CN202563884U - Voice recognition processor and intelligent device - Google Patents
Voice recognition processor and intelligent device Download PDFInfo
- Publication number
- CN202563884U CN202563884U CN2011204618062U CN201120461806U CN202563884U CN 202563884 U CN202563884 U CN 202563884U CN 2011204618062 U CN2011204618062 U CN 2011204618062U CN 201120461806 U CN201120461806 U CN 201120461806U CN 202563884 U CN202563884 U CN 202563884U
- Authority
- CN
- China
- Prior art keywords
- voice recognition
- microcontroller
- voice
- port
- recognition processor
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The utility model relates to a voice recognition processor and an intelligent device. In the specific voice recognition processor provided by the utility model, pre-input voices of a specific user are stored in a storage; after an analog-digital converter converts a simulation voice to a digital voice, an arithmetic operation element performs voice recognition on the user according to an input digital voice and generates a recognition result for external output; and the recognition result is carried with a control order. The external intelligent device provided by the utility model (such as household appliances) performs a corresponding action such as open or close and the like according to the control order of the recognition result, so as to realize voice control on a household appliance. Compared with the situation that the household appliance is controlled through a remote control in the prior art, the control method provided by the utility model is more flexible and effective, and the problems caused by the control of the remote control are avoided.
Description
Technical field
The utility model relates to the circuit engineering field, relates in particular to a kind of voice recognition processor and smart machine.
Background technology
The Along with people's growth in the living standard, household appliances develop into remote control control by the control of opening the light of the earliest machinery.With respect to the machinery control of opening the light, remote control control makes people control household appliances through telepilot and opens or close that control mode is comparatively flexible.
But existing remote control control mode is confined to special-purpose telepilot, and telepilot need mate with concrete household appliances usually.The corresponding special-purpose TV remote controller of televisor for example, the corresponding special-purpose air-conditioning remote control of air-conditioning etc.In case the user can not find dedicated remote control or telepilot does not have electricity, then need control home appliance through the button on the operation household appliances, even uncontrollable home appliance (for example wall-hanging air conditioner).
Therefore, existing household appliances control mode is further improved.
The utility model content
It is a kind of to the special speaker processor that the fundamental purpose of the utility model is to provide, and then realize the voice control of persona certa to household appliances.
In order to achieve the above object, the utility model proposes a kind of persona certa's voice recognition processor, comprising:
Microcontroller, power management and reset circuit, function IO port, analog to digital converter, storer, mathematical operation unit and oscillatory circuit;
Wherein, said power management and reset circuit are connected with said microcontroller, are used for said microcontroller is provided power supply and resets said microcontroller;
Said function IO port is connected with said microcontroller, is used to receive the control signal of outside input and outwards export recognition result, carries steering order in the said recognition result;
Said analog to digital converter is used to receive the analog voice of outside input, and converts analog voice into digital speech;
Said storer is used to store the digital speech of user's typing;
Said mathematical operation unit is connected with said microcontroller, is used for carrying out user's voice identification and generating recognition result according to the digital speech of input, carries steering order in the said recognition result;
Said oscillatory circuit is connected with said microcontroller, is used to provide the clock signal of said microcontroller operation.
Preferably, said storer also stores the prompt tone that needs broadcast;
Said voice recognition processor also comprises:
With the digital to analog converter that said microcontroller is connected, said digital to analog converter is used for the prompt tone that said needs are play is converted into the prompt tone signal output of simulation.
Preferably, voice recognition processor also comprises:
Operational amplifier and audio frequency power amplifier;
Said operational amplifier is connected with said digital to analog converter, is used for the prompt tone signal of said simulation is carried out audio mixing filtering;
Said audio frequency power amplifier is connected with microcontroller with operational amplifier, is used for the filtered prompt tone signal of audio mixing is carried out power amplification.
Preferably, said oscillating circuit comprises:
Base frequency oscillation circuit and the phase-locked loop circuit that is connected with said base frequency oscillation circuit;
Said phase-locked loop circuit is to said microcontroller clock signal.
Preferably, described voice recognition processor also comprises:
The PWM playback port that is connected with said microcontroller.
