CN109003604A - A kind of audio recognition method that realizing low-power consumption standby and system - Google Patents
A kind of audio recognition method that realizing low-power consumption standby and system Download PDFInfo
- Publication number
- CN109003604A CN109003604A CN201810637441.0A CN201810637441A CN109003604A CN 109003604 A CN109003604 A CN 109003604A CN 201810637441 A CN201810637441 A CN 201810637441A CN 109003604 A CN109003604 A CN 109003604A
- Authority
- CN
- China
- Prior art keywords
- signal
- infrared
- processing unit
- human body
- voice signal
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 80
- 230000005855 radiation Effects 0.000 claims abstract description 17
- 206010002953 Aphonia Diseases 0.000 claims abstract description 7
- 238000011946 reduction process Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims 2
- 230000005616 pyroelectricity Effects 0.000 claims 2
- 230000005236 sound signal Effects 0.000 claims 1
- 241000282326 Felis catus Species 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000003638 chemical reducing agent Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/10—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors
- G01J5/12—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors using thermoelectric elements, e.g. thermocouples
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V8/00—Prospecting or detecting by optical means
- G01V8/10—Detecting, e.g. by using light barriers
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention provides a kind of speech method for realizing low-power consumption standby, including following method and step: acquiring the infrared signal of human body radiation, by handling infrared signal, judges whether there is human body and enter or move out area-of-interest；When thering is human body to enter or moving out or rest on the area-of-interest, start to detect in ambient enviroment with the presence or absence of voice signal；When detecting that there are voice signals in ambient enviroment, then start to judge in the voice signal with the presence or absence of keyword；If there are keywords in the voice signal, by the transmitting voice signal to remote data center processing, after the remote data center is by handling voice signal, return instruction signal.The present invention opens speech detection step by step, the power consumption of system is effectively reduced by the generation for multiple affair.
Description
Technical field
The present invention relates to field of artificial intelligence, in particular to a kind of audio recognition method for realizing low-power consumption standby and
System.
Background technique
Intelligent sound identification is for equipment such as smart phone, intelligent sound boxes.They pick up periphery voice using microphone and believe
Breath, when being tested with voice input and being keyword, smart machine is activated, and can receive further keyword and know
Not, and corresponding function is opened, for example weather lookup, requesting songs, travelling are predetermined etc..
Usual smart machine is powered using battery, therefore reduction power consumption can be improved smart machine and use the time.But it is existing
The audio-frequency information for thering is intelligent sound identifying system to need to pick up by microphone in real time, to progresss noise reduction etc. handle, so
After carry out speech detection.If having detected voice input, opens corresponding processing unit and carry out speech detection.In standby rank
Section, microphone and Real-time Noisy Reducer needs are normally opened, and operation power consumption is larger, and reduce smart machine uses the time.
Therefore, to solve the above-mentioned problems, a kind of audio recognition method for realizing low-power consumption standby and system are needed.
Summary of the invention
One aspect of the present invention is to provide a kind of audio recognition method for realizing low-power consumption standby, the method includes
Following method and step:
The infrared signal for acquiring human body radiation judges whether there is human body and enters or move out by handling infrared signal
Area-of-interest；
When have human body enter or move out or rest on the area-of-interest, start detect ambient enviroment in whether
There are voice signals；
When detecting that there are voice signals in ambient enviroment, then start to judge in the voice signal with the presence or absence of key
Word；
If there are keywords in the voice signal, by the transmitting voice signal to remote data center processing, institute
After remote data center is stated by handling voice signal, return instruction signal.
Preferably, the infrared signal of human body radiation is acquired by infrared detection module, and infrared signal is handled.
Preferably, the infrared detection module include but is not limited to pyroelectric infrared sensor, thermopile infrared sensor,
First digital analog converter and infrared signal processing unit, the infrared detection module locate infrared signal by the following method
Reason:
Human body radiation is infrared in the pyroelectric infrared sensor and/or thermopile infrared sensor acquisition ambient enviroment
Infrared signal is converted to electric signal by signal, after the first digital analog converter is converted to digital signal, is input at infrared signal
Unit is managed,
The infrared signal processing unit judges whether the digital signal of input changes, and when a change, then sentences
It is disconnected to there is human body to enter or move out area-of-interest；
The infrared signal processing unit judges whether the digital signal of input is more than threshold value, when a threshold is exceeded, is then sentenced
It is disconnected to there is human body to rest on area-of-interest.
