CN107103904A - A kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice and noise-reduction method - Google Patents
A kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice and noise-reduction method Download PDFInfo
- Publication number
- CN107103904A CN107103904A CN201710235726.7A CN201710235726A CN107103904A CN 107103904 A CN107103904 A CN 107103904A CN 201710235726 A CN201710235726 A CN 201710235726A CN 107103904 A CN107103904 A CN 107103904A
- Authority
- CN
- China
- Prior art keywords
- noise
- signal
- voice
- language
- module
- 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.)
- Granted
Links
- 230000009467 reduction Effects 0.000 title claims abstract description 27
- 230000009977 dual effect Effects 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims abstract description 11
- 238000001228 spectrum Methods 0.000 claims description 45
- 238000012545 processing Methods 0.000 claims description 20
- 230000003321 amplification Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000004378 air conditioning Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 5
- 241000209140 Triticum Species 0.000 description 2
- 235000021307 Triticum Nutrition 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241001347978 Major minor Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 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
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L21/0232—Processing in the frequency domain
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0316—Speech enhancement, e.g. noise reduction or echo cancellation by changing the amplitude
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02165—Two microphones, one receiving mainly the noise signal and the other one mainly the speech signal
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Fittings On The Vehicle Exterior For Carrying Loads, And Devices For Holding Or Mounting Articles (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The present invention relates to a kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice and noise-reduction method, including the net sound module of main microphon, secondary microphone, voice and speech recognition subsequent treatment module;The main microphon:The sound and driving noise of typing passenger;The secondary microphone:Typing driving noise;The net sound module of voice:Handle the language noise cancellation signal of the main microphon and the secondary microphone typing, and optimize the language noise cancellation signal acquisition noise signal of the secondary microphone typing by noise model storehouse, the treated main microphon language noise cancellation signal subtracts noise signal and obtains voice signal, by voice signal and speech model storehouse matching optimization, clean speech signal is obtained;The speech recognition subsequent treatment module:The voice signal sent is recognized and respective operations are performed.The present invention is equipped with noise model storehouse and speech model storehouse, and matching optimization voice signal obtains clean speech, the in-car phonetic recognization rate of lifting, it is ensured that the complete execution of phonetic function.
Description
Technical field
The invention belongs to automotive electronics applied technical field, and in particular to a kind of diamylose gram recognized applied to vehicle-mounted voice
Wind noise reduction system and noise-reduction method.
Background technology
With the development of automotive field science and technology, people are more strong to the use desire of in-car electronic product.
Speech recognition is the new technology grown up in recent years, is also the New function for just having penetrated into automotive field, and it leads to
The mode for crossing interactive voice controls the partial function of vehicle, and the driving of lifting driver is enjoyed.
One of key technology of speech recognition be exactly voice sound clarity processing, that is, voice noise reduction technology.It is existing
Some noise-reduction methods have following several:
Chinese patent CN201410076957.4 discloses a kind of voice de-noising method, using single microphone scheme, calculates preceding 30
The power noise Power estimation value of frame calculates average power spectra when speaking as speech frame, speech frame subtracts quiet as mute frame
Sound frame obtains the voice after noise reduction as the speech manual after noise reduction, then by processing, and this method is due to using making an uproar before speaking
Sound is not accurate enough during processing noise reduction, it is impossible in voice not with real-time background noise of speaking as mute frame as mute frame
Used in this high accurately function of identification.
Chinese patent CN201410042189.0 discloses a kind of two-way microphone voice de-noising processing method and system,
Using dual microphone scheme, two paths of signals summation is taken and averagely estimated as noisy speech signal, ask difference is average to believe as noise
Number estimation, noisy speech signal estimation with noise signal estimate power spectrum subtraction obtain clean speech signal power spectrum, finally
The noise signal obtained by processing in pure voice signal, such a method is subtracted each other by simple two-way signal to be drawn, due to
The noise of vehicle is different from voice noise, and institute can not also use in the car in this way.
