CN107274901A - A kind of far field voice interaction device - Google Patents
A kind of far field voice interaction device Download PDFInfo
- Publication number
- CN107274901A CN107274901A CN201710680172.1A CN201710680172A CN107274901A CN 107274901 A CN107274901 A CN 107274901A CN 201710680172 A CN201710680172 A CN 201710680172A CN 107274901 A CN107274901 A CN 107274901A
- Authority
- CN
- China
- Prior art keywords
- voice
- memory
- far field
- module
- interaction device
- 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.)
- Withdrawn
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 25
- 230000015654 memory Effects 0.000 claims abstract description 30
- 230000004913 activation Effects 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 12
- 230000002093 peripheral effect Effects 0.000 claims abstract description 9
- 230000003321 amplification Effects 0.000 claims abstract description 8
- 238000003199 nucleic acid amplification method Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000005055 memory storage Effects 0.000 claims abstract description 6
- 241000209140 Triticum Species 0.000 claims description 5
- 235000021307 Triticum Nutrition 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 5
- 244000301850 Cupressus sempervirens Species 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 9
- 230000010354 integration Effects 0.000 abstract description 5
- 230000008030 elimination Effects 0.000 abstract description 4
- 238000003379 elimination reaction Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 239000000047 product Substances 0.000 description 4
- 241000218691 Cupressaceae Species 0.000 description 3
- 230000004807 localization Effects 0.000 description 3
- 239000004568 cement Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000013589 supplement Substances 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention provides a kind of far field voice interaction device, including voice pickup model, front end amplification module, processor, first memory, second memory, wireless communication module, indicator lamp and power module；Voice signal in voice pickup model environment-identification；The voice signal that front end amplification module is picked up to voice pickup model is filtered and enhanced processing；The bottoms such as first memory storaged voice algorithmic code are instructed；The upper strata instructions such as the configuration information and activation word of the peripheral intelligent hardware devices of second memory storage；The instruction of computing device first memory and second memory；The peripheral intelligent hardware devices of wireless communication module connection；Indicator lamp is LED light emitting diodes；Power module provides power supply for each part mentioned above.The present invention uses high integration and high performance-price ratio integrated design, with functions such as comprehensive wake-up, sound source direction finding, orientation pickup, noise suppressed, reverberation elimination, echo cancelltion, far field speech recognitions.
Description
Technical field
The present invention relates to field of artificial intelligence, more particularly to a kind of far field voice interaction device.
Background technology
Intelligent hardware is based on platform bottom software and hardware, interconnected with intelligent sensing, man-machine interaction, new display and
Big data processing etc. generation information technology be characterized, newly to design, new material hardware as carrier novel intelligent terminal product
And service.With the continuous maturation in technology upgrading, association base very well equipped and application service market, the product shape of Intelligent hardware
State extends to the wearable, smart home of intelligence, intelligent vehicle-carried, medical treatment ＆ health, intelligent Unmanned Systems etc. from smart mobile phone, as letter
The joint that breath technology is merged with conventional industries.
At present, Intelligent hardware product is denounced under many scenes because interactive voice experience is deep not as people's will, studies carefully it
Reason is mainly the change of interactive voice user's scene, when user is switched to similar intelligent sound box from the Siri of mobile phone,
The environment that actually microphone faces just change, this difference whispered and loudly shouted just as two people completely.Voice
Interaction is limited to the multiple complicated factors such as background noise, other people acoustic jamming, echo and reverberation, and distance is recognized caused by entering
Closely, the low obvious pain spot of discrimination.
The content of the invention
(1) technical problem solved
In order to solve the above-mentioned technical problem, the invention provides a kind of far field voice interaction device, using high integration and
High performance-price ratio integrated design, is supported with comprehensive wake-up, sound source direction finding, orientation pickup, noise suppressed, reverberation elimination, echo
Disappear, the function such as far field speech recognition.
(2) technical scheme
A kind of far field voice interaction device, including voice pickup model, front end amplification module, processor, first memory,
Second memory, wireless communication module, indicator lamp and power module；
Voice signal in the voice pickup model environment-identification；
The voice signal that the front end amplification module is picked up to the voice pickup model is filtered and enhanced processing；
The bottoms such as the first memory storaged voice algorithmic code are instructed, and user can not be changed bottom instruction；
The upper strata instructions, user couple such as the configuration information and activation word of the peripheral intelligent hardware devices of second memory storage
The upper strata instruction can modify；
The instruction of first memory and the second memory described in the computing device；
The peripheral intelligent hardware devices of wireless communication module connection；
The indicator lamp is LED light emitting diodes；
The power module provides power supply for each part mentioned above.