Preferably, the voice signal in ambient enviroment is detected by speech detection module.
Preferably, the speech detection module includes microphone array, the second digital analog converter and Speech processing list
Member, the detection of voice signal is handled by the following method in ambient enviroment:
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue
After converter is converted to digital signal, it is input to Speech processing unit；
Speech processing unit carries out noise reduction process, number letter of the detection by noise reduction process to the digital signal of input
It whether there is voice signal in number.
Preferably, the keyword in voice signal is judged by keyword recognition module.
Another aspect of the present invention is to provide a kind of speech recognition system for realizing low-power consumption standby, the system packet
Include remote data center and user terminal, wherein the user terminal includes: infrared detection module, for acquiring human body radiation
Infrared signal, judge that human body enters or moves out or rest on area-of-interest；
Speech detection module, for detecting ambient enviroment with the presence or absence of voice signal；
Keyword recognition module, for detecting the voice signal detected in speech detection module with the presence or absence of keyword；
Wireless communication module, for the voice signal with keyword to be sent to remote data center, and for connecing
Receive the command signal that remote data center is sent.
Preferably, the infrared detection module include but is not limited to pyroelectric infrared sensor, thermopile infrared sensor,
First digital analog converter and infrared signal processing unit, the infrared detection module locate infrared signal by the following method
Reason:
Human body radiation is infrared in the pyroelectric infrared sensor and/or thermopile infrared sensor acquisition ambient enviroment
Infrared signal is converted to electric signal by signal, after the first digital analog converter is converted to digital signal, is input at infrared signal
Unit is managed,
The infrared signal processing unit judges whether the digital signal of input changes, and when a change, then sentences
It is disconnected to there is human body to enter or move out area-of-interest；
The infrared signal processing unit judges whether the digital signal of input is more than threshold value, when a threshold is exceeded, is then sentenced
It is disconnected to there is human body to rest on area-of-interest.
Preferably, the speech detection module includes microphone array, the second digital analog converter and Speech processing list
Member, the detection of voice signal is handled by the following method in ambient enviroment:
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue
After converter is converted to digital signal, it is input to Speech processing unit；
Speech processing unit carries out noise reduction process, number letter of the detection by noise reduction process to the digital signal of input
It whether there is voice signal in number.
The present invention is a kind of audio recognition method for realizing low-power consumption standby and system, is in normal by infrared detection module
Open state acquires the infrared signal of human body radiation, is in speech detection module, keyword module and wireless communication module and closes
State, when infrared detection module detects someone's activity in area-of-interest, just unlatching speech recognition, opens speech detection step by step
And wireless communication.Since the power consumption of infrared acquisition is well below the power consumption of audio processing, can significantly reduce using speech recognition
Smart machine stand-by power consumption.
The present invention opens speech detection step by step, the power consumption of system is effectively reduced by the generation for multiple affair.
It should be appreciated that aforementioned description substantially and subsequent detailed description are exemplary illustration and explanation, it should not
As the limitation to the claimed content of the present invention.
Detailed description of the invention
With reference to the attached drawing of accompanying, the more purposes of the present invention, function and advantage are by the as follows of embodiment through the invention
Description is illustrated, in which:
Fig. 1 diagrammatically illustrates a kind of structural block diagram for the speech recognition system for realizing low-power consumption standby of the present invention.
Fig. 2 shows a kind of flow diagrams for the audio recognition method for realizing low-power consumption standby of the invention.
Specific embodiment
By reference to exemplary embodiment, the purpose of the present invention and function and the side for realizing these purposes and function
Method will be illustrated.However, the present invention is not limited to exemplary embodiment as disclosed below；Can by different form come
It is realized.The essence of specification is only to aid in those skilled in the relevant arts' Integrated Understanding detail of the invention.
Hereinafter, the embodiment of the present invention will be described with reference to the drawings, relevant technical terms should be those skilled in the art
Known to member.In the accompanying drawings, identical appended drawing reference represents same or similar component or same or like step,
Unless otherwise indicated.The contents of the present invention are illustrated below by specific embodiment, according to an embodiment of the invention, real
Applying a kind of speech recognition system for realizing low-power consumption standby in example includes remote data center and user terminal, remote data center
It can be remote server, realize the communication with user terminal.User terminal can be the intelligence such as bright smart phone, intelligent sound box
Equipment.The present embodiment is particularly by taking smart phone as an example, a kind of speech recognition for realizing low-power consumption standby of the present invention as shown in Figure 1
The structural block diagram of system, a kind of speech recognition system that realizing low-power consumption standby include remote data center 200 and user terminal
100。
User terminal 100 includes infrared detection module 101, speech detection module 109, keyword recognition module 110 and nothing
Line communication module 111.Remote data center 200 includes the channel radio being in communication with each other with the wireless communication module 111 of user terminal
Believe module 202 and data processing centre 201.