In addition there are the dual microphone noise reduction system and method being applied on mobile phone, its main microphon and secondary microphone
Keep certain distance, so ensure that voice that major and minor microphone is received has an amplitude difference, and the noise received be it is the same, so
Noise is removed by the method subtracted each other afterwards.Although this method preferably removes noise, vehicle audio identification is not suitable for.
On the one hand, the major-minor microphone of vehicle all has certain distance with driver, it is impossible to obvious to distinguish noise and the sound of people, secondly
Speech identifying function is also that copilot and back-seat passengers provide, so vehicle audio identification can not make in this way.
The content of the invention
In order to solve above-mentioned technical problem, the present invention devises a kind of diamylose gram recognized applied to vehicle-mounted voice
Wind noise reduction system and noise-reduction method, pass through the processing to tonequality, it is ensured that voice typing it is clear, so as to lift phonetic recognization rate,
Ensure that the normal of phonetic function is used.
In order to solve above-mentioned technical problem, present invention employs following scheme:
A kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice, it is characterised in that including main microphon, secondary Mike
The net sound module of wind, voice and speech recognition subsequent treatment module;
The main microphon:The sound and driving noise of typing passenger;
The secondary microphone:Typing driving noise;
The net sound module of voice:The language noise cancellation signal of the main microphon and the secondary microphone typing is handled, and passes through noise
The language noise cancellation signal that model library optimizes the secondary microphone typing obtains noise signal, and the treated main microphon language is made an uproar letter
Number subtracting noise signal obtains voice signal, by the voice signal and speech model storehouse matching optimization, obtains clean speech letter
Number;
The speech recognition subsequent treatment module:The clean speech signal sent is recognized and respective operations are performed.
Further, the net sound module of the voice includes:
Signal conversion module:Analog signal is switched into data signal;
Noise pickup module:Divided by sound frequency, pick up the noise components in the language noise cancellation signal of the secondary microphone typing,
Matched again with noise model storehouse, extend noise components, finally by noise components and the primitive noise cancellation signal of the secondary microphone typing
Contrast is handled, and obtains final noise signal;
Noise model storehouse:Built-in noisy speech frequency spectrum and optimization program, assess noise trend and improve the noise signal;Wherein
Noisy speech frequency spectrum is noise data statistics of the early stage for vehicle under various travel situations, and the language noise cancellation signal of secondary microphone can
With in contrast, the noise signal under corresponding states is filtered out;
Audio processing modules:The noise signal that language noise cancellation signal and the noise pickup module to the main microphon typing are obtained
Handled, by Fourier transformation, respectively obtain language make an uproar power spectrum and power noise spectrum;
Signal integration module:Language power spectrum of making an uproar is subtracted into power noise spectrum, show that phonetic speech power is composed, and is converted by data, also
Former voice signal;
Net sound processing module:Voice signal after reduction is matched with speech model storehouse, optimizes voice signal;
Speech model storehouse:Built-in language voice spectrum and optimization program, and by scoring and Optimization Mechanism to the voice signal
Further screening and optimization;
Signal amplification module:Voice signal after optimization is further amplified, strengthens the realization of subsequent voice function.
Further, the driving noise of the main microphon typing mainly includes air conditioning exhausting sound, windowing wind sound, in-car machinery
The driving noise such as fricative.
A kind of dual microphone noise-reduction method recognized applied to vehicle-mounted voice, it is characterised in that comprise the following steps:
Step 1, speech recognition is opened in the car, and sends phonetic order;
Step 2, main microphon sends the language noise cancellation signal of typing to the net sound module of voice, corresponding in the net sound module of voice
Signal conversion module language analog signal of making an uproar is converted into sending after data signal to corresponding audio processing modules;Simultaneously
Secondary microphone sends the language noise cancellation signal of typing to the net sound module of the voice, corresponding signal in the net sound module of voice
Language analog signal of making an uproar is converted into sending after data signal to noise pickup module by modular converter, and noise pickup module is by making an uproar
Sound excision, pickup, optimal way obtain noise signal, and the noise signal are sent to corresponding audio processing modules;Make an uproar
Sound pickup model will come from the secondary microphone and be divided into many sections by the language noise cancellation signal changed, then for every segment signal
Contrasted with noise model storehouse, pickup wherein noise signal section, and the noise signal section after pickup is integrated and optimized;
Step 3, the audio processing modules carry out amplitude spectrum and phase spectrum to corresponding language noise cancellation signal and noise signal respectively
Split, and to amplitude spectrum carry out Fourier transformation, obtain language make an uproar power spectrum and power noise spectrum;
Step 4, in signal integration module, power spectrum of being made an uproar with institute's predicate subtracts the power noise spectrum, obtains voice signal work(
Rate is composed, and is reduced into voice signal by change;
Step 5, the voice signal after reduction is matched and optimized with speech model storehouse;
Step 6, the voice signal after optimization is amplified by signal amplifier, obtains final pure amplification voice signal, finally
Send to speech recognition program, recognize and perform respective operations.