Further, the voice pickup model is microphone array, and the microphone array number of columns is 6.
Further, the annular spread that it is diameter 8cm that the microphone array, which is listed on pcb board,.
Further, the first memory is DDR3, and the phonetic algorithm of the first memory storage includes language
Sound activation detection, voice wake-up, echo cancellor, low signal-to-noise ratio and reverberation.
Further, the second memory is eMMC.
Further, the processor is Cypress CYW43438.
Further, the wireless communication module be infrared module, bluetooth module or WIFI module in one kind or
Person combines.
(3) beneficial effect
The invention provides a kind of far field voice interaction device, using high integration and high performance-price ratio integrated design, tool
There are the functions such as comprehensive wake-up, sound source direction finding, orientation pickup, noise suppressed, reverberation elimination, echo cancelltion, far field speech recognition,
It is widely used in the intelligent hardware devices such as intelligent sound box, DOT, TV box.
Brief description of the drawings
Fig. 1 is a kind of far field voice interaction device system block diagram involved in the present invention.
Fig. 2 is a kind of far field voice interaction device PCB distribution schematic diagrams involved in the present invention.
Fig. 3 is a kind of far field voice interaction device phonetic algorithm flow chart involved in the present invention.
Embodiment
Embodiment involved in the present invention is described in further details below in conjunction with the accompanying drawings.
Embodiment 1：
As shown in figure 1, a kind of far field voice interaction device, including voice pickup model, front end amplification module, processor,
First memory, second memory, wireless communication module, indicator lamp and power module；
Voice signal in voice pickup model environment-identification；
The voice signal that front end amplification module is picked up to voice pickup model is filtered and enhanced processing；
The bottoms such as first memory storaged voice algorithmic code are instructed, and user can not be changed bottom instruction；
The upper strata instructions such as the configuration information and activation word of the peripheral intelligent hardware devices of second memory storage, user is to upper strata
Instruction can modify；
The instruction of computing device first memory and second memory；
The peripheral intelligent hardware devices of wireless communication module connection；
Indicator lamp is LED light emitting diodes；
Power module provides power supply for each part mentioned above.
Embodiment 2：
With reference to Fig. 2 and Fig. 3, illustrate device operation principle.
Voice pickup model is microphone array, and microphone array is to utilize certain amount, the acoustics of certain space configuration
Sensor group is into the system sampled and handled for the spatial character to sound field.Linearly, annular, spherical microphone array
Too big difference is had no in principle, only because steric configuration is different, causes their distinguishable spatial dimensions also different.Than
Such as, in auditory localization, linear array only has one-dimension information, can only differentiate 180 degree；Annular array is planar array, there is bidimensional
Information, can differentiate 360 degree；Ball array is stereoscopic three-dimensional space array, there is three-dimensional information, can distinguish 360 degree azimuth and
The 180 degree angle of pitch.Secondly the number of microphone is more, and the positioning precision to speaker is higher, but the difference body of positioning precision
In the distance of present interaction distance, if interaction distance is not far, the locating effect difference of 5 wheats and 8 wheats is not very big.This
Outside, microphone number is more, and the space that wave beam can be distinguished is finer, and the pickup quality under noisy environment is higher, but one
As under indoor quiet environment, the discrimination difference of 5 wheats and 8 wheats is not very big.Microphone number is more simultaneously, and cost is also got over
It is high.
Comprehensive consideration, microphone array number of columns chooses 6, and is designed to that a diameter of 8cm annular is divided on pcb board
Cloth, has the high position precision and high pickup quality of 360 degrees omnidirection concurrently, while so that development cost will not be very high, being conducive to dress
The Miniaturization Design put.
First memory selects DDR3, and belonging to the memory articles of SDRAM families, there is provided the operation higher compared to DDR2
Efficiency and lower voltage, power consumption and caloric value are smaller.
The phonetic algorithm of DDR3 storages includes voice activation detection, voice wake-up, echo cancellor, low signal-to-noise ratio and reverberation.
