CN109389994A - Identification of sound source method and device for intelligent transportation system - Google Patents
Identification of sound source method and device for intelligent transportation system Download PDFInfo
- Publication number
- CN109389994A CN109389994A CN201811358787.3A CN201811358787A CN109389994A CN 109389994 A CN109389994 A CN 109389994A CN 201811358787 A CN201811358787 A CN 201811358787A CN 109389994 A CN109389994 A CN 109389994A
- Authority
- CN
- China
- Prior art keywords
- signal
- whistle
- frame
- sound
- identification
- 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 32
- 239000000284 extract Substances 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000000926 separation method Methods 0.000 claims abstract description 11
- 238000007664 blowing Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000009432 framing Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 2
- 230000004807 localization Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 abstract description 5
- 238000013499 data model Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000027455 binding Effects 0.000 description 1
- 238000009739 binding Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/84—Detection of presence or absence of voice signals for discriminating voice from noise
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
- G10L25/24—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters the extracted parameters being the cepstrum
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The present invention relates to a kind of identification of sound source method and devices for intelligent transportation system, this method comprises: obtaining the sound-source signal of acoustic array acquisition, and make sub-frame processing to the sound-source signal, so that each frame signal short-term stationarity；The cepstrum of each frame signal is analyzed, and extracts its frequency domain character, obtains the frequency separation of each frame signal；Whether all frames meet trigger condition in the continuous whistle duration of judgement, if so, being whistle signal by all signal identifications in continuous whistle duration using first frame in duration of continuously blowing a whistle as trigger signal start frame；Wherein, the trigger condition is the signal for occurring meeting frequency separation.The present invention can satisfy the demand of real-time and accuracy in intelligent transportation auditory localization practical application, the priori knowledge for counting ambient noise in advance is not needed, without whistle database training data model, it is simple and easy to operate, and accuracy is high, algorithm implementation complexity is low, and can extract whistle signal from a segment signal and carry out subsequent location Calculation.
Description
Technical field
The invention belongs to field of intelligent transportation technology more particularly to a kind of identification of sound source methods for intelligent transportation system
And device.
Background technique
In recent years, with the quickening of internet and field of traffic fusion paces, urban transportation control in China's increasingly tends to intelligence
Energyization, it is information-based；With effective integrations such as information technology, data transfer communications technology, advanced sensors technology and big datas
The foundation of ground traffic control system plays significant role in the construction of smart city.In addition, the increase of car ownership also adds
Big city noise pollution problem, serious noise pollution directly affects the daily work and rest of people and physically and mentally healthy, in order to ensure
The people-oriented comprehensive approach to the management of social problems system of quiet environment and embodiment of the citizen in routine work and life, many cities are numerous and confused
Legislation is not, it is specified that particular time, sensitive area allow to blow a whistle.Intelligently illegal whistle phenomenon is supervised in order to more efficient
Control, whistle control are come into being with illegal whistle capturing system.The system to sound source data received by microphone array into
Row processing, thus the position where orienting sound source, linkage video camera is captured, and is handled by backstage license plate identification software
Obtain the information of vehicles such as license plate and be uploaded to traffic control center, reliably detect out whistle sound be auditory localization algorithm and after
The key point that can continuous processing be realized.
The method that identification whistle signal is commonly used in the whistle positioning system being currently known is generally divided into several classes:
1, short-time energy and short-time zero-crossing rate joint judgement；The end-point detection (VAD) that this method is similar to voice signal is calculated
Method.The algorithm by with ambient noise real time contrast, the threshold value of short-time energy and short-time zero-crossing rate is set by the method for statistics
Carry out triggering judgement.In this method, need to take the no signal section of former frames of every segment signal to make an uproar as the back judged each time, so
And in practical applications, since microphone array receives the limitation of upload data mechanism, the selection of ambient noise is often difficult to boundary
Fixed, this will largely effect on subsequent judgement and signal identification；Furthermore this method needs to count the feature-set threshold of short signal
Value, the experience that the selected needs of appropriate threshold are repeatedly tested.
2, sound pressure level combines judgement with frequency；Such method is to judge to combine with frequency domain by time domain judgement, but this side
Method needs the priori knowledge of ambient noise, counts the sound pressure level of ambient noise first, sets a suitable threshold value then to protect
For card when without whistle situation, system maintains not triggering state；Then by judging signal frequency to signal progress spectrum analysis is received
Whether in whistle frequency separation, two characteristic bindings judge whether signal collected be whistle signal to rate；
3, the recognition methods of machine learning；This method is that a large amount of whistle data of training obtain a model, by being acquired
Signal judges whether the signal is whistle signal with whether the model matches；Such method intelligent, accuracy rate is higher, but
And the priori knowledge of whistle signal is needed, when no whistle database, such method will be not suitable for, and be determined
Whistle data cannot effectively filter out non-whistle data packet.
