and a plurality of keys connected to said signaling means for providing keystroke input to said signaling means for transmission therethrough; and a voice input means; and a voice recognition means connected to said voice input means to convert spoken words into operating instructions for transmission through the signal means.
a signaling means for transmitting signals capable of being of two types, a first type suitable for transmission to said computer system and a second type suitable for transmission to at least one electronic device; and a plurality of keys connected to said signaling means for providing keystroke input to said signaling means for transmission therethrough; and a voice input means; and a voice recognition means connected to said voice input means to convert spoken words into operating instructions for transmission through the signal means.
17. The voice recognition keyboard according to claim 16 wherein said signals of said type suitable for transmission to at least one electronic device are transmitted using an infrared signal.
18. The voice recognition keyboard according to claim 16 wherein said signals of said type suitable for transmission to at least one electronic device are transmitted using a radio-frequency (RF) signal.
19. The voice recognition keyboard according to claim 16 wherein said signals of said type suitable for transmission to said computer are in accordance with a Universal Serial Bus (USB) technique.
20. The voice recognition keyboard according to claim 16 further comprising a memory means connected to said voice recognition means.
21. The voice recognition keyboard according to claim 20 wherein said memory means contains a voice print of at least one authorized user for comparison to vice data from said voice input means.
22. The voice recognition keyboard according to claim 16 further comprising a voice output means connected to said signal means to receive voice signals transmitted to said signal means from said computer system and at least one electronic device.
23. The voice recognition keyboard according to claim 22 wherein said voice input and output means are combined into a single unit suitable for use as a receiver for telephony.
24. The voice recognition keyboard according to claim 22 wherein at least one of said operating instructions is adapted to initiate voice over Internet provider telephony.
25. The voice recognition keyboard according to claim 16 wherein said voice recognition means also converts spoken words into corresponding keystroke input for transmission through the signal means.
26. A voice recognition input device for providing voice access to the internet from a computer configured to be connected to the internet, comprising:
a voice input means; and a voice recognition means for identifying spoken commands, at least one of said commands defined to initiate internet access; and a signal means for triggering the execution of said command.
a voice input means; and a voice recognition means for identifying spoken commands, at least one of said commands defined to initiate internet access; and a signal means for triggering the execution of said command.
27. A voice recognition input device according to claim 26 wherein said input device is a keyboard.
28. The voice recognition input device according to claim 26 wherein at least one of said commands is defined to initiate voice over internet provider telephony.
29. A voice recognition input device for providing voice access to the internet from a computer connected to a world-wide network of computers comprising:
a voice input means; and a voice recognition means for identifying spoken commands, at least one of said commands defined to initiate internet access; and a signal means for executing said commands.
a voice input means; and a voice recognition means for identifying spoken commands, at least one of said commands defined to initiate internet access; and a signal means for executing said commands.
30. A voice recognition input device according to claim 29 wherein at least one of said commands is defined to permit navigation of the internet.
31. The voice recognition keyboard according to claim 29 wherein at least one of said commands is defined to initiate voice over internet provider telephony.
32. A voice recognition input device according to claim 29 wherein said input device is a keyboard.
33. A method for providing keystroke and voice input to a computer system over a single interface comprising the steps:
inputting a voice signal;
converting said voice signal to digital voice signal;
inputting a keystroke signal;
processing simultaneously said digital voice signal and said keystroke signal by a single interface controller to generate a combined signal; and transmitting said combined signal to said computer system.
inputting a voice signal;
converting said voice signal to digital voice signal;
inputting a keystroke signal;
processing simultaneously said digital voice signal and said keystroke signal by a single interface controller to generate a combined signal; and transmitting said combined signal to said computer system.
34. The method of claim 33 further comprising:
said computer splitting said combined signal into a separate digital voice signal component and a separate keystroke signal component for separate processing by said computer system.
said computer splitting said combined signal into a separate digital voice signal component and a separate keystroke signal component for separate processing by said computer system.
35. A method for providing keystroke and voice input to a computer system over a single interface comprising the steps:
storing a sample voice print;
inputting a voice signal;
inputting a keystroke signal;
converting said voice signal to a digital voice signal;
comparing said digital voice signal to said sample voice print;
if said digital voice signal matches said sample voice print, processing simultaneously said digital voice signal and said keystroke signal by a single interface controller to a combined signal; and transmitting said combined signal to said computer system.
storing a sample voice print;
inputting a voice signal;
inputting a keystroke signal;
converting said voice signal to a digital voice signal;
comparing said digital voice signal to said sample voice print;
if said digital voice signal matches said sample voice print, processing simultaneously said digital voice signal and said keystroke signal by a single interface controller to a combined signal; and transmitting said combined signal to said computer system.