Further, in above-mentioned steps 2, the language noise cancellation signal that noise pickup module picks up secondary microphone carries out audio division,
Extract wherein noise components, then noise components match with noise model storehouse, by Data Matching with optimize program by noise
Part is perfect, and the noise components after improving are contrasted with language noise cancellation signal again, are deleted spilling sound frequency, are finally given noise signal.
The dual microphone noise reduction system and noise-reduction method that are applied to vehicle-mounted voice identification have the advantages that:
(1)Noise model storehouse and speech model storehouse that the present invention is arranged by early stage, matching optimization voice signal obtain pure language
Sound, the in-car phonetic recognization rate of lifting, it is ensured that the complete execution of phonetic function.
(2)The present invention is that main microphon receives voice+noise, secondary wheat on the basis of the basic framework that signal differential amplifies
Gram wind individually receives noise, and passes through noise model storehouse noise optimized signal.It is pure by the optimization of speech model storehouse after difference
Voice signal.Compared to traditional approach, make the voice signal finally given purer clear, be more suitable for vehicle-mounted voice identification system
System.
Brief description of the drawings
Fig. 1:The structural representation for the dual microphone noise reduction system that the present invention is recognized applied to vehicle-mounted voice;
Fig. 2:The workflow diagram for the dual microphone noise reduction system that the present invention is recognized applied to vehicle-mounted voice;
Fig. 3:The workflow diagram of noise pickup module in the present invention.
Description of reference numerals:
1-main microphon;2-secondary microphone;The net sound module of 3-voice;4-speech recognition subsequent treatment module.
Embodiment
Below in conjunction with the accompanying drawings, the present invention will be further described:
Fig. 1 shows a kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice, including main microphon 1, secondary microphone
2nd, the net sound module 3 of voice and speech recognition subsequent treatment module 4.
Main microphon 1:The sound and driving noise of typing passenger, its middle rolling car noise mainly include air conditioning exhausting
The driving noises such as sound, windowing wind sound, in-car mechanical friction sound.
Secondary microphone 2:Typing driving noise.
The net sound module 3 of voice includes:
Signal conversion module:Analog signal is switched into data signal;
Noise pickup module:The language noise cancellation signal of secondary microphone typing is handled, because the frequency of driving noise is spoken with normal person
Frequency it is different, divided by sound frequency, pick up wherein noise components, then match with noise model storehouse, extension noise components,
Finally noise components and the contrast of primitive noise cancellation signal are handled, final noise signal is obtained;
Noise model storehouse:Built-in noisy speech frequency spectrum and optimization program, assess noise trend and improve noise signal;
Audio processing modules:Language noise cancellation signal and noise signal are handled, by Fourier transformation, language is respectively obtained and makes an uproar power
Spectrum and power noise spectrum;
Signal integration module:Language power spectrum of making an uproar is subtracted into power noise spectrum, show that phonetic speech power is composed, and is converted by data, also
Former voice signal;
Net sound processing module:Voice signal after reduction is matched with speech model storehouse, optimizes voice signal;
Speech model storehouse:Built-in language voice spectrum and optimization program, and one is entered to voice signal by scoring and Optimization Mechanism
Step screening and optimization.