In view of this, a kind of priori knowledge for not needing whistle signal and ambient noise is needed, without according to repeatedly survey
The threshold value of examination setting characteristic value can reduce the identification of sound source of the complexity of model and the calculation amount of signal processing in big degree
Method.
Summary of the invention
The purpose of the present invention is to provide a kind of identification of sound source method and devices for intelligent transportation system, are based on cepstrum
Analysis method, extracts signal characteristic by short time discrete Fourier transform and is analyzed, and vehicle whistle sound is effectively identified, by sound of blowing a whistle
Sound screens the data source as subsequent auditory localization.
The present invention provides a kind of identification of sound source methods for intelligent transportation system, comprising:
Step 1: the sound-source signal of acoustic array acquisition is obtained, and sub-frame processing is made to the sound-source signal, so that each frame
Signal short-term stationarity；
Step 2: analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains the frequency zones of each frame signal
Between；
Step 3: whether all frames meet trigger condition in the continuous whistle duration of judgement, if so, with duration of continuously blowing a whistle
Interior first frame is trigger signal start frame, is whistle signal by all signal identifications in continuous whistle duration；Wherein, the touching
Clockwork spring part is the signal for occurring meeting frequency separation.
Further, the step 2 includes:
The frequency domain character of each frame signal is extracted based on short time discrete Fourier transform.
Further, this method does not need the priori knowledge for obtaining ambient noise and whistle signal in advance.
The present invention also provides a kind of identification of sound source devices for intelligent transportation system, comprising:
Framing module for obtaining the sound-source signal of acoustic array acquisition, and makees sub-frame processing to the sound-source signal, so that
Each frame signal short-term stationarity；
Analysis module for analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains the frequency of each frame signal
Rate section；
Whether judgment module meets trigger condition for all frames in the duration that judges continuously to blow a whistle, if so, continuously to ring
First frame is trigger signal start frame in flute duration, is whistle signal by all signal identifications in continuous whistle duration；Wherein,
The trigger condition is the signal for occurring meeting frequency separation.
Further, the analysis module extracts the frequency domain character of each frame signal based on short time discrete Fourier transform.
Further, which does not need the priori knowledge for obtaining ambient noise and whistle signal in advance.
Compared with prior art the beneficial effects of the present invention are:
The demand that can satisfy real-time and accuracy in intelligent transportation auditory localization practical application does not need to count in advance
The priori knowledge of ambient noise, it is simple and easy to operate without whistle database training data model, and accuracy is high, algorithm is real
Existing complexity is low, and can extract whistle signal from a segment signal and carry out subsequent location Calculation.
Detailed description of the invention
Fig. 1 is flow chart of the present invention for the identification of sound source method of intelligent transportation system；
Fig. 2 is structural block diagram of the present invention for the identification of sound source device of intelligent transportation system；
Fig. 3 is the whistle signal recognition effect figure using the present invention for the identification of sound source method of intelligent transportation system.
Specific embodiment
The present invention is described in detail for each embodiment shown in reference to the accompanying drawing, but it should be stated that, these
Embodiment is not limitation of the present invention, those of ordinary skill in the art according to these embodiments made by function, method,
Or equivalent transformation or substitution in structure, all belong to the scope of protection of the present invention within.
Join shown in Fig. 1, present embodiments provide a kind of identification of sound source method (algorithm) for intelligent transportation system, wraps
It includes:
Step S1: the sound-source signal of acoustic array acquisition is obtained, and sub-frame processing is made to the sound-source signal, so that each frame
Signal short-term stationarity；
Step S2: analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains the frequency zones of each frame signal
Between；
Step S3: whether all frames meet trigger condition in the continuous whistle duration of judgement, if so, with duration of continuously blowing a whistle
Interior first frame is trigger signal start frame, is whistle signal by all signal identifications in continuous whistle duration；Wherein, the touching
Clockwork spring part is the signal for occurring meeting frequency separation.
For example, a length of t when customized continuous whistle, judges signal for trigger signal, judge whether all frames are full in continuous t
Sufficient trigger condition, if meeting condition, using first frame in t as trigger signal start frame, at least all signals of t time will be identified
For whistle signal, into the calculating of subsequent location algorithm.
By the identification of sound source method, real-time and accuracy in intelligent transportation auditory localization practical application can satisfy
Demand does not need the priori knowledge for counting ambient noise in advance, without whistle database training data model, easy easily behaviour
Make, and accuracy is high, algorithm implementation complexity is low, and can extract whistle signal from a segment signal and carry out subsequent location Calculation.
In the present embodiment, step S2 includes:
The frequency domain character of each frame signal is extracted based on short time discrete Fourier transform.
In the present embodiment, this method does not need the priori knowledge for obtaining ambient noise and whistle signal in advance.