Preferably, said function IO port comprises:
Drive ports is used to export the drive signal of driving LED or motor;
Begin to train input port, be used to receive the beginning training signal of outside input;
Finish the training input port, be used to receive the end training signal of outside input;
The recognition result output port is used for outwards exporting the recognition result that the mathematical operation unit is exported.
Preferably, said function IO port also comprises:
Infrared output port is used for exporting voice identification result according to the standard infrared protocol with carrier format;
Dormancy awakening input control port is used to receive the dormancy of outside input or wake control signal up.
Preferably, said microcontroller is 8 nuclears of enhancement mode, and the figure place of said digital to analog converter and analog to digital converter is 16.
The utility model also proposes a kind of smart machine, comprises aforesaid persona certa's voice recognition processor.
Propose in persona certa's voice recognition processor at the utility model; Store the voice of specific user's typing in advance in the storer; After analog to digital converter converted analog voice into digital speech, the mathematical operation unit carried out user's voice identification and generates recognition result outwards exporting according to the digital speech of input.Outside home appliance is carried out corresponding action according to the steering order of recognition result, for example opens or closes etc., and then realize the voice control of home appliance.With respect to telepilot control home appliance of the prior art, control mode is more flexible effectively, the problem of avoiding telepilot control to bring.
Description of drawings
Fig. 1 is the structural representation of persona certa's voice recognition processor of providing of the utility model.
Fig. 2 is the concrete structure figure of the voice recognition processor that provides of present embodiment.
Fig. 3 is the connection synoptic diagram of digital to analog converter, operational amplifier and audio frequency power amplifier in the voice recognition processor that provides of present embodiment.
Fig. 4 is the encapsulation synoptic diagram of the voice recognition processor that provides of present embodiment.
For the purpose, technical scheme and the advantage that make the utility model is clearer,, the utility model is further elaborated below in conjunction with accompanying drawing and embodiment.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explanation the utility model, and be not used in qualification the utility model.
With reference to figure 1, Fig. 1 is the structural representation of persona certa's voice recognition processor of providing of the utility model.
In the present embodiment, voice recognition processor specifically comprises: microcontroller 10, power management and reset circuit 20, function IO port 30, analog to digital converter 40, storer 50, mathematical operation unit 60 and oscillatory circuit 70.
Wherein, said power management and reset circuit 20 are connected with said microcontroller 10, are used for said microcontroller 10 is provided power supply and resets said microcontroller 10;
Said function IO port 30 is connected with said microcontroller 10, is used to receive the control signal of outside input and outwards export recognition result, carries steering order in the said recognition result;
Said analog to digital converter 40 is used to receive the analog voice of outside input, and converts analog voice into digital speech;
Said storer 50 is used to store the digital speech of user's typing;
Said mathematical operation unit 60 is connected with said microcontroller 10, is used for carrying out user's voice identification and generating recognition result according to the digital speech of input, carries steering order in the said recognition result;
Said oscillatory circuit 70 is connected with said microcontroller 10, is used to provide the clock signal of said microcontroller 10 operations.
Propose in persona certa's voice recognition processor at the utility model; Store the voice of specific user's typing in advance in the storer 50; After analog to digital converter 40 converts analog voice into digital speech; Mathematical operation unit 60 carries out user's voice identification and generates recognition result outwards exporting according to the digital speech of input, carries steering order in this recognition result.Outside smart machine (for example home appliance) is carried out corresponding action according to the steering order of recognition result, for example opens or closes etc., and then realize the voice control of home appliance.With respect to telepilot control home appliance of the prior art, control mode is more flexible effectively, the problem of avoiding telepilot control to bring.
Further, storer 50 also stores the prompt tone of need playing, and for example points out prompt tone that the user says instruction etc.; Voice recognition processor can also comprise:
With the digital to analog converter 80 that said microcontroller 10 is connected, said digital to analog converter 80 is used for the prompt tone that said needs are play is converted into the prompt tone signal output of simulation.
Present embodiment is through increasing digital to analog converter 80; Can voice recognition processor when the user controls home appliance through voice; Send the corresponding prompt sound to the user; For example point out the user to say instruction or require the user to repeat or instruct input prompt for successful etc., can improve user's Experience Degree.