Signal amplification module:Voice signal after optimization is further amplified, strengthens the realization of subsequent voice function.
Speech recognition subsequent treatment module 4:The voice signal sent is recognized and respective operations are performed.
During work, as depicted in figs. 1 and 2, client opens speech recognition in the car, and sends phonetic order.Wherein, main wheat
Gram wind 1 sends the language noise cancellation signal of typing to the net sound module 3 of voice, corresponding signal conversion module in the net sound module 3 of voice
Language analog signal of making an uproar is converted into sending after data signal to corresponding audio processing modules.And secondary microphone 2 is by typing
Language noise cancellation signal is sent to the net sound module 3 of voice, and corresponding signal conversion module makes an uproar the language simulation letter in the net sound module 3 of voice
Number it is converted into sending after data signal to noise pickup module, noise pickup module is cut off by noise, picked up, optimal way is obtained
Sent to noise signal, and by the noise signal to corresponding audio processing modules.Audio processing modules are respectively to corresponding
Language noise cancellation signal and noise signal carry out amplitude spectrum and phase spectrum and split, and Fourier transformation is carried out to amplitude spectrum, obtains language and make an uproar
Power spectrum and power noise spectrum.In signal integration module, by language make an uproar power spectrum subtract power noise spectrum, obtain voice signal work(
Rate is composed, and by changing reduction journey voice signal;Voice signal after reduction is matched with speech model storehouse, voice signal now
Band segment incompleteness is there may be, and band segment is not enough, it is necessary to which the sentence frequency spectrum of contrast phone model library is to incomplete, not enough
Phonological component mending-leakage, compensation.Voice signal after optimization is amplified by signal amplification module, final pure amplification voice is obtained
Signal, finally sends to speech recognition program, recognizes and performs respective operations.
As shown in figure 3, the language noise cancellation signal that wherein noise pickup module picks up secondary microphone carries out audio division, it is extracted
Middle noise components, then match noise components with noise model storehouse, by Data Matching and optimization program that noise components are complete
Kind and comprehensive, the noise components after improving are contrasted with language noise cancellation signal again, are deleted spilling sound frequency, are finally given noise signal.
Noise model storehouse and speech model storehouse that the present invention is arranged by early stage, matching optimization voice signal obtain pure
Voice, the in-car phonetic recognization rate of lifting, it is ensured that the complete execution of phonetic function.
The present invention is that main microphon receives voice+noise, secondary microphone on the basis of the basic framework that signal differential amplifies
Individually noise is received, and pass through noise model storehouse noise optimized signal.Clean speech is optimized by speech model storehouse after difference
Signal.Compared to traditional approach, make the voice signal finally given purer clear, be more suitable for vehicle-mounted voice identifying system.
Exemplary description is carried out to the present invention above in conjunction with accompanying drawing, it is clear that realization of the invention is not by aforesaid way
Limitation, it is or not improved by the present invention as long as employing the various improvement of inventive concept and technical scheme of the present invention progress
Design and technical scheme directly apply to other occasions, within the scope of the present invention.
Claims (6)
1. a kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice, it is characterised in that including main microphon, secondary Mike
The net sound module of wind, voice and speech recognition subsequent treatment module;
The main microphon:The sound and driving noise of typing passenger;
The secondary microphone:Typing driving noise;
The net sound module of voice:The language noise cancellation signal of the main microphon and the secondary microphone typing is handled, and passes through noise
The language noise cancellation signal that model library optimizes the secondary microphone typing obtains noise signal, and the treated main microphon language is made an uproar letter
Number subtracting noise signal obtains voice signal, by the voice signal and speech model storehouse matching optimization, obtains clean speech letter
Number;
The speech recognition subsequent treatment module:The clean speech signal sent is recognized and respective operations are performed.