Voice activation detection is exactly when to judge when to have voice in environment without voice, follow-up voice letter
Number processing is carried out in the efficient voice fragment for intercepting out in this step, can so be significantly reduced amount of calculation, together
When can also reduce situations such as noise is misidentified.
Voice wake-up is the main triggering mode of man-machine interaction, and work is carried out after voice activation detects voice signal
Make, judge whether comprising the activation word prestored in voice signal, if comprising, follow-up voice signal is continued to recognize,
Otherwise follow-up voice is without processing.
Echo cancellor is a noun in full-duplex communication, i.e., can be with pickup while playing.The difficulty of echo cancellor
Point is that it will have a balance and compromise between the acoustics of intelligent hardware devices such as intelligent sound box.
Low signal-to-noise ratio and reverberation.Sometimes ambient noise is very big in environment, such as family drives TV or inside automobile
Etc., so that voice quality is deteriorated, i.e., signal to noise ratio is reduced.The reverberation that wall reflection in other home environment is formed is to language
Sound quality also has very important influence.In order to strengthen voice signal, the signal to noise ratio of voice is improved, passes through depth nerve
Network carries out regression fit modeling to the complex relationship between noisy speech and clean speech, and it is minimum that this method is based on log power spectrum
Mean-square error criteria, multiframe extension has very great help to lifting speech enhan-cement quality and continuity.
Second memory selects eMMC memories, and it carries multimedia card interface, flash memory device and master controller,
It is all to be conducive to equipment miniaturization all in a small-sized BGA package, while interface rate is up to 52M bytes per second.
Processor selects Cypress CYW43438 model chips, integrated chip IEEE802.11a/b/g/n/ac
WLAN and bluetooth, using the integrated design of high integration and high performance-price ratio, can be achieved the Internet of product design of small size.
Wireless communication module is one kind in infrared module, bluetooth module or WIFI module or combination.Given this
Processor has been integrated with bluetooth and WIFI module in embodiment, only need to supplement infrared module.
Far field speech recognition is, it is necessary to which software and hardware combining, is on the one hand believed by hardware using annular 6 microphone array and filtering
Number amplifying circuit, by auditory localization and Adaptive beamformer speech enhan-cement, far field pickup is completed in hardware end, and preliminary complete
Made an uproar into filter, it is right on the other hand by the phonetic algorithm code stored in Cypress CYW43438 processor running memories DDR3
Voice signal carries out the processing of voice activation detection, voice wake-up, echo cancellor, low signal-to-noise ratio and reverberation, from the voice of environment
Extracted in signal and clearly activate word.User connects several peripheries according to individual demand by infrared, bluetooth or WIFI
Intelligent hardware devices and the multiple activation words of setting, and configuration information and activation word are stored in eMMC memories.Work as processor
When receiving effectively activation word, LED light flicker, the corresponding peripheral intelligent hardware devices of simultaneous processor control are carried out
Response.
In actual use, the sensitivity of a kind of far field voice interaction device provided by the present invention>-42dBV@
94dB 1KHz, horizontal direction realizes 360 ° of auditory localizations, and positioning precision is ± 10 °, and dynamic noise suppresses>20dB, signal to noise ratio>
65dB, wakes up the reachable 20m of distance, and 3m wake-up rate>96%, 5m wake-up rate>91%；The reachable 5m of identification distance, and
2m discrimination>95%, 5m discrimination>90%, support is arbitrarily interrupted, continuous to wake up, and has fully met general indoor intelligence
Can hardware device arrangement demand.
The invention provides a kind of far field voice interaction device, using high integration and high performance-price ratio integrated design, tool
There are the functions such as comprehensive wake-up, sound source direction finding, orientation pickup, noise suppressed, reverberation elimination, echo cancelltion, far field speech recognition,
It is widely used in the intelligent hardware devices such as intelligent sound box, DOT, TV box.
The above-described embodiments are merely illustrative of preferred embodiments of the present invention, not to the structure of the present invention
Think and scope is defined.On the premise of design concept of the present invention is not departed from, technology of this area ordinary person to the present invention
The all variations and modifications that scheme is made, all should drop into protection scope of the present invention, claimed technology contents of the invention,
All record in detail in the claims.