Further, the voice recognition processor that provides of present embodiment also comprises:
Operational amplifier 90 and audio frequency power amplifier 100;
Wherein, operational amplifier 90 is connected with said digital to analog converter 80, is used for the prompt tone signal of said simulation is carried out audio mixing filtering;
Said audio frequency power amplifier 100 is connected with microcontroller 10 with operational amplifier, is used for the filtered prompt tone signal of audio mixing is carried out power amplification.
Present embodiment can realize that through increasing operational amplifier 90 and audio frequency power amplifier 100 direct loudspeaker to the outside drives, and has strengthened the function of voice recognition processor.
Referring to Fig. 2, Fig. 2 is the cut-away view of the voice recognition processor that provides of present embodiment.
In the present embodiment, microcontroller is specially 8 nuclears of enhancement mode, and the figure place of digital to analog converter (DAC) and analog to digital converter (ADC) is 16.Storer comprises ROM (read-only memory) (ROM) and static memory (SRAM), wherein stores the control program of prompt tone that need to play and training, identification.Oscillating circuit is specially VCO-PLL in the present embodiment, and wherein VCO-PLL specifically comprises: base frequency oscillation circuit and the phase-locked loop circuit that is connected with said base frequency oscillation circuit, phase-locked loop circuit is to said microcontroller output system clock signal.
In the present embodiment, voice recognition processor also comprises 12 PWM playback ports that are connected with said microcontroller.
Referring to Fig. 3, Fig. 3 is the connection synoptic diagram of digital to analog converter, operational amplifier and audio frequency power amplifier in the voice recognition processor that provides of present embodiment.
As shown in the figure, CL wherein, RL, CR, RR, RF, CF are the peripheral capacitance resistance ware of voice recognition processor.The diagram circuit can be realized the mixing amplification and the filtering of AUDIO_L and AUDIO_R two paths of signals, and its output terminal OP_O can directly connect AMP_IN.Use for the overwhelming majority, AUDIO_L, the AUDIO_R two-way need not use simultaneously, and only need connect AUDIO_L and get final product, at this moment, and CR, RR can omit.
Well known port below in conjunction with in Fig. 2-3 pair voice recognition processor describes, and outside port commonly used can roughly be divided into four types:
1. power port
It comprises VCC, GND, VDD, VSS, VPP, VSL and RESET pin.
The power supply of VCC, GND---numerical portion and ground.
The power supply of VDD, VSS---analog part and ground.
VPP, VSL---the power supply of the built-in ROM of voice recognition processor.
Low level resetted after the resetting pin of RESET---voice recognition processor, voice recognition processor powered on.
2. oscillatory circuit port
The oscillatory circuit port specifically comprises R_FREQ and C_PLL pin.The inner integrated R/C vibration of voice recognition processor (base frequency oscillation) and PLL circuit, the R_FREQ pin needs external 270K resistance, can realize the base frequency oscillation of 1.86MHz.The stabilization time of C_PLL foot control system PLL circuit, can be vacant or the electric capacity of use≤1000pF.
3. audio port
Audio port specifically comprises ADC_IN, AUDIO_L, AUDIO_R, OP_P, OP_N, OP_O, AMP_IN, AMP_P and AMP_N pin.
ADC_IN---the input port of 16 ADC, input range 0 ~ VDD, the suggestion DC level is arranged on 0.51 ~ 0.53VDD place, to obtain the better linearity.Voice recognition processor power on or reset after can carry out the ADC_IN pin automatically DC level detect, the time spent is 0.5 ~ 0.75 second.
AUDIO_L---the delivery outlet of left road DAC, output area are 0 ~ VDD.
AUDIO_R---the delivery outlet of right wing DAC, output area are 0 ~ VDD.
OP_P---the in-phase input end of audio mixing filtering operation amplifier, internal system connects 1/2 VDD, please be vacant during conventional the use.
OP_N---audio mixing filtering operation amplifier's inverting input.
OP_O---the signal output part of audio mixing filtering operation amplifier is connected to AMP_IN in the standard application.