2. the dual microphone noise reduction system according to claim 1 recognized applied to vehicle-mounted voice, it is characterised in that described
The net sound module of voice includes:
Signal conversion module:Analog signal is switched into data signal;
Noise pickup module:Divided by sound frequency, pick up the noise components in the language noise cancellation signal of the secondary microphone typing,
Matched again with noise model storehouse, extend noise components, finally by noise components and the primitive noise cancellation signal of the secondary microphone typing
Contrast is handled, and obtains final noise signal;
Noise model storehouse:Built-in noisy speech frequency spectrum and optimization program, assess noise trend and improve the noise signal;
Audio processing modules:The noise signal that language noise cancellation signal and the noise pickup module to the main microphon typing are obtained
Handled, by Fourier transformation, respectively obtain language make an uproar power spectrum and power noise spectrum;
Signal integration module:Language power spectrum of making an uproar is subtracted into power noise spectrum, show that phonetic speech power is composed, and is converted by data, also
Former voice signal;
Net sound processing module:Voice signal after reduction is matched with speech model storehouse, optimizes voice signal;
Speech model storehouse:Built-in language voice spectrum and optimization program, and by scoring and Optimization Mechanism to the voice signal
Further screening and optimization;
Signal amplification module:Voice signal after optimization is further amplified, strengthens the realization of subsequent voice function.
3. the dual microphone noise reduction system according to claim 2 recognized applied to vehicle-mounted voice, it is characterised in that described
Noise data statistics of the noisy speech frequency spectrum for early stage for vehicle under various travel situations in noise model storehouse.
4. being applied to the dual microphone noise reduction system that vehicle-mounted voice is recognized according to claim 1,2 or 3, its feature exists
In the driving noise of the main microphon typing mainly includes the drivings such as air conditioning exhausting sound, windowing wind sound, in-car mechanical friction sound
Noise.
5. a kind of dual microphone noise-reduction method recognized applied to vehicle-mounted voice, it is characterised in that comprise the following steps:
Step 1, speech recognition is opened in the car, and sends phonetic order;
Step 2, main microphon sends the language noise cancellation signal of typing to the net sound module of voice, corresponding in the net sound module of voice
Signal conversion module language analog signal of making an uproar is converted into sending after data signal to corresponding audio processing modules;Simultaneously
Secondary microphone sends the language noise cancellation signal of typing to the net sound module of the voice, corresponding signal in the net sound module of voice
Language analog signal of making an uproar is converted into sending after data signal to noise pickup module by modular converter, and noise pickup module is by making an uproar
Sound excision, pickup, optimal way obtain noise signal, and the noise signal are sent to corresponding audio processing modules;
Step 3, the audio processing modules carry out amplitude spectrum and phase spectrum to corresponding language noise cancellation signal and noise signal respectively
Split, and to amplitude spectrum carry out Fourier transformation, obtain language make an uproar power spectrum and power noise spectrum;
Step 4, in signal integration module, power spectrum of being made an uproar with institute's predicate subtracts the power noise spectrum, obtains voice signal work(
Rate is composed, and by changing reduction journey voice signal;
Step 5, the voice signal after reduction is matched and optimized with speech model storehouse;
Step 6, the voice signal after optimization is amplified by signal amplifier, obtains final pure amplification voice signal, finally
Send to speech recognition program, recognize and perform respective operations.