36. A method for converting spoken words into text comprising the steps:
inputting a voice signal containing spoken words;
converting said voice signal to a digital voice signal;
inputting a keystroke signal;
processing simultaneously said digital voice signal and said keyboard signal by a single interface controller to a combined signal;
transmitting said combined signal to a computer system over a single interface;
splitting said combined signal at said computer into a digital voice signal component and a keystroke signal component; and processing said digital voice signal component to convert said spoken words into corresponding text.
inputting a voice signal containing spoken words;
converting said voice signal to a digital voice signal;
inputting a keystroke signal;
processing simultaneously said digital voice signal and said keyboard signal by a single interface controller to a combined signal;
transmitting said combined signal to a computer system over a single interface;
splitting said combined signal at said computer into a digital voice signal component and a keystroke signal component; and processing said digital voice signal component to convert said spoken words into corresponding text.
37. The method of claim 36 further comprising converting said text into a second keystroke signal.
38. A method for providing access to the internet from a computer connected to the internet comprising:
inputting a voice signal containing spoken words;
converting said voice signal to a digital voice signal;
identifying said spoken words within said digital voice signal;
converting said spoken words to commands, at least one of said commands defined to initiate internet access; and transmitting said commands to said computer.
inputting a voice signal containing spoken words;
converting said voice signal to a digital voice signal;
identifying said spoken words within said digital voice signal;
converting said spoken words to commands, at least one of said commands defined to initiate internet access; and transmitting said commands to said computer.
39. The method of claim 38 wherein internet access connects said computer to a world-wide network of computers.
40. A method of remotely controlling at least one electronic device with a spoken command comprising:
inputting a spoken command as a voice signal to a keyboard;
inputting keystroke data using said keyboard;
converting said voice signal into operating instructions;
transmitting said operating instructions to said at least one electronic device;
and transmitting said keystroke data to a computer system, wherein the exact order of steps is not significant.
inputting a spoken command as a voice signal to a keyboard;
inputting keystroke data using said keyboard;
converting said voice signal into operating instructions;
transmitting said operating instructions to said at least one electronic device;
and transmitting said keystroke data to a computer system, wherein the exact order of steps is not significant.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US60242500A | 2000-06-23 | 2000-06-23 | |
| US09/602,425 | 2000-06-23 | ||
| PCT/US2001/019999 WO2002001551A1 (en) | 2000-06-23 | 2001-06-22 | Input device for voice recognition and articulation using keystroke data. |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CA2407930A1 true CA2407930A1 (en) | 2002-01-03 |
Family
ID=24411298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CA002407930A Abandoned CA2407930A1 (en) | 2000-06-23 | 2001-06-22 | Input device for voice recognition and articulation using keystroke data. |
Country Status (8)
| Country | Link |
|---|---|
| EP (1) | EP1312077A4 (en) |
| JP (1) | JP2004509385A (en) |
| CN (1) | CN1237509C (en) |
| AU (1) | AU2001270088A1 (en) |
| CA (1) | CA2407930A1 (en) |
| HK (1) | HK1059332A1 (en) |
| TW (1) | TW514824B (en) |
| WO (1) | WO2002001551A1 (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004128789A (en) * | 2002-10-01 | 2004-04-22 | Matsushita Electric Ind Co Ltd | Internet phone device and internet phone system |
| US8346983B2 (en) * | 2005-12-20 | 2013-01-01 | Creative Technology Ltd | Simultaneous sharing of system resources by multiple input devices |
| JP4337891B2 (en) * | 2007-03-01 | 2009-09-30 | セイコーエプソン株式会社 | Storage terminal and information processing system |
| CN104468572A (en) * | 2014-12-08 | 2015-03-25 | 上海大学 | Method for remote voice control over strain selecting instrument through Android mobile phone |