The signal input part of AMP_IN---audio-frequency power amplifier.
The positive output of AMP_P---audio-frequency power amplifier is disconnected, can directly drive loudspeaker or the piezo of 0.5W/8 Ω.
The negative output of AMP_N---audio-frequency power amplifier is disconnected, can directly drive loudspeaker or the piezo of 0.5W/8 Ω.
4. function IO port
Function IO port specifically comprises two groups of PORT0 and PORT1 totally 16 pins, provides power supply control, button input, the LED of SPI Flash port, voicefrequency circuit to drive, MOTOR drives, infrared emission drives and multiple common function such as serial data output.
Wherein, P00---begin to train the key input port, low pulse is effective.Invalid under training mode; Under recognition mode,, get into training mode, remove the data of former training, again training for " beginning training ".
P01---BLA controls delivery outlet, this port default output high level, and output low level when voice recognition processor plays sound, playback is got back to high level after finishing.Can connect the LED lamp, but also CD-ROM drive motor.(produced by process simulation) when voice recognition processor is in quiet in the voice segments, port is failure to actuate, and gets back to high level.
P02---LED dynamically shows the control mouth, and effectively low, this port function starts when voice recognition processor plays sound, and playback stops after finishing.Port can change output level according to the size of volume.
Function details: port default output high level, during voice recognition processor decoding playback, like the value (16Bit) of speech data between mid point level ± 1000H, port output high level, otherwise port output low level.
P03---3Hz shows the control mouth, and effectively low, this port function starts when voice recognition processor plays sound, and playback stops after finishing.This function is if start, when then playing sound, and will be according to the output level of the frequency values of setting in the Flash (can not be 3Hz) conversion port.
P04---train the key input port again, low pulse is effective.Under the training mode: when training this entry second time, restart to train this entry; When training this entry first pass, train a last entry again.Under the recognition mode: trained termination to continue training from last time, and accomplished until whole statement training.As when sheet is worked, the master control voice recognition processor need produce low pulse greater than 50ms to make it work.
P05---finish training key input port, low pulse is effective.End training and get into recognition mode, useless under recognition mode.As when sheet is worked, the master control voice recognition processor need produce low pulse greater than 50ms to make it work.
P04, P05 can cooperate realization Voice Test function, are used for whole sound of system are tested, and whether can detect the sentence combination of loosing correct.
The method of application of Voice Test is: start-up prompting sound drags down P04 and P05 before playing and finishing simultaneously, and then voice recognition processor is with all voice in the automatic Play System in order.Any one or two uprise among P04, the P05, then EOT.If voice all finish, voice recognition processor will get into training/recognition mode.
P06---sleeping/waking input control mouth, low level is effective.When for the first time dragging down the port and kept for 3 seconds (or 50ms, optional), system plays shutdown prompt tone (maskable), and get into dormancy; Drag down the port (negative edge triggering) once more and can wake voice recognition processor up, behind the system plays prompt tone (maskable), get into status recognition.Utilize the port, configurable " start/shutdown " button also can constitute principal and subordinate's control system with voice recognition processor as coprocessor.
P07---infrared output port, the port can be used for realizing the intelligent sound control to infrared equipments such as household electrical appliances.According to the setting in the Flash, behind each end of identification, voice recognition processor will send control data with carrier format according to the standard infrared protocol.The port function need cooperate outside infrared emission circuit to realize.
Above-mentioned each port all can determine its state when dormancy through the Flash content is set.Whether port status can be set to input pattern or output mode, configurablely under the input pattern draw on, and output mode draws on down meaningless.Should be according to external circuit, the reasonable disposition port status is to reach the purpose that reduces system power dissipation.Under the default conditions, each port is and draws input during dormancy.Measured data shows: when driving is simply hanged down effective led circuit, be set to during dormancy draw in the input, power consumption is lower during with the specific output high level.
P10 ~ P13---SPI Flash port, P10 connects the CLK pin of Flash; P11 connects the CS pin of Flash; P12 is the data output of voice recognition processor, connects the Data in pin of Flash; P13 is the data input of voice recognition processor, connects the Data out pin of Flash.