Infrared detection module 101 judges that human body enters or moves out or stop for acquiring the infrared signal of human body radiation
Stay in area-of-interest.Infrared detection module 101 includes but is not limited to pyroelectric infrared sensor (pir sensor) 102a, heat
Pile infrared sensor (TPS sensor) 102b, the first digital analog converter 104 and infrared signal processing unit 105.Infrared acquisition
Module handles infrared signal by the following method:
Pyroelectric infrared sensor 102 acquires the infrared signal of human body radiation in ambient enviroment, and infrared signal is converted to
Electric signal is input to infrared signal processing unit 105 after the first digital analog converter 104 is converted to digital signal.
Infrared signal processing unit 105 judges whether the digital signal of input changes, and when a change, then judges
There is human body to enter or move out area-of-interest.
Infrared signal processing unit judges whether the digital signal of input is more than threshold value, and when a threshold is exceeded, then judgement has
Human body rests on area-of-interest.
In the embodiment of the present invention, the infrared signal of pyroelectric infrared sensor (pir sensor) 102a acquisition passes through red
External signal processing unit 105 judges whether the digital signal of input changes.Thermopile infrared sensor (TPS sensor)
The infrared signal of 102b acquisition judges whether the digital signal of input is more than threshold value by infrared signal processing unit
When judging that someone enters or move out or rest on area-of-interest, infrared signal processing unit 105 is to voice
Detection module 109 sends a trigger signal, and triggering speech detection module 109 opens work.Sense mentioned in the present invention is emerging
Interesting region refers to a preset regional scope, when human body enters or moves out or rest on the regional scope, then
Infrared signal processing unit 105 changes the digital signal for determining input.The present invention in the standby state, infrared acquisition mould
Block is in running order always, constantly acquisition infrared signal.
Speech detection module 109, for detecting ambient enviroment with the presence or absence of voice signal.Speech detection module 109 includes
Microphone array, the second digital analog converter 107 and Speech processing unit 106.In the present embodiment, schematically by multiple wheats
The microphone array that gram wind 108 forms is connected with each other between multiple microphones 108, and is connected to the second digital analog converter 107
It is communicated with Speech processing unit 106.
When speech detection module 109 receives the trigger signal of the transmission of infrared signal processing unit 105, then speech detection module
Work is opened, including opens microphone array, the second digital analog converter 107 and Speech processing unit 106.
Speech detection module 109 handles the detection of voice signal in ambient enviroment by the following method:
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue
After converter 107 is converted to digital signal, it is input to Speech processing unit 106.
The digital signal of 106 pairs of Speech processing unit inputs carries out noise reduction process, detects the number Jing Guo noise reduction process
It whether there is voice signal in word signal.Speech processing unit 106 is not specifically limited the detection algorithm of voice signal,
Can use those skilled in the art it is conceivable that any speech detection algorithms, for example, by using the speech of Third-order cumulants theory
Whether detection algorithm has voice signal in the audio-frequency information to detect microphone array acquisition.
Keyword recognition module 110, for detecting the voice signal detected in speech detection module with the presence or absence of keyword.
According to an embodiment of the invention, then passing through Speech processing unit when detecting voice signal in speech detection module 109
106 send a trigger signal to keyword recognition module 110, and keyword recognition module 110 receives trigger signal, keyword
Identification module is opened, and carries out keyword search to the voice signal that Speech processing unit 106 is sent.
Whether there is special key words (such as keyword " day in the voice signal of the detection input of keyword recognition module 110
Cat "), similarly, the present invention is not specifically limited the detection algorithm of keyword, can use those skilled in the art can
Any keyword search algorithm expected, such as the keyword based on fuzzy theory know algorithm.
When keyword recognition module 110 detects keyword, then to the transmission of the wireless communication module 111 of user terminal 100
One trigger signal, triggering wireless communication module 111 start, meanwhile, voice signal is sent to nothing by keyword recognition module 110
Line communication module 111.