Join shown in Fig. 2, the present embodiment additionally provides a kind of identification of sound source device for intelligent transportation system, comprising:
Framing module 10 for obtaining the sound-source signal of acoustic array acquisition, and makees sub-frame processing to the sound-source signal, with
Make each frame signal short-term stationarity；
Analysis module 20 for analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains each frame signal
Frequency separation；
Whether judgment module 30 meets trigger condition for all frames in the duration that judges continuously to blow a whistle, if so, with continuous
First frame is trigger signal start frame in duration of blowing a whistle, and is whistle signal by all signal identifications in continuous whistle duration；Its
In, the trigger condition is the signal for occurring meeting frequency separation.
Continuous whistle duration in the present embodiment hands over rule to require to be set according to different application and different cities, than
Such as some city requirements, duration of blowing a whistle, which is greater than, can be regarded as malice whistle for 1 second, will carry out punishment on contravention of regulation to it, less than 1 second, not make
Processing.
For example, a length of t when customized continuous whistle, judges signal for trigger signal, judge whether all frames are full in continuous t
Sufficient trigger condition, if meeting condition, using first frame in t as trigger signal start frame, at least all signals of t time will be identified
For whistle signal, into the calculating of subsequent location algorithm.
By the identification of sound source device, real-time and accuracy in intelligent transportation auditory localization practical application can satisfy
Demand does not need the priori knowledge for counting ambient noise in advance, without whistle database training data model, easy easily behaviour
Make, and accuracy is high, algorithm implementation complexity is low, and can extract whistle signal from a segment signal and carry out subsequent location Calculation.
In the present embodiment, analysis module 20 extracts the frequency domain character of each frame signal based on short time discrete Fourier transform.
In the present embodiment, which does not need the priori knowledge for obtaining ambient noise and whistle signal in advance.
It the use of data is in whistle detection device to verify the validity and accuracy that this algorithm is identified in sound source endpoint
Erecting bed acquires the mixed signal of whistle sound and ambient noise.This experiment with 16ms be a frame carry out to whole segment signal into
Row framing in short-term, recognition result are as shown in Figure 3.
It is verified by real data, which can effectively identify the whistle signal in mixed signal, and have good
Anti-interference.
The series of detailed descriptions listed above only for feasible embodiment of the invention specifically
Protection scope bright, that they are not intended to limit the invention, it is all without departing from equivalent implementations made by technical spirit of the present invention
Or change should all be included in the protection scope of the present invention.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.
Claims (6)
1. a kind of identification of sound source method for intelligent transportation system characterized by comprising
Step 1: the sound-source signal of acoustic array acquisition is obtained, and sub-frame processing is made to the sound-source signal, so that each frame signal
Short-term stationarity；
Step 2: analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains the frequency separation of each frame signal；
Step 3: whether all frames meet trigger condition in the continuous whistle duration of judgement, if so, in duration of continuously blowing a whistle the
One frame is trigger signal start frame, is whistle signal by all signal identifications in continuous whistle duration；Wherein, the triggering item
Part is the signal for occurring meeting frequency separation.
2. identification of sound source method according to claim 1, which is characterized in that the step 2 includes:
The frequency domain character of each frame signal is extracted based on short time discrete Fourier transform.
3. identification of sound source method according to claim 1, which is characterized in that this method does not need to obtain ambient noise in advance
With the priori knowledge of whistle signal.
4. a kind of identification of sound source device for intelligent transportation system characterized by comprising
Framing module for obtaining the sound-source signal of acoustic array acquisition, and makees sub-frame processing to the sound-source signal, so that each
Frame signal short-term stationarity；
Analysis module for analyzing the cepstrum of each frame signal, and extracts its frequency domain character, obtains the frequency zones of each frame signal
Between；
Whether judgment module meets trigger condition for all frames in the duration that judges continuously to blow a whistle, if so, when continuously blowing a whistle
First frame is trigger signal start frame in long, is whistle signal by all signal identifications in continuous whistle duration；Wherein, described
Trigger condition is the signal for occurring meeting frequency separation.
5. identification of sound source device according to claim 4, which is characterized in that the analysis module is become based on Short-time Fourier
Change the frequency domain character for extracting each frame signal.
6. identification of sound source device according to claim 4, which is characterized in that the device does not need to obtain ambient noise in advance
With the priori knowledge of whistle signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811358787.3A CN109389994A (en) | 2018-11-15 | 2018-11-15 | Identification of sound source method and device for intelligent transportation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811358787.3A CN109389994A (en) | 2018-11-15 | 2018-11-15 | Identification of sound source method and device for intelligent transportation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109389994A true CN109389994A (en) | 2019-02-26 |
Family
ID=65428744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811358787.3A Pending CN109389994A (en) | 2018-11-15 | 2018-11-15 | Identification of sound source method and device for intelligent transportation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109389994A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647949A (en) * | 2019-10-21 | 2020-01-03 | 中国计量大学 | Calibration method of automobile whistling snapshot device based on deep learning |
| CN112992176A (en) * | 2020-09-30 | 2021-06-18 | 北京海兰信数据科技股份有限公司 | Ship acoustic signal identification method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104781862A (en) * | 2012-10-12 | 2015-07-15 | 塔塔咨询服务有限公司 | Real-time traffic detection |
| CN104794894A (en) * | 2015-01-29 | 2015-07-22 | 青岛智能产业技术研究院 | Automobile whistle noise monitoring device, system and method |
| CN104916289A (en) * | 2015-06-12 | 2015-09-16 | 哈尔滨工业大学 | Quick acoustic event detection method under vehicle-driving noise environment |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106875678A (en) * | 2017-01-23 | 2017-06-20 | 上海良相智能化工程有限公司 | A kind of vehicle whistle law enforcement evidence-obtaining system |
| CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
| CN108627238A (en) * | 2017-03-20 | 2018-10-09 | 中国科学院声学研究所 | A kind of ambient noise monitoring device |
-
2018
- 2018-11-15 CN CN201811358787.3A patent/CN109389994A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104781862A (en) * | 2012-10-12 | 2015-07-15 | 塔塔咨询服务有限公司 | Real-time traffic detection |
| CN104794894A (en) * | 2015-01-29 | 2015-07-22 | 青岛智能产业技术研究院 | Automobile whistle noise monitoring device, system and method |
| CN104916289A (en) * | 2015-06-12 | 2015-09-16 | 哈尔滨工业大学 | Quick acoustic event detection method under vehicle-driving noise environment |
| CN106355893A (en) * | 2016-10-28 | 2017-01-25 | 东方智测（北京）科技有限公司 | Method and system for real-time positioning of whistling motor vehicle |
| CN106875678A (en) * | 2017-01-23 | 2017-06-20 | 上海良相智能化工程有限公司 | A kind of vehicle whistle law enforcement evidence-obtaining system |
| CN108627238A (en) * | 2017-03-20 | 2018-10-09 | 中国科学院声学研究所 | A kind of ambient noise monitoring device |
| CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110647949A (en) * | 2019-10-21 | 2020-01-03 | 中国计量大学 | Calibration method of automobile whistling snapshot device based on deep learning |
| CN110647949B (en) * | 2019-10-21 | 2024-02-20 | 中国计量大学 | Calibration method of car whistle snapshot device based on deep learning |
| CN112992176A (en) * | 2020-09-30 | 2021-06-18 | 北京海兰信数据科技股份有限公司 | Ship acoustic signal identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109616140B (en) | Abnormal sound analysis system | |
| CN102163427B (en) | Method for detecting audio exceptional event based on environmental model | |
| CN102664006B (en) | Abnormal voice detecting method based on time-domain and frequency-domain analysis | |
| CN104916289A (en) | Quick acoustic event detection method under vehicle-driving noise environment | |
| CN107527617A (en) | Monitoring method, apparatus and system based on voice recognition | |
| CN109816987B (en) | Electronic police law enforcement snapshot system for automobile whistling and snapshot method thereof | |
| CN101364408A (en) | Sound image combined monitoring method and system | |
| CN111436944B (en) | Falling detection method based on intelligent mobile terminal | |
| EP2827326A1 (en) | Scene recognition method, device and mobile terminal based on ambient sound | |
| CN106251874A (en) | A kind of voice gate inhibition and quiet environment monitoring method and system | |
| CN106128452A (en) | Acoustical signal detection keyboard is utilized to tap the system and method for content | |
| CN106846803A (en) | Traffic incidents detection device and method based on audio | |
| CN103198838A (en) | Abnormal sound monitoring method and abnormal sound monitoring device used for embedded system | |
| CN107360157A (en) | A kind of user registering method, device and intelligent air conditioner | |
| CN103971681A (en) | Voice recognition method and system | |
| CN105640748A (en) | Vibration blind-guiding clothing | |
| CN102821194B (en) | Cellphone indoor positioning device and cellphone indoor positioning method on basis of various sensors | |
| CN109949823A (en) | A kind of interior abnormal sound recognition methods based on DWPT-MFCC and GMM | |
| CN103956164A (en) | Voice awakening method and system | |
| CN106205606A (en) | A kind of dynamic positioning and monitoring method based on speech recognition and system | |
| CN106713633A (en) | Deaf people prompt system and method, and smart phone | |
| CN109473119A (en) | A kind of acoustic target event-monitoring method | |
| CN101833843A (en) | Monitoring system based on voiceprint authentication | |
| CN105825857A (en) | Voiceprint-recognition-based method for assisting deaf patient in determining sound type | |
| CN107105092A (en) | A kind of human body tumble recognition methods based on dynamic time warping |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190226 |