6. the dual microphone noise-reduction method according to claim 5 recognized applied to vehicle-mounted voice, it is characterised in that above-mentioned
In step 2, the language noise cancellation signal that noise pickup module picks up secondary microphone carries out audio division, extracts wherein noise components, so
Noise components are matched with noise model storehouse afterwards, by Data Matching and optimization program that noise components are perfect, making an uproar after improving
Line point is contrasted with language noise cancellation signal again, is deleted spilling sound frequency, is finally given noise signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710235726.7A CN107103904B (en) | 2017-04-12 | 2017-04-12 | Double-microphone noise reduction system and method applied to vehicle-mounted voice recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710235726.7A CN107103904B (en) | 2017-04-12 | 2017-04-12 | Double-microphone noise reduction system and method applied to vehicle-mounted voice recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107103904A true CN107103904A (en) | 2017-08-29 |
CN107103904B CN107103904B (en) | 2020-06-09 |
Family
ID=59675083
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710235726.7A Active CN107103904B (en) | 2017-04-12 | 2017-04-12 | Double-microphone noise reduction system and method applied to vehicle-mounted voice recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107103904B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107507623A (en) * | 2017-10-09 | 2017-12-22 | 维拓智能科技(深圳)有限公司 | Self-service terminal based on Microphone Array Speech interaction |
CN107910015A (en) * | 2017-12-12 | 2018-04-13 | 上海与德科技有限公司 | A kind of terminal device noise-reduction method and terminal device |
CN108674344A (en) * | 2018-03-30 | 2018-10-19 | 斑马网络技术有限公司 | Speech processing system based on steering wheel and its application |
CN108806682A (en) * | 2018-06-12 | 2018-11-13 | 奇瑞汽车股份有限公司 | The method and apparatus for obtaining Weather information |
CN109256140A (en) * | 2018-08-30 | 2019-01-22 | 努比亚技术有限公司 | A kind of way of recording, system and audio separation method, equipment and storage medium |
CN109817209A (en) * | 2019-01-16 | 2019-05-28 | 深圳市友杰智新科技有限公司 | A kind of intelligent speech interactive system based on two-microphone array |
CN110111791A (en) * | 2019-05-21 | 2019-08-09 | 扬州航盛科技有限公司 | A kind of speech recognition system based on vehicle intelligent net connection |
CN112102825A (en) * | 2020-08-11 | 2020-12-18 | 湖北亿咖通科技有限公司 | Audio processing method and device based on vehicle-mounted machine voice recognition and computer equipment |
CN112735408A (en) * | 2020-12-24 | 2021-04-30 | 浙江天成自控股份有限公司 | Voice control system and control method for automobile seat |
CN113345433A (en) * | 2021-05-30 | 2021-09-03 | 重庆长安汽车股份有限公司 | Voice interaction system outside vehicle |
CN114093364A (en) * | 2020-06-18 | 2022-02-25 | 杭州普安科技有限公司 | Off-line voice recognition and playing circuit for passive secondary loop check meter |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1902684A (en) * | 2004-01-13 | 2007-01-24 | 西门子公司 | Method and device for processing a voice signal for robust speech recognition |
CN103594091A (en) * | 2013-11-15 | 2014-02-19 | 深圳市中兴移动通信有限公司 | Mobile terminal and voice signal processing method thereof |
CN104810024A (en) * | 2014-01-28 | 2015-07-29 | 上海力声特医学科技有限公司 | Double-path microphone speech noise reduction treatment method and system |
KR20160009731A (en) * | 2014-07-16 | 2016-01-27 | 현대모비스 주식회사 | Noise reduction apparatus and method for car microphone |
CN105489224A (en) * | 2014-09-15 | 2016-04-13 | 讯飞智元信息科技有限公司 | Voice noise reduction method and system based on microphone array |
-
2017
- 2017-04-12 CN CN201710235726.7A patent/CN107103904B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1902684A (en) * | 2004-01-13 | 2007-01-24 | 西门子公司 | Method and device for processing a voice signal for robust speech recognition |
CN103594091A (en) * | 2013-11-15 | 2014-02-19 | 深圳市中兴移动通信有限公司 | Mobile terminal and voice signal processing method thereof |
CN104810024A (en) * | 2014-01-28 | 2015-07-29 | 上海力声特医学科技有限公司 | Double-path microphone speech noise reduction treatment method and system |
KR20160009731A (en) * | 2014-07-16 | 2016-01-27 | 현대모비스 주식회사 | Noise reduction apparatus and method for car microphone |