P14---the CLK pin of two-wire serial output, the port is that the serial output of voice recognition processor duty and recognition result provides clock line.
P15---init state and end-point detection indication mouth, but driving LED, low level is effective.The port is a low level in system's power-up initializing process always, after system gets into status recognition, and the output high level.Under the status recognition, begin when detecting sound, output low level, sound finishes, and returns high level; Under the non-status recognition (like playback time), keep high level.Whether the port is used to indicate sound end to detect accurate; Whether also can monitor voice recognition processor starts normal: if the initialization failure, voice recognition processor will be attempted initialization once more, and still failure then gets into park mode, and in this process, P15 will be low always.
P16---the DATA pin of two-wire serial output, the port is that the serial output of voice recognition processor duty and recognition result provides data line.SOD serial output data is 0, and representative system is just being play and answered the record prompt tone; Data are 1 ~ N, and representing recognition result is the 1st ~ N model, N the corresponding Different control instruction of model; N+1 shows that then importing voice is refused to know.
The power supply control mouth of P17---microphone audio amplifying circuit can be set high effective or effectively low through changing the relative set among the Flash.Be set at highly effectively the time, port can provide the drive current of maximum 4mA.The port steering logic is by the voice recognition processor inner setting, and start and initialization success postposition are effective status, then export reverse level after the dormancy.
The port status of P10 ~ P17 under dormant state controlled by system automatically, need not the user set.
The voice recognition processor that present embodiment provides on the basis of 8 little process nuclear of enhancement mode, integrated special-purpose mathematical operation unit, but the decoding replayed section of real-time implementation persona certa's voice training, identification and high compression formatted voice; In addition, processor includes SRAM and ROM, has embedded the complete routine of training, identification control; Voice recognition processor provides 1 tunnel 16 ADC and 2 tunnel 16 DAC passages, can realize high-quality audio frequency input and output conversion; The built-in audio-frequency power amplifier of voice recognition processor can directly drive the loudspeaker of 0.5W 8 Ω; In addition, also be integrated with the controlled PLL circuit of R/C base frequency oscillation circuit and frequency multiplication in the voice recognition processor.The SOC mentality of designing makes the peripheral circuit of voice recognition processor simplify greatly, becomes the highest voice recognition processor of integrated level in the present Embedded Speech Recognition System field.
In addition, voice recognition processor has defined the port of a plurality of action controls, can realize that through easy configuration button input, LED demonstration, motor driven and infrared emission drive function.Voice recognition processor provides the serial data output of voice identification result, can make coprocessor and use, and is convenient to the application extension of system.Voice recognition processor can be applied to the man-machine interaction of intelligence dialogue toy, household electrical appliances Based Intelligent Control, PDA and handheld device etc.
Referring to Fig. 4, Fig. 4 is the voice recognition processor encapsulation synoptic diagram that present embodiment provides.
The voice recognition processor that present embodiment provides comprises 44 pins, and concrete pin definitions is following:
The power supply of 1-VDDP simulating signal: 2.7V ~ 3.6V (representative value 3.0V);
The reference ground of 2-VSSP simulating signal;
The signal input part of 3-AMP_INA audio frequency power amplifier;
The output terminal of 4-OP_OA internal arithmetic amplifier;
The in-phase input end of 5-OP_PA internal arithmetic amplifier;
6-OP_NA internal arithmetic amplifier's inverting input;
The passage DAC output of a 7-AUDIO_LA left side;
The right passage DAC output of 8-AUDIO_RA;
9～10NC keeps, and does not connect;
The signal input part of 11-ADC_INAADC;
12 ~ 19NC keeps, and does not connect;
The power supply of the inner ROM of 20-VPPP;
The power supply of the inner ROM of 21-VSLP;
Resistance input end (the suggestion: 270K) of the inner fundamental frequency VCO of 22-R_FREQI;
The damping capacitor end of the inner PLL circuit of 23-C_PLLI (suggestion: vacant or meet 1000pf);
The reference ground of 24-GNDP digital signal;
The power supply of 25-VCCP digital signal: 2.7V ~ 3.6V (representative value 3.0V);
The 26-RESETIS resetting pin, low level is effective;
The power control terminal of 27-PORT17O microphone audio amplifying circuit;
The DATA pin of 28-PORT16O two-wire serial output;
29-PORT15O initialization and end-point detection indication pin;
The CLK pin of 30-PORT14O two-wire serial output;
The infrared output drive ports of 31-PORT07O;
32-PORT06IS sleeping/waking input control mouth;
33-PORT05IS ends training;
34-PORT04IS trains again;
35-PORT03O3Hz shows the control mouth;
36-PORT02OLED dynamically shows the control mouth;
37-PORT01OBLA controls delivery outlet;
38-PORT00IS begins training;
Main equipment input/slave unit the output of 39-PORT13/SPI_MISOI/O SPI port;
Main equipment output/slave unit the input of 40-PORT12/SPI_MOSII/O SPI port;
The SSB end of 41-PORT11/SSBOSPI port;
The SCK end of 42-PORT10/SCKI/O SPI port;
The negative output terminal of 43-AMP_NA audio frequency power amplifier (directly connecing loudspeaker or piezo);
The positive output end of 44AMP_PA audio frequency power amplifier (directly connecing loudspeaker or piezo).
More than persona certa's voice recognition processor that present embodiment is provided carried out detailed introduction, present embodiment also provides a kind of smart machine at last, it comprises aforesaid persona certa's voice recognition processor.Wherein, smart machine is not limited to other home appliances such as intelligent television, mobile phone, intelligent air condition, fan.In the smart machine that the utility model provides, comprise persona certa's voice recognition processor; Storer 50 in the voice recognition processor stores the voice of specific user's typing in advance; After analog to digital converter 40 converted analog voice into digital speech, mathematical operation unit 60 carried out user's voice identification and generates recognition result outwards exporting according to the digital speech of input.Smart machine is carried out corresponding action according to the steering order of recognition result, for example opens or closes etc., and then realize the voice control of smart machine.With respect to telepilot control home appliance of the prior art, control mode is more flexible effectively, the problem of avoiding telepilot control to bring.
The above is merely the preferred embodiment of the utility model; Be not thus the restriction the utility model claim; Every equivalent structure or flow process conversion that utilizes the utility model instructions and accompanying drawing content to be done; Or directly or indirectly be used in other relevant technical field, all in like manner be included in the scope of patent protection of the utility model.
Claims (9)
1. a voice recognition processor is characterized in that, comprising:
Microcontroller, power management and reset circuit, function IO port, analog to digital converter, storer, mathematical operation unit and oscillatory circuit;
Wherein, said power management and reset circuit are connected with said microcontroller, are used for said microcontroller is provided power supply and resets said microcontroller;
Said function IO port is connected with said microcontroller, is used to receive the control signal of outside input and outwards export recognition result, carries steering order in the said recognition result;
Said analog to digital converter is used to receive the analog voice of outside input, and converts analog voice into digital speech;
Said storer is used to store the digital speech of user's typing;
Said mathematical operation unit is connected with said microcontroller, is used for carrying out user's voice identification and generating recognition result according to the digital speech of input, carries steering order in the said recognition result;
Said oscillatory circuit is connected with said microcontroller, is used to provide the clock signal of said microcontroller operation.
2. voice recognition processor according to claim 1 is characterized in that, said storer also stores the prompt tone that needs broadcast; Said voice recognition processor also comprises: with the digital to analog converter that said microcontroller is connected, said digital to analog converter is used for the prompt tone that said needs are play is converted into the prompt tone signal output of simulation.
3. voice recognition processor according to claim 2 is characterized in that, also comprises: operational amplifier and audio frequency power amplifier; Said operational amplifier is connected with said digital to analog converter, is used for the prompt tone signal of said simulation is carried out audio mixing filtering;
Said audio frequency power amplifier is connected with microcontroller with operational amplifier, is used for the filtered prompt tone signal of audio mixing is carried out power amplification.
4. voice recognition processor according to claim 1 is characterized in that, said oscillating circuit comprises: base frequency oscillation circuit and the phase-locked loop circuit that is connected with said base frequency oscillation circuit; Said phase-locked loop circuit is to said microcontroller clock signal.
5. voice recognition processor according to claim 1 is characterized in that, also comprises: the PWM playback port that is connected with said microcontroller.
6. according to each described voice recognition processor among the claim 1-5, it is characterized in that said function IO port comprises: drive ports is used to export the drive signal of driving LED or motor; Begin to train input port, be used to receive the beginning training signal of outside input; Finish the training input port, be used to receive the end training signal of outside input; The recognition result output port is used for outwards exporting the recognition result that the mathematical operation unit is exported.
7. voice recognition processor according to claim 6 is characterized in that, said function IO port also comprises: infrared output port is used for exporting voice identification result according to the standard infrared protocol with carrier format; Dormancy awakening input control port is used to receive the dormancy of outside input or wake control signal up.
8. voice recognition processor according to claim 7 is characterized in that, said microcontroller is 8 nuclears of enhancement mode, and the figure place of said digital to analog converter and analog to digital converter is 16.
9. a smart machine is characterized in that, comprises like each described persona certa's voice recognition processor of claim 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011204618062U CN202563884U (en) | 2011-11-18 | 2011-11-18 | Voice recognition processor and intelligent device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011204618062U CN202563884U (en) | 2011-11-18 | 2011-11-18 | Voice recognition processor and intelligent device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202563884U true CN202563884U (en) | 2012-11-28 |
Family
ID=47213512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011204618062U Expired - Fee Related CN202563884U (en) | 2011-11-18 | 2011-11-18 | Voice recognition processor and intelligent device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202563884U (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104318150A (en) * | 2014-11-21 | 2015-01-28 | 长江大学 | Database access authentication device based on voice query |
| CN104511036A (en) * | 2013-09-26 | 2015-04-15 | 樱花卫厨（中国）股份有限公司 | Intelligent voice control circuit of disinfection cabinet |
| CN105609118A (en) * | 2015-12-30 | 2016-05-25 | 生迪智慧科技有限公司 | Speech detection method and device |
| CN105679320A (en) * | 2014-11-21 | 2016-06-15 | 佛山市顺德区美的电热电器制造有限公司 | Voice control device and voice control method for home appliances |
| CN106710197A (en) * | 2017-01-18 | 2017-05-24 | 深圳市网多多科技有限公司 | Remote control method and remote control device |
| CN107369461A (en) * | 2017-07-25 | 2017-11-21 | 成都德芯数字科技股份有限公司 | Audio broadcasting control system and method |
| CN108447236A (en) * | 2018-01-30 | 2018-08-24 | 广东家天下光环境智控有限公司 | Home equipment control method, switch and nonvolatile computer storage media |
| CN109243498A (en) * | 2018-11-20 | 2019-01-18 | 南京莱斯信息技术股份有限公司 | A kind of endpoint detection system and detection method based on FFT voice signal |
| CN111245688A (en) * | 2019-12-26 | 2020-06-05 | 的卢技术有限公司 | Method and system for intelligently controlling electrical equipment based on indoor environment |
| WO2020133850A1 (en) * | 2018-12-29 | 2020-07-02 | 展讯通信（深圳）有限公司 | Signal generating circuit and audio processing device |
| CN113223530A (en) * | 2021-05-19 | 2021-08-06 | 中山亿联智能科技有限公司 | Method for controlling fan by voice command |
-
2011
- 2011-11-18 CN CN2011204618062U patent/CN202563884U/en not_active Expired - Fee Related
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104511036A (en) * | 2013-09-26 | 2015-04-15 | 樱花卫厨（中国）股份有限公司 | Intelligent voice control circuit of disinfection cabinet |
| CN104511036B (en) * | 2013-09-26 | 2017-04-05 | 樱花卫厨（中国）股份有限公司 | Disinfection cabinet intelligent sound control circuit |
| CN105679320A (en) * | 2014-11-21 | 2016-06-15 | 佛山市顺德区美的电热电器制造有限公司 | Voice control device and voice control method for home appliances |
| CN104318150A (en) * | 2014-11-21 | 2015-01-28 | 长江大学 | Database access authentication device based on voice query |
| CN105679320B (en) * | 2014-11-21 | 2019-09-27 | 佛山市顺德区美的电热电器制造有限公司 | Phonetic controller and sound control method for household electrical appliance |
| CN105609118A (en) * | 2015-12-30 | 2016-05-25 | 生迪智慧科技有限公司 | Speech detection method and device |
| CN105609118B (en) * | 2015-12-30 | 2020-02-07 | 生迪智慧科技有限公司 | Voice detection method and device |
| CN106710197B (en) * | 2017-01-18 | 2021-06-01 | 深圳市网多多科技有限公司 | Remote control method and device |
| CN106710197A (en) * | 2017-01-18 | 2017-05-24 | 深圳市网多多科技有限公司 | Remote control method and remote control device |
| CN107369461A (en) * | 2017-07-25 | 2017-11-21 | 成都德芯数字科技股份有限公司 | Audio broadcasting control system and method |
| CN108447236A (en) * | 2018-01-30 | 2018-08-24 | 广东家天下光环境智控有限公司 | Home equipment control method, switch and nonvolatile computer storage media |
| CN109243498A (en) * | 2018-11-20 | 2019-01-18 | 南京莱斯信息技术股份有限公司 | A kind of endpoint detection system and detection method based on FFT voice signal |
| CN109243498B (en) * | 2018-11-20 | 2023-03-14 | 南京莱斯信息技术股份有限公司 | End point detection system and method based on FFT (fast Fourier transform) voice signal |
| WO2020133850A1 (en) * | 2018-12-29 | 2020-07-02 | 展讯通信（深圳）有限公司 | Signal generating circuit and audio processing device |
| US11881821B2 (en) | 2018-12-29 | 2024-01-23 | Spreadtrum Communications (Shenzhen) Co., Ltd. | Signal generating circuit and audio processing device |
| CN111245688A (en) * | 2019-12-26 | 2020-06-05 | 的卢技术有限公司 | Method and system for intelligently controlling electrical equipment based on indoor environment |
| CN113223530A (en) * | 2021-05-19 | 2021-08-06 | 中山亿联智能科技有限公司 | Method for controlling fan by voice command |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN202563884U (en) | Voice recognition processor and intelligent device | |
| CN101236744B (en) | Speech recognition object response system and method | |
| CN206283621U (en) | A kind of intelligent remote controller | |
| CN109859757A (en) | A kind of speech ciphering equipment control method, device and terminal | |
| CN104299296A (en) | Door lock control system and control method | |
| CN106877783A (en) | A kind of motor drive circuit, method and electronic equipment | |
| CN105605738B (en) | A kind of air-conditioner control system | |
| CN107945799A (en) | A kind of multifunction speech interactive intelligence machine | |
| CN102740411B (en) | A kind of wireless microphone system based on WIFI wireless network | |
| CN208094778U (en) | A kind of voice control intelligent sound box | |
| CN104793965B (en) | Electronic device, functional unit and its closedown method | |
| CN206283575U (en) | A kind of settable remote control based on mobile terminal | |
| CN213028445U (en) | Intelligent sound box | |
| CN212259318U (en) | Bluetooth desktop loudspeaker box with wireless microphone | |
| CN209453563U (en) | A kind of intelligent robot | |
| CN211132965U (en) | Environment monitoring type entertainment terminal equipment | |
| CN214588016U (en) | Voice control treadmill | |
| CN211555012U (en) | Password fingerprint lock system based on bluetooth | |
| CN210161169U (en) | Home service robot | |
| CN210578969U (en) | Video alarm clock player | |
| CN209159579U (en) | A kind of vehicle intelligent speech aid | |
| CN215030506U (en) | Intelligent water curtain separation wall and control device thereof | |
| CN207833930U (en) | A kind of Bluetooth remote control recording device and bluetooth sound pick-up outfit | |
| CN208193636U (en) | A kind of amusement vehicle for child to blow bubbles | |
| CN217506704U (en) | Ultrasonic remote control circuit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20121128 Termination date: 20161118 |