Claims (7)
1. a kind of far field voice interaction device, it is characterised in that：Including voice pickup model, front end amplification module, processor,
One memory, second memory, wireless communication module, indicator lamp and power module；
Voice signal in the voice pickup model environment-identification；
The voice signal that the front end amplification module is picked up to the voice pickup model is filtered and enhanced processing；
The bottoms such as the first memory storaged voice algorithmic code are instructed, and user can not be changed bottom instruction；
The upper strata instructions such as the configuration information and activation word of the peripheral intelligent hardware devices of second memory storage, user is to described
Upper strata instruction can modify；
The instruction of first memory and the second memory described in the computing device；
The peripheral intelligent hardware devices of wireless communication module connection；
The indicator lamp is LED light emitting diodes；
The power module provides power supply for each part mentioned above.
2. a kind of far field voice interaction device according to claim 1, it is characterised in that：The voice pickup model is wheat
Gram wind array, and the microphone array number of columns is 6.
3. a kind of far field voice interaction device according to claim 2, it is characterised in that：The microphone array is listed in PCB
It is diameter 8cm annular spread on plate.
4. a kind of far field voice interaction device according to claim 1, it is characterised in that：The first memory is
DDR3, the phonetic algorithm of the first memory storage includes voice activation detection, voice wake-up, echo cancellor, low letter
Make an uproar than and reverberation.
5. a kind of far field voice interaction device according to claim 1, it is characterised in that：The second memory is
eMMC。
6. a kind of far field voice interaction device according to claim 1, it is characterised in that：The processor is Cypress
CYW43438。
7. a kind of far field voice interaction device according to claim 1, it is characterised in that：The wireless communication module is red
One kind or combination in outer wire module, bluetooth module or WIFI module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710680172.1A CN107274901A (en) | 2017-08-10 | 2017-08-10 | A kind of far field voice interaction device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710680172.1A CN107274901A (en) | 2017-08-10 | 2017-08-10 | A kind of far field voice interaction device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107274901A true CN107274901A (en) | 2017-10-20 |
Family
ID=60079768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710680172.1A Withdrawn CN107274901A (en) | 2017-08-10 | 2017-08-10 | A kind of far field voice interaction device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107274901A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108122563A (en) * | 2017-12-19 | 2018-06-05 | 北京声智科技有限公司 | Improve voice wake-up rate and the method for correcting DOA |
| CN108228577A (en) * | 2018-01-31 | 2018-06-29 | 北京百度网讯科技有限公司 | Translation on line method, apparatus, equipment and computer-readable medium |
| CN108289267A (en) * | 2018-04-14 | 2018-07-17 | 北京智网时代科技有限公司 | Eliminate echo cancelling device, method, speaker, the voice frequency sender of TV interference |
| CN108335697A (en) * | 2018-01-29 | 2018-07-27 | 北京百度网讯科技有限公司 | Minutes method, apparatus, equipment and computer-readable medium |
| CN108461083A (en) * | 2018-03-23 | 2018-08-28 | 北京小米移动软件有限公司 | Electronic equipment mainboard, audio-frequency processing method, device and electronic equipment |
| CN108538305A (en) * | 2018-04-20 | 2018-09-14 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and computer readable storage medium |
| CN109192219A (en) * | 2018-09-11 | 2019-01-11 | 四川长虹电器股份有限公司 | The method for improving microphone array far field pickup based on keyword |
| CN109474853A (en) * | 2018-11-27 | 2019-03-15 | 深圳Tcl新技术有限公司 | A kind of television set wake-up circuit and the television set with it |
| CN109856593A (en) * | 2018-12-21 | 2019-06-07 | 南京理工大学 | Intelligent miniature array sonic transducer and its direction-finding method towards sound source direction finding |
| CN109935226A (en) * | 2017-12-15 | 2019-06-25 | 上海擎语信息科技有限公司 | A kind of far field speech recognition enhancing system and method based on deep neural network |
| CN113299319A (en) * | 2021-05-25 | 2021-08-24 | 华晨鑫源重庆汽车有限公司 | Voice recognition module and recognition method based on edge AI chip |
-
2017
- 2017-08-10 CN CN201710680172.1A patent/CN107274901A/en not_active Withdrawn
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109935226A (en) * | 2017-12-15 | 2019-06-25 | 上海擎语信息科技有限公司 | A kind of far field speech recognition enhancing system and method based on deep neural network |
| CN108122563A (en) * | 2017-12-19 | 2018-06-05 | 北京声智科技有限公司 | Improve voice wake-up rate and the method for correcting DOA |
| CN108122563B (en) * | 2017-12-19 | 2021-03-30 | 北京声智科技有限公司 | Method for improving voice awakening rate and correcting DOA |
| CN108335697A (en) * | 2018-01-29 | 2018-07-27 | 北京百度网讯科技有限公司 | Minutes method, apparatus, equipment and computer-readable medium |
| CN108228577A (en) * | 2018-01-31 | 2018-06-29 | 北京百度网讯科技有限公司 | Translation on line method, apparatus, equipment and computer-readable medium |
| CN108461083A (en) * | 2018-03-23 | 2018-08-28 | 北京小米移动软件有限公司 | Electronic equipment mainboard, audio-frequency processing method, device and electronic equipment |
| CN108289267A (en) * | 2018-04-14 | 2018-07-17 | 北京智网时代科技有限公司 | Eliminate echo cancelling device, method, speaker, the voice frequency sender of TV interference |
| CN108538305A (en) * | 2018-04-20 | 2018-09-14 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and computer readable storage medium |
| US11074924B2 (en) | 2018-04-20 | 2021-07-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Speech recognition method, device, apparatus and computer-readable storage medium |
| CN109192219A (en) * | 2018-09-11 | 2019-01-11 | 四川长虹电器股份有限公司 | The method for improving microphone array far field pickup based on keyword |
| CN109192219B (en) * | 2018-09-11 | 2021-12-17 | 四川长虹电器股份有限公司 | Method for improving far-field pickup of microphone array based on keywords |
| CN109474853A (en) * | 2018-11-27 | 2019-03-15 | 深圳Tcl新技术有限公司 | A kind of television set wake-up circuit and the television set with it |
| CN109474853B (en) * | 2018-11-27 | 2021-11-09 | 深圳Tcl新技术有限公司 | Television wake-up circuit and television with same |
| CN109856593A (en) * | 2018-12-21 | 2019-06-07 | 南京理工大学 | Intelligent miniature array sonic transducer and its direction-finding method towards sound source direction finding |
| CN109856593B (en) * | 2018-12-21 | 2023-01-03 | 南京理工大学 | Sound source direction-finding-oriented miniature intelligent array type acoustic sensor and direction-finding method thereof |
| CN113299319A (en) * | 2021-05-25 | 2021-08-24 | 华晨鑫源重庆汽车有限公司 | Voice recognition module and recognition method based on edge AI chip |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107274901A (en) | A kind of far field voice interaction device | |
| KR102393364B1 (en) | Method for controlling audio signal and electronic device supporting the same | |
| US11789697B2 (en) | Methods and systems for attending to a presenting user | |
| US11806862B2 (en) | Robots, methods, computer programs, computer-readable media, arrays of microphones and controllers | |
| CN203075421U (en) | Music playing system based on emotion change | |
| KR20180062746A (en) | Lamp device for inputting or outputting voice signals and a method of driving the lamp device | |
| US9620116B2 (en) | Performing automated voice operations based on sensor data reflecting sound vibration conditions and motion conditions | |
| US20110235817A1 (en) | Earphone, electronic system and power-saving method | |
| CN201414156Y (en) | Movable terminal with prompt facility of radiant intensity | |
| US20140286517A1 (en) | Network of speaker lights and wearable devices using intelligent connection managers | |
| CN106782519A (en) | A kind of robot | |
| CN207182906U (en) | A kind of far field voice interaction device | |
| CN108447483A (en) | Speech recognition system | |
| CN109246525A (en) | Headset control method, device and headphone based on gesture | |
| CN109447027A (en) | Fingerprint acquisition device, fingerprint identification method and terminal | |
| CN106325113B (en) | Robot controls engine and system | |
| CN111105792A (en) | Voice interaction processing method and device | |
| CN204145834U (en) | Intelligent lightening device and illuminator | |
| CN206162837U (en) | Civilization behavior detection reminding device | |
| CN108680902A (en) | A kind of sonic location system based on multi-microphone array | |
| CN104536580B (en) | The method and apparatus for detecting electronic equipment posture | |
| CN105957535A (en) | Robot voice signal detecting and identifying system | |
| CN206891912U (en) | A kind of portable air quality detection apparatus | |
| CN208538474U (en) | Speech recognition system | |
| CN104836876A (en) | Air quality sensing suite based on smart phone audio interface |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171020 |
|
| WW01 | Invention patent application withdrawn after publication |