Wireless communication module, for the voice signal with keyword to be sent to remote data center, and for connecing
Receive the command signal that remote data center is sent.
It is carried out wireless communication after the starting of wireless communication module 111 with the wireless communication module 202 of remote data center 200
Voice signal, is sent to the wireless communication module 202 of remote data center 200, remotely by (such as bluetooth connection, wifi connection)
The wireless communication module 202 of data center 200 receive voice signal be converted to digital signal be sent to data processor 201 into
The further keyword recognition of row.Data processor 201 is after to keyword recognition, if detecting, there are also specific in voice signal
Keyword, then send a command signal to user terminal, and user terminal executes dependent instruction according to command signal.Citing comes
It says, when keyword recognition module 110 detects in voice signal there is keyword " day cat ", and data processor 201 is detected
Keyword " electric appliance ", then remote data center sends electric appliance shopping in an opening day cat store APP to user terminal (mobile phone)
The instruction of the page, user terminal is according to instruction execution relevant action.
A kind of audio recognition method for realizing low-power consumption standby of the present invention is illustrated below, as shown in Figure 2 the present invention
A kind of flow diagram of audio recognition method that realizing low-power consumption standby, a kind of speech recognition for realizing low-power consumption standby of the present invention
Method includes following method and step:
Step S101, infrared signal is acquired, judge whether there is human body into figure or removes or rest on area-of-interest.
The infrared signal of infrared detection module acquisition human body radiation judges whether there is human body by handling infrared signal
Into or move out area-of-interest.
Infrared detection module includes but is not limited to pyroelectric infrared sensor, thermopile infrared sensor, the first digital-to-analogue turn
Parallel operation and PIR signal processing unit, infrared detection module handle infrared signal by the following method.
Pyroelectric infrared sensor acquires the infrared signal of human body radiation in ambient enviroment, and infrared signal is converted to telecommunications
Number, after the first digital analog converter is converted to digital signal, it is input to infrared signal processing unit.
Infrared signal processing unit judges whether the digital signal of input changes, and when a change, then judgement has
Human body enters or moves out area-of-interest.
Infrared signal processing unit judges whether the digital signal of input is more than threshold value, and when a threshold is exceeded, then judgement has
Human body rests on area-of-interest.
When judging that someone enters or move out or rest on area-of-interest, infrared signal processing unit is to speech detection
Module sends a trigger signal, and triggering speech detection module opens work.The present invention in the standby state, infrared detection module
Always in running order, constantly acquire infrared signal.
Step S102, triggering speech detection module is opened, and detection ambient enviroment whether there is voice signal.
When having human body to enter or move out or rest on area-of-interest, infrared signal processing unit is to speech detection
Module sends a trigger signal, and triggering speech detection module opens work, and speech detection module starts to detect in ambient enviroment
With the presence or absence of voice signal.
Speech detection module includes microphone array, the second digital analog converter and Speech processing unit, ambient enviroment
The detection of middle voice signal is handled by the following method.
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue
After converter is converted to digital signal, it is input to Speech processing unit.
Speech processing unit carries out noise reduction process, number letter of the detection by noise reduction process to the digital signal of input
It whether there is voice signal in number.
When detecting that there are voice signals in ambient enviroment, then pass through Speech processing unit to keyword recognition module
A trigger signal is sent, triggering keyword recognition module is started to work.When being not detected in ambient enviroment there are voice signal,
Then speech detection module is closed, to reduce power consumption.
Step S103, keyword recognition module is triggered, judges whether there is keyword in voice signal.
When detecting that there are voice signals in ambient enviroment, then start to judge in the voice signal with the presence or absence of key
Word.
If there are keywords in voice signal, a triggering letter is sent to the wireless communication module 111 of user terminal 100
Number, triggering wireless communication module 111 starts, by transmitting voice signal to remote data center processing.
When shutdown word is not present in voice signal, then keyword recognition module is closed, and close wireless communication module.
Step S104, transmitting voice signal to remote data center is handled.
If there are keywords in voice signal, by transmitting voice signal to remote data center processing.In teledata
The wireless communication module of the heart, which receives voice signal and is converted to digital signal and is sent to data processor, carries out further keyword
Identification, judges whether voice signal further has specific keyword.
Step 105, remote data center return instruction signal.
After remote data center is by handling voice signal, return instruction signal, when the number of remote data center
Keyword is further detected according to processor, then according to further keyword to the return instruction of user terminal.Such as into one
Step has keyword " electric appliance ", then return instruction control user terminal, which is opened, opens electric appliance shopping page in day cat store APP.When
The data processor of remote data center further detects and keyword is not detected, then is detected according to keyword search module
Keyword return instruction signal.Such as return instruction control user terminal is opened and opens day cat store APP.
In the present invention in speech recognition process, each identification module is opened step by step, is only opened in the standby state infrared
Detecting module can greatly reduce the power consumption of system.
The present invention shown in table 1 in the standby state with the power consumption under different language identification module working condition.
| Power consumption 1 | Power consumption 2 | Power consumption 3 | Power consumption 4 | |
| Infrared detection module | It opens | It opens | It opens | It opens |
| Speech detection module | It closes | It opens | It opens | It opens |
| Keyword recognition module | It closes | It closes | It opens | It closes |
| Wireless communication module | It closes | It closes | It closes | It closes |
Aobvious as shown in table 1, from power consumption 1 to mode 4, power consumption is successively increased.Under lowest power consumption 1, infrared acquisition is only opened
Module.Only when infrared detection module detect area-of-interest have event it is anti-raw when, i.e., someone pass in and out area-of-interest or
In this regional activity, it can just enter power consumption 2.Speech detection module can be opened under power consumption mode 2, do not detecting audio-frequency information
When input, also can language identification module continue for some time after close, return back to power consumption 1 later.Speech detection module detects
Voice input then enters power consumption 3.The lower keyword identification module of power consumption 3 carries out keyword recognition, if not identifying effective pass
Key word, then returning back to power consumption 2.If there is keyword recognition goes out, then entering power consumption 4.All sound restricting the numbers under power consumption mode 4
Remote data center is given by transmission module, remote data center carries out the identification of further keyword, according to data processing
As a result to user terminal return instruction.
The present invention be a kind of audio recognition method for realizing low-power consumption standby and system mainly to solve existing system power consumption big
The problem of, normally open is in by infrared detection module, acquires the infrared signal of human body radiation, makes speech detection module, close
Key word modules and wireless communication module are in close state, when infrared detection module detects in area-of-interest someone's activity,
Speech recognition is just opened, opens speech detection and wireless communication step by step.Since the power consumption of infrared acquisition is well below audio processing
Power consumption, the stand-by power consumption of the smart machine using speech recognition can be significantly reduced.
The present invention opens speech detection step by step, the power consumption of system is effectively reduced by the generation for multiple affair.
In conjunction with the explanation and practice of the invention disclosed here, the other embodiment of the present invention is for those skilled in the art
It all will be readily apparent and understand.Illustrate and embodiment is regarded only as being exemplary, true scope of the invention and purport are equal
It is defined in the claims.
Claims (9)
1. a kind of audio recognition method for realizing low-power consumption standby, which is characterized in that the method includes following method and steps:
The infrared signal for acquiring human body radiation judges whether there is human body entrance or moves out and feel emerging by handling infrared signal
Interesting region；
When having human body to enter or moving out or rest on the area-of-interest, starting to detect whether there is in ambient enviroment
Voice signal；
When detecting that there are voice signals in ambient enviroment, then start to judge in the voice signal with the presence or absence of keyword；
If there are keywords in the voice signal, described remote by the transmitting voice signal to remote data center processing
After journey data center is by handling voice signal, return instruction signal.
2. the method according to claim 1, wherein acquiring the infrared letter of human body radiation by infrared detection module
Number, and infrared signal is handled.
3. according to the method described in claim 2, it is characterized in that, the infrared detection module includes but is not limited to that pyroelectricity is red
Outer sensor, thermopile infrared sensor, the first digital analog converter and infrared signal processing unit, the infrared detection module pair
Infrared signal is handled by the following method:
The infrared letter of human body radiation in the pyroelectric infrared sensor and/or thermopile infrared sensor acquisition ambient enviroment
Number, infrared signal is converted into electric signal, after the first digital analog converter is converted to digital signal, is input to infrared signal processing
Unit,
The infrared signal processing unit judges whether the digital signal of input changes, and when a change, then judgement has
Human body enters or moves out area-of-interest；
The infrared signal processing unit judges whether the digital signal of input is more than threshold value, and when a threshold is exceeded, then judgement has
Human body rests on area-of-interest.
4. the method according to claim 1, wherein detecting the language in ambient enviroment by speech detection module
Sound signal.
5. according to the method described in claim 4, it is characterized in that, the speech detection module includes microphone array, second
Digital analog converter and Speech processing unit, the detection of voice signal is handled by the following method in ambient enviroment:
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue conversion
After device is converted to digital signal, it is input to Speech processing unit；
Speech processing unit carries out noise reduction process to the digital signal of input, detects in the digital signal Jing Guo noise reduction process
With the presence or absence of voice signal.
6. the method according to claim 1, wherein judging the pass in voice signal by keyword recognition module
Key word.
7. a kind of speech recognition system for realizing low-power consumption standby, which is characterized in that the system comprises remote data center and
User terminal, wherein the user terminal includes:
Infrared detection module judges that human body enters or move out or rest on sense for acquiring the infrared signal of human body radiation
Interest region；
Speech detection module, for detecting ambient enviroment with the presence or absence of voice signal；
Keyword recognition module, for detecting the voice signal detected in speech detection module with the presence or absence of keyword；
Wireless communication module, it is remote for the voice signal with keyword to be sent to remote data center, and for receiving
The command signal that journey data center sends.
8. system according to claim 7, which is characterized in that the infrared detection module includes but is not limited to that pyroelectricity is red
Outer sensor, thermopile infrared sensor, the first digital analog converter and infrared signal processing unit, the infrared detection module pair
Infrared signal is handled by the following method:
The infrared letter of human body radiation in the pyroelectric infrared sensor and/or thermopile infrared sensor acquisition ambient enviroment
Number, infrared signal is converted into electric signal, after the first digital analog converter is converted to digital signal, is input to infrared signal processing
Unit,
The infrared signal processing unit judges whether the digital signal of input changes, and when a change, then judgement has
Human body enters or moves out area-of-interest；
The infrared signal processing unit judges whether the digital signal of input is more than threshold value, and when a threshold is exceeded, then judgement has
Human body rests on area-of-interest.
9. system according to claim 7, which is characterized in that the speech detection module includes microphone array, second
Digital analog converter and Speech processing unit, the detection of voice signal is handled by the following method in ambient enviroment:
Microphone array acquires the audio-frequency information in ambient enviroment, audio-frequency information is converted to electric signal, through the second digital-to-analogue conversion
After device is converted to digital signal, it is input to Speech processing unit；
Speech processing unit carries out noise reduction process to the digital signal of input, detects in the digital signal Jing Guo noise reduction process
With the presence or absence of voice signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810637441.0A CN109003604A (en) | 2018-06-20 | 2018-06-20 | A kind of audio recognition method that realizing low-power consumption standby and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810637441.0A CN109003604A (en) | 2018-06-20 | 2018-06-20 | A kind of audio recognition method that realizing low-power consumption standby and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109003604A true CN109003604A (en) | 2018-12-14 |
Family
ID=64601169
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810637441.0A Pending CN109003604A (en) | 2018-06-20 | 2018-06-20 | A kind of audio recognition method that realizing low-power consumption standby and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109003604A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381216A (en) * | 2019-07-31 | 2019-10-25 | 深圳市小魔信息技术有限公司 | A kind of mobile phone charging data line and its awakening method with arousal function |
| CN110933345A (en) * | 2019-11-26 | 2020-03-27 | 深圳创维－Rgb电子有限公司 | Method for reducing television standby power consumption, television and storage medium |
| CN112153279A (en) * | 2020-08-20 | 2020-12-29 | 瑞芯微电子股份有限公司 | Intelligent device false wake-up filtering method and system |
| CN112252855A (en) * | 2020-10-27 | 2021-01-22 | 广东科徕尼智能科技有限公司 | Remote monitoring intelligent lock and remote monitoring intelligent lock system |
| CN112259128A (en) * | 2020-10-21 | 2021-01-22 | 恒玄科技(上海)股份有限公司 | Audio device and voice recognition method |
| CN112735401A (en) * | 2020-12-11 | 2021-04-30 | 广州朗国电子科技有限公司 | Voice recognition detection method and device based on PIR sensor and all-in-one machine |
| CN113009936A (en) * | 2019-12-20 | 2021-06-22 | 杭州乐秀电子科技有限公司 | Positioning system and positioning control method of fan heater |
| CN113495489A (en) * | 2020-04-07 | 2021-10-12 | 深圳爱根斯通科技有限公司 | Automatic configuration method and device, electronic equipment and storage medium |
| CN114363105A (en) * | 2022-01-17 | 2022-04-15 | 深圳市海曼科技股份有限公司 | Intelligent equipment control method based on voice recognition |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1365487A (en) * | 1999-06-24 | 2002-08-21 | 西门子公司 | Voice recognition method and device |
| CN1841249A (en) * | 2005-03-29 | 2006-10-04 | 华为技术有限公司 | Multimedia terminal and state switching method thereof |
| CN101018302A (en) * | 2006-11-23 | 2007-08-15 | 深圳创维－Rgb电子有限公司 | A method for realizing the low power consumption standby |
| CN101907102A (en) * | 2010-07-30 | 2010-12-08 | 中山大学 | Intelligent electric fan and method for realizing intelligent control over electric fan |
| CN104217719A (en) * | 2014-09-03 | 2014-12-17 | 深圳如果技术有限公司 | Triggering processing method |
| CN104408954A (en) * | 2014-12-10 | 2015-03-11 | 天津江湾科技有限公司 | Light-guide fiber intelligent prompt system for pedestrian crosswalk |
| CN104519256A (en) * | 2014-12-26 | 2015-04-15 | 广东光阵光电科技有限公司 | Infrared triggering shooting camera module of VTM machine and shooting method of infrared triggering shooting camera module |
| CN104538030A (en) * | 2014-12-11 | 2015-04-22 | 科大讯飞股份有限公司 | Control system and method for controlling household appliances through voice |
| CN104766608A (en) * | 2014-01-07 | 2015-07-08 | 深圳市中兴微电子技术有限公司 | Voice control method and voice control device |
| CN106782554A (en) * | 2016-12-19 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Voice awakening method and device based on artificial intelligence |
| CN107360327A (en) * | 2017-07-19 | 2017-11-17 | 腾讯科技（深圳）有限公司 | Audio recognition method, device and storage medium |
| CN107403621A (en) * | 2017-08-25 | 2017-11-28 | 深圳市沃特沃德股份有限公司 | Voice Rouser and method |
| CN108156727A (en) * | 2017-08-03 | 2018-06-12 | 南京邮电大学盐城大数据研究院有限公司 | A kind of method that multistage more word sounds of infrared thermal release electric triggering wake up control lamps and lanterns |
-
2018
- 2018-06-20 CN CN201810637441.0A patent/CN109003604A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1365487A (en) * | 1999-06-24 | 2002-08-21 | 西门子公司 | Voice recognition method and device |
| CN1841249A (en) * | 2005-03-29 | 2006-10-04 | 华为技术有限公司 | Multimedia terminal and state switching method thereof |
| CN101018302A (en) * | 2006-11-23 | 2007-08-15 | 深圳创维－Rgb电子有限公司 | A method for realizing the low power consumption standby |
| CN101907102A (en) * | 2010-07-30 | 2010-12-08 | 中山大学 | Intelligent electric fan and method for realizing intelligent control over electric fan |
| CN104766608A (en) * | 2014-01-07 | 2015-07-08 | 深圳市中兴微电子技术有限公司 | Voice control method and voice control device |
| CN104217719A (en) * | 2014-09-03 | 2014-12-17 | 深圳如果技术有限公司 | Triggering processing method |
| CN104408954A (en) * | 2014-12-10 | 2015-03-11 | 天津江湾科技有限公司 | Light-guide fiber intelligent prompt system for pedestrian crosswalk |
| CN104538030A (en) * | 2014-12-11 | 2015-04-22 | 科大讯飞股份有限公司 | Control system and method for controlling household appliances through voice |
| CN104519256A (en) * | 2014-12-26 | 2015-04-15 | 广东光阵光电科技有限公司 | Infrared triggering shooting camera module of VTM machine and shooting method of infrared triggering shooting camera module |
| CN106782554A (en) * | 2016-12-19 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Voice awakening method and device based on artificial intelligence |
| CN107360327A (en) * | 2017-07-19 | 2017-11-17 | 腾讯科技（深圳）有限公司 | Audio recognition method, device and storage medium |
| CN108156727A (en) * | 2017-08-03 | 2018-06-12 | 南京邮电大学盐城大数据研究院有限公司 | A kind of method that multistage more word sounds of infrared thermal release electric triggering wake up control lamps and lanterns |
| CN107403621A (en) * | 2017-08-25 | 2017-11-28 | 深圳市沃特沃德股份有限公司 | Voice Rouser and method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381216A (en) * | 2019-07-31 | 2019-10-25 | 深圳市小魔信息技术有限公司 | A kind of mobile phone charging data line and its awakening method with arousal function |
| CN110381216B (en) * | 2019-07-31 | 2024-04-30 | 深圳市小魔信息技术有限公司 | Mobile phone charging data line with awakening function |
| CN110933345A (en) * | 2019-11-26 | 2020-03-27 | 深圳创维－Rgb电子有限公司 | Method for reducing television standby power consumption, television and storage medium |
| CN110933345B (en) * | 2019-11-26 | 2021-11-02 | 深圳创维－Rgb电子有限公司 | Method for reducing television standby power consumption, television and storage medium |
| CN113009936A (en) * | 2019-12-20 | 2021-06-22 | 杭州乐秀电子科技有限公司 | Positioning system and positioning control method of fan heater |
| CN113495489A (en) * | 2020-04-07 | 2021-10-12 | 深圳爱根斯通科技有限公司 | Automatic configuration method and device, electronic equipment and storage medium |
| CN112153279A (en) * | 2020-08-20 | 2020-12-29 | 瑞芯微电子股份有限公司 | Intelligent device false wake-up filtering method and system |
| CN112259128A (en) * | 2020-10-21 | 2021-01-22 | 恒玄科技(上海)股份有限公司 | Audio device and voice recognition method |
| CN112259128B (en) * | 2020-10-21 | 2023-07-28 | 恒玄科技(上海)股份有限公司 | Audio device and voice recognition method |
| CN112252855A (en) * | 2020-10-27 | 2021-01-22 | 广东科徕尼智能科技有限公司 | Remote monitoring intelligent lock and remote monitoring intelligent lock system |
| CN112735401A (en) * | 2020-12-11 | 2021-04-30 | 广州朗国电子科技有限公司 | Voice recognition detection method and device based on PIR sensor and all-in-one machine |
| CN114363105A (en) * | 2022-01-17 | 2022-04-15 | 深圳市海曼科技股份有限公司 | Intelligent equipment control method based on voice recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109003604A (en) | A kind of audio recognition method that realizing low-power consumption standby and system | |
| US11996092B1 (en) | Noise cancellation for open microphone mode | |
| CN111223497B (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| US10721661B2 (en) | Wireless device connection handover | |
| US10485049B1 (en) | Wireless device connection handover | |
| CN105704298A (en) | Voice wakeup detecting device and method | |
| KR20190022109A (en) | Method for activating voice recognition servive and electronic device for the same | |
| US11605372B2 (en) | Time-based frequency tuning of analog-to-information feature extraction | |
| CN105912092A (en) | Voice waking up method and voice recognition device in man-machine interaction | |
| CN105869655A (en) | Audio device and method for voice detection | |
| CN107358783A (en) | A kind of long distance monitoring method and device | |
| CN106249614A (en) | Intelligent terminal, intelligent domestic system, audio recognition method and ordering method | |
| CN105700660A (en) | Electronic Device Comprising a Wake Up Module Distinct From a Core Domain | |
| CN105699936B (en) | Intelligent home indoor positioning method | |
| DE112015004522T5 (en) | Acoustic device with low power consumption and method of operation | |
| CN103106717A (en) | Intelligent warehouse voice control doorkeeper system based on voiceprint recognition and identity authentication method thereof | |
| US12014732B2 (en) | Energy efficient custom deep learning circuits for always-on embedded applications | |
| CN111862524B (en) | Monitoring alarm method and device based on intelligent home system | |
| CN110322596A (en) | Boot method of controlling switch and system based on position identification and speech recognition | |
| CN108810280A (en) | Processing method, device, storage medium and the electronic equipment of voice collecting frequency | |
| CN108597164A (en) | A kind of theft preventing method, device, terminal and computer-readable medium | |
| CN106887120A (en) | Electronic equipment based on user's identification is gone out system for prompting | |
| CN206057845U (en) | Intelligent terminal, intelligent domestic system | |
| CN106971715A (en) | A kind of speech recognition equipment applied to robot | |
| CN107656923A (en) | Voice translation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 201306 room 904, No. 800, Huanhu West 2nd Road, Lingang New Area, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai Applicant after: Hengxuan Technology (Shanghai) Co., Ltd Address before: 200135 Shanghai 647 free trade pilot area, 171 Pudong New Area Road, 1 buildings, 6 rooms Applicant before: Heng Xuan Technology (Shanghai) Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181214 |
|
| RJ01 | Rejection of invention patent application after publication |