| KR102346026B1 (en) | 2019-02-11 | 2021-12-31 | 삼성전자주식회사 | Electronic device and Method for controlling the electronic device thereof |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA1186028A (en) * | 1982-06-23 | 1985-04-23 | Microdesign Limited | Method and apparatus for scrambling and unscrambling data streams using encryption and decryption |
| US5903870A (en) * | 1995-09-18 | 1999-05-11 | Vis Tell, Inc. | Voice recognition and display device apparatus and method |
| US5874939A (en) * | 1996-12-10 | 1999-02-23 | Motorola, Inc. | Keyboard apparatus and method with voice recognition |
| US5893064A (en) * | 1997-05-14 | 1999-04-06 | K2 Interactive Llc | Speech recognition method and apparatus with voice commands and associated keystrokes |
| JPH1125098A (en) * | 1997-06-24 | 1999-01-29 | Internatl Business Mach Corp <Ibm> | Information processor and method for obtaining link destination file and storage medium |
| DE19815760A1 (en) * | 1998-04-08 | 1998-11-26 | Siegfried Dipl Ing Schmidt | Telephone appts. with speech based dialling |
| DE19853689A1 (en) * | 1998-11-20 | 2000-05-31 | Detlef Arndt | Speech-controlled machine operating method uses remote-control device for accessing control functions for controlled machine or device stored in computer control program |
-
2001
- 2001-06-19 TW TW90114892A patent/TW514824B/en not_active IP Right Cessation
- 2001-06-22 JP JP2002505609A patent/JP2004509385A/en active Pending
- 2001-06-22 AU AU2001270088A patent/AU2001270088A1/en not_active Abandoned
- 2001-06-22 WO PCT/US2001/019999 patent/WO2002001551A1/en active Application Filing
- 2001-06-22 CN CN 01809495 patent/CN1237509C/en not_active Expired - Fee Related
- 2001-06-22 EP EP01948631A patent/EP1312077A4/en not_active Withdrawn
- 2001-06-22 CA CA002407930A patent/CA2407930A1/en not_active Abandoned
-
2004
- 2004-03-24 HK HK04102174A patent/HK1059332A1/en not_active IP Right Cessation
Also Published As
| Publication number | Publication date |
|---|---|
| EP1312077A1 (en) | 2003-05-21 |
| AU2001270088A1 (en) | 2002-01-08 |
| EP1312077A4 (en) | 2005-08-17 |
| CN1451156A (en) | 2003-10-22 |
| WO2002001551A9 (en) | 2002-11-14 |
| WO2002001551A1 (en) | 2002-01-03 |
| CN1237509C (en) | 2006-01-18 |
| HK1059332A1 (en) | 2004-06-25 |
| JP2004509385A (en) | 2004-03-25 |
| TW514824B (en) | 2002-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6169789B1 (en) | Intelligent keyboard system | |
| US20130300545A1 (en) | Internet Enabled Mobile Device for Home Control of Light, Temperature, and Electrical Outlets | |
| US6083270A (en) | Devices and methods for interfacing human users with electronic devices | |
| JP2020529032A (en) | Speech recognition translation method and translation device | |
| US20020138274A1 (en) | Server based adaption of acoustic models for client-based speech systems | |
| US7577261B2 (en) | Wireless audio system using wireless local area network | |
| US8346948B2 (en) | Information processing apparatus, selector, remote operation system, scan code transmission method, and program product therefor | |
| JP2007504568A (en) | Keyboard with digital audio function | |
| GB2392573A (en) | A pc based tv set-top box system and method of providing contents exclusively by the system | |
| US6512467B1 (en) | Method and apparatus for dynamically configuring device using device code | |
| EP1039671B1 (en) | Methods, system and computer program for encryption of computer telephony | |
| CA2407930A1 (en) | Input device for voice recognition and articulation using keystroke data. | |
| CN111798851A (en) | AI double-screen intelligent voice translation system | |
| US20060150235A1 (en) | Display system and method | |
| JPH03132797A (en) | Voice recognition device | |
| CN109346041A (en) | Audio data processing method and device for robot | |
| JPH0934895A (en) | Translation system | |
| US8073930B2 (en) | Screen reader remote access system | |
| JPH0226436B2 (en) | ||
| US20050181825A1 (en) | Wireless peripheral voice input device | |
| KR20000033518A (en) | Voice language translation system using network and method therefor | |
| KR200217890Y1 (en) | Computer system equipped with a display device for recognizing voice information | |
| JPH11296269A (en) | Input converting device | |
| CN116939464A (en) | Hearing aid system and method | |
| JP3107097B2 (en) | Telephone equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| EEER | Examination request | ||
| FZDE | Discontinued | ||
| FZDE | Discontinued |
Effective date: 20100415 |