CN105489224A (en) * | 2014-09-15 | 2016-04-13 | 讯飞智元信息科技有限公司 | Voice noise reduction method and system based on microphone array |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107507623A (en) * | 2017-10-09 | 2017-12-22 | 维拓智能科技(深圳)有限公司 | Self-service terminal based on Microphone Array Speech interaction |
CN107910015A (en) * | 2017-12-12 | 2018-04-13 | 上海与德科技有限公司 | A kind of terminal device noise-reduction method and terminal device |
CN108674344B (en) * | 2018-03-30 | 2024-04-02 | 斑马网络技术有限公司 | Voice processing system based on steering wheel and application thereof |
CN108674344A (en) * | 2018-03-30 | 2018-10-19 | 斑马网络技术有限公司 | Speech processing system based on steering wheel and its application |
CN108806682A (en) * | 2018-06-12 | 2018-11-13 | 奇瑞汽车股份有限公司 | The method and apparatus for obtaining Weather information |
CN108806682B (en) * | 2018-06-12 | 2020-12-01 | 奇瑞汽车股份有限公司 | Method and device for acquiring weather information |
CN109256140A (en) * | 2018-08-30 | 2019-01-22 | 努比亚技术有限公司 | A kind of way of recording, system and audio separation method, equipment and storage medium |
CN109817209A (en) * | 2019-01-16 | 2019-05-28 | 深圳市友杰智新科技有限公司 | A kind of intelligent speech interactive system based on two-microphone array |
CN110111791A (en) * | 2019-05-21 | 2019-08-09 | 扬州航盛科技有限公司 | A kind of speech recognition system based on vehicle intelligent net connection |
CN114093364A (en) * | 2020-06-18 | 2022-02-25 | 杭州普安科技有限公司 | Off-line voice recognition and playing circuit for passive secondary loop check meter |
CN112102825A (en) * | 2020-08-11 | 2020-12-18 | 湖北亿咖通科技有限公司 | Audio processing method and device based on vehicle-mounted machine voice recognition and computer equipment |
CN112735408A (en) * | 2020-12-24 | 2021-04-30 | 浙江天成自控股份有限公司 | Voice control system and control method for automobile seat |
CN113345433A (en) * | 2021-05-30 | 2021-09-03 | 重庆长安汽车股份有限公司 | Voice interaction system outside vehicle |
CN113345433B (en) * | 2021-05-30 | 2023-03-14 | 重庆长安汽车股份有限公司 | Voice interaction system outside vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN107103904B (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107103904A (en) | A kind of dual microphone noise reduction system recognized applied to vehicle-mounted voice and noise-reduction method | |
CN209183264U (en) | Speech processing system | |
EP2151821B1 (en) | Noise-reduction processing of speech signals | |
CN104704560B (en) | The voice signals enhancement that formant relies on | |
CN201177964Y (en) | In-vehicle active sound eliminating system | |
CN204836533U (en) | Acoustic control intelligence audio amplifier with echo elimination function | |
CN105513605A (en) | Voice enhancement system and method for cellphone microphone | |
CN109087631A (en) | A kind of Vehicular intelligent speech control system and its construction method suitable for complex environment | |
CN106205623A (en) | A kind of sound converting method and device | |
CN110383798A (en) | Acoustic signal processing device, acoustics signal processing method and hands-free message equipment | |
CN112634926B (en) | Short wave channel voice anti-fading auxiliary enhancement method based on convolutional neural network | |
CN103827967B (en) | Voice signal restoring means and voice signal restored method | |
CN111091833A (en) | Endpoint detection method for reducing noise influence | |
CN101853665A (en) | Method for eliminating noise in voice | |
CN112259113A (en) | Preprocessing system for improving accuracy rate of speech recognition in vehicle and control method thereof | |
CN109327752A (en) | Bluetooth sound pick-up, mobile unit and automobile | |
CN101458931A (en) | Method for eliminating environmental noise from voice signal | |
Alam et al. | Robust feature extraction for speech recognition by enhancing auditory spectrum | |
KR100446626B1 (en) | Noise suppression method and apparatus | |
JP2007251354A (en) | Microphone and sound generation method | |
EP1286334A3 (en) | Method and circuit arrangement for reducing noise during voice communication in communications systems | |
CN106448662A (en) | Method and system for interrupting vehicle message broadcast by use of automobile horn voiceprint | |
CN103824562B (en) | The rearmounted perceptual filter of voice based on psychoacoustic model | |
CN113707156B (en) | Vehicle-mounted voice recognition method and system | |
CN201294092Y (en) | Ear voice noise eliminator |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |