CN103594092A - Single microphone voice noise reduction method and device - Google Patents
Single microphone voice noise reduction method and device Download PDFInfo
- Publication number
- CN103594092A CN103594092A CN201310599189.6A CN201310599189A CN103594092A CN 103594092 A CN103594092 A CN 103594092A CN 201310599189 A CN201310599189 A CN 201310599189A CN 103594092 A CN103594092 A CN 103594092A
- Authority
- CN
- China
- Prior art keywords
- noise
- voice signal
- filtering
- voice
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Telephone Function (AREA)
Abstract
The invention relates to the technical field of communication noise reduction, in particular to a single microphone voice noise reduction method. According to the method, time slots with no user voice input during a conversation process are identified, and voice signals collected by a microphone during the time slots with no user voice input are all background noise signals, so that the time slots are used for obtaining the background noise signals, then noise filtering processing is conducted on the voice signals during the conversation process according to the background noise signals, and therefore the noise disturbance problem can be solved by only one microphone, and the cost and design difficulty of mobile communication equipment are reduced.
Description
Technical field
Noise reduction technology field, particularly a kind of single microphone voice de-noising method the present invention relates to communicate by letter.The method, by setting up functional module construction, is controlled computer system by computer program instructions and is completed.
Background technology
Along with the development of technology, mobile communication equipment is popularized greatly.In use mobile communication equipment carries out communication process, inevitably have background noise, the existence of background noise has had a strong impact on the quality of call, and different due to call environment, background noise is also different.To this, in order to improve speech quality, be mainly in the industry at present to adopt the mode of dual microphone to filter the processing of making an uproar.As the patent No. is: the patent document of CN 103219011A discloses a kind of for solving the noise-reduction method of the noise jamming problem in communication terminal when call, and this noise-reduction method comprises: control the first audio input device (i.e. the first microphone) and gather the residing neighbourhood noise of described communication terminal; The scene noise prestoring in described neighbourhood noise and described communication terminal is carried out to Spectrum Analysis Comparison, and obtain a comparing result; And according to described comparing result, call noise reduction parameters corresponding to described neighbourhood noise, and isolate according to described noise reduction parameters the user voice that described the second audio input device (being second microphone) gathers.
Visible, in the prior art, for filter out noise, mobile communication equipment must possess two microphones, one of them microphone is used for gathering background noise, another microphone is for gathering the voice of user's input, and this has not only increased the cost of mobile communication equipment, has also increased the design difficulty of the mobile communication equipment of miniaturization.
Summary of the invention
The object of the invention is to avoid above-mentioned weak point of the prior art and provide a kind of and can realize the voice de-noising method that carry out noise reduction process to communication process by microphone.
Object of the present invention is achieved through the following technical solutions:
A voice de-noising method, comprising:
Benchmark speech feature extraction step: the reference characteristic parameter T1 that obtains user voice signal before call under noiselessness environment;
Call noise acquisition step: judge in the received voice signal of communication process whether comprise user voice signal according to reference characteristic parameter T1, the voice signal that the time slot that does not comprise user voice signal in sent voice signal is received is defined as background noise;
Noise-filtering step: according to the noise in background noise filtering voice signal to be sent to form without noisy speech signal.
Wherein, also comprise timing step: call starts timing while starting, according to property time-count cycle, start described call noise acquisition step to periodically update described background noise.
Wherein, the method also comprises the preliminary filter step of making an uproar: when call starts, differ from the voice signal of reference characteristic parameter T1 in filtering voice signal to be sent.
Wherein, described noise-filtering step comprises:
Feature of noise parameter extraction step: the feature of noise parameter T2 that extracts background noise;
Direct filtering step: the noise signal that meets feature of noise parameter T2 in filtering voice signal to be sent is to form without noisy speech signal.
Beneficial effect of the present invention: the present invention by identifying the time slot of no user phonetic entry in communication process, the voice signal that microphone collects in the time slot of no user phonetic entry is background noise, therefore utilize this time slot to carry out background extraction noise signal, then according to this background noise, the voice signal in communication process is filtered to the processing of making an uproar, thereby realize, utilize a microphone can solve the problem of noise jamming, reduced cost and the design difficulty of mobile communication equipment.
Embodiment
The invention will be further described with the following Examples.
The embodiment of a kind of single microphone voice de-noising method of the present invention, comprising:
Steps A: the reference characteristic parameter T1 that obtains user voice signal before call under noiselessness environment; This step can be by the voice of user's typing oneself under quiet environment, then the characteristic parameter that system is extracted in voice is automatically realized, certainly, in Input Process, system also can detect to help user to obtain a noiseless input environment to environmental volume.Particularly, the characteristic parameter that extracts voice belongs to common practise in the art, does not repeat them here.
Step B: when call starts, obviously differ from the voice signal of reference characteristic parameter T1 in filtering voice signal to be sent.When call starts, user input voice, owing to only there being a microphone, now system also fails to gather the noise signal in environment, also with regard to failing, according to environmental noise signal, the voice signal of user's input is carried out to noise reduction process, therefore adopting this step will be obviously the characteristic parameter of user input voice from reference characteristic parameter T1(in the voice signal of user's input) (the method only can be for preliminary noise reduction in different voice signal filterings, background noise in filtering voice completely), with this, reach the preliminary noise reduction object of incipient stage in call.Certainly, the preliminary noise reduction that this step is only used for conversing before incipient stage background extraction noise signal not yet in effect is used, and in actual application, also can not adopt this step.
Step C: after call starts, every a time period T, according to reference characteristic parameter T1, judge in the received voice signal of communication process whether comprise user voice signal, the voice signal that the time slot that does not comprise user voice signal in sent voice signal is received is defined as background noise;
Concrete, according to reference characteristic parameter T1, judge that the method that whether comprises user voice signal in the received voice signal of communication process belongs to comparatively proven technique of this area, due to reference characteristic parameter, T1 has obvious speech envelope, and frequency spectrum and intensity voice and change, and ground unrest has more stable frequency and intensity, utilize first order IIR filtering device can obtain the spectrum distribution of noise, can instantaneously identify voice and noise signal thus, and whether can identify this voice signal be that this user says; System just can utilize this principle judgement user when speaking, and when has not spoken;
In addition, this method adopts and periodically updates background noise, concrete cycle length and cycle strategy can arrange flexibly, it is 5 seconds that update cycle is for example set, cycle strategy can be that system just starts whether to comprise user voice signal to gather background noise in the voice signal that receives of judgement every 5 seconds in communication process, can also be has also upgraded at every turn background noise after 5 seconds system start whether to comprise user voice signal with collection background noise in voice signal that judgement receives.
Step D: extract the feature of noise parameter T2 of background noise, the noise signal that meets feature of noise parameter T2 in filtering voice signal to be sent is to form without noisy speech signal.With this, realize the noise in filtering voice signal to be sent.Certainly, those skilled in the art also can adopt additive method according to the noise in background noise filtering voice signal to be sent, and for example adopting the patent No. is the filter method for de-noising in the patent document of CN 103219011A, and this is located to repeat no more.
The method providing herein, all or part of step wherein can, by setting up functional module construction, be controlled computer system by computer program instructions and complete.These computer program instructions are stored in computer-readable recording medium.
Finally should be noted that; above embodiment is only in order to illustrate technical scheme of the present invention; but not limiting the scope of the invention; although the present invention has been done to explain with reference to preferred embodiment; those of ordinary skill in the art is to be understood that; can modify or be equal to replacement technical scheme of the present invention, and not depart from essence and the scope of technical solution of the present invention.
Claims (8)
1. a single microphone voice de-noising method, is characterized in that comprising:
Benchmark speech feature extraction step: the reference characteristic parameter T1 that obtains user voice signal before call under noiselessness environment;
Call noise acquisition step: judge in the received voice signal of communication process whether comprise user voice signal according to reference characteristic parameter T1, the voice signal that the time slot that does not comprise user voice signal in sent voice signal is received is defined as background noise;
Noise-filtering step: according to the noise in background noise filtering voice signal to be sent to form without noisy speech signal.
2. a kind of single microphone voice de-noising method as claimed in claim 1, characterized by further comprising timing step: call starts timing while starting, and according to property time-count cycle, starts described call noise acquisition step to periodically update described background noise.
3. a kind of single microphone voice de-noising method as claimed in claim 1, characterized by further comprising the preliminary filter step of making an uproar: when call starts, differ from the voice signal of reference characteristic parameter T1 in filtering voice signal to be sent.
4. a kind of single microphone voice de-noising method as claimed in claim 1, is characterized in that described noise-filtering step comprises:
Feature of noise parameter extraction step: the feature of noise parameter T2 that extracts background noise;
Direct filtering step: the noise signal that meets feature of noise parameter T2 in filtering voice signal to be sent is to form without noisy speech signal.
5. a single microphone voice noise reduction device, is characterized in that comprising:
Benchmark speech feature extraction device: the reference characteristic parameter T1 that obtains user voice signal before call under noiselessness environment;
Call noise harvester: judge in the received voice signal of communication process whether comprise user voice signal according to reference characteristic parameter T1, the voice signal that the time slot that does not comprise user voice signal in sent voice signal is received is defined as background noise;
Noise-filtering device: according to the noise in background noise filtering voice signal to be sent to form without noisy speech signal.
6. a kind of single microphone voice noise reduction device as claimed in claim 1, characterized by further comprising time set: call starts timing while starting, and according to property time-count cycle, starts described call noise harvester to periodically update described background noise.
7. a kind of single microphone voice noise reduction device as claimed in claim 1, characterized by further comprising the preliminary filter device of making an uproar: when call starts, differ from the voice signal of reference characteristic parameter T1 in filtering voice signal to be sent.
8. a kind of single microphone voice noise reduction device as claimed in claim 1, is characterized in that described noise-filtering device comprises:
Feature of noise parameter extraction device: the feature of noise parameter T2 that extracts background noise;
Direct filtering device: the noise signal that meets feature of noise parameter T2 in filtering voice signal to be sent is to form without noisy speech signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310599189.6A CN103594092A (en) | 2013-11-25 | 2013-11-25 | Single microphone voice noise reduction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310599189.6A CN103594092A (en) | 2013-11-25 | 2013-11-25 | Single microphone voice noise reduction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103594092A true CN103594092A (en) | 2014-02-19 |
Family
ID=50084198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310599189.6A Pending CN103594092A (en) | 2013-11-25 | 2013-11-25 | Single microphone voice noise reduction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103594092A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104409081A (en) * | 2014-11-25 | 2015-03-11 | 广州酷狗计算机科技有限公司 | Speech signal processing method and device |
| CN105374364A (en) * | 2014-08-25 | 2016-03-02 | 联想(北京)有限公司 | Signal processing method and electronic device |
| CN105719657A (en) * | 2016-02-23 | 2016-06-29 | 惠州市德赛西威汽车电子股份有限公司 | Human voice extracting method and device based on microphone |
| CN106486130A (en) * | 2015-08-25 | 2017-03-08 | 百度在线网络技术（北京）有限公司 | Noise elimination, audio recognition method and device |
| CN108766453A (en) * | 2018-05-24 | 2018-11-06 | 江西午诺科技有限公司 | Voice de-noising method, device, readable storage medium storing program for executing and mobile terminal |
| CN109389970A (en) * | 2018-12-28 | 2019-02-26 | 合肥凯捷技术有限公司 | A kind of speech analysis recognition methods |
| CN110191397A (en) * | 2019-06-28 | 2019-08-30 | 歌尔科技有限公司 | A kind of noise-reduction method and bluetooth headset |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079261A (en) * | 2007-07-02 | 2007-11-28 | 徐忠义 | Voice extraction circuit for suppressing environment noise |
| CN101193139A (en) * | 2006-11-20 | 2008-06-04 | 鸿富锦精密工业（深圳）有限公司 | A method and its mobile phone for filtering environmental noise |
| US20110231187A1 (en) * | 2010-03-16 | 2011-09-22 | Toshiyuki Sekiya | Voice processing device, voice processing method and program |
| US20120191450A1 (en) * | 2009-07-27 | 2012-07-26 | Mark Pinson | System and method for noise reduction in processing speech signals by targeting speech and disregarding noise |
| CN102629472A (en) * | 2011-02-07 | 2012-08-08 | Jvc建伍株式会社 | Noise rejection apparatus and noise rejection method |
| CN102737646A (en) * | 2012-06-21 | 2012-10-17 | 佛山市瀚芯电子科技有限公司 | Real-time dynamic voice noise reduction method for single microphone |
| CN102859592A (en) * | 2010-06-04 | 2013-01-02 | 苹果公司 | User-specific noise suppression for voice quality improvements |
| CN103310794A (en) * | 2012-03-11 | 2013-09-18 | 闻泰通讯股份有限公司 | Method filtering conversation noise and device filtering conversation noise |
-
2013
- 2013-11-25 CN CN201310599189.6A patent/CN103594092A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101193139A (en) * | 2006-11-20 | 2008-06-04 | 鸿富锦精密工业（深圳）有限公司 | A method and its mobile phone for filtering environmental noise |
| CN101079261A (en) * | 2007-07-02 | 2007-11-28 | 徐忠义 | Voice extraction circuit for suppressing environment noise |
| US20120191450A1 (en) * | 2009-07-27 | 2012-07-26 | Mark Pinson | System and method for noise reduction in processing speech signals by targeting speech and disregarding noise |
| US20110231187A1 (en) * | 2010-03-16 | 2011-09-22 | Toshiyuki Sekiya | Voice processing device, voice processing method and program |
| CN102859592A (en) * | 2010-06-04 | 2013-01-02 | 苹果公司 | User-specific noise suppression for voice quality improvements |
| CN102629472A (en) * | 2011-02-07 | 2012-08-08 | Jvc建伍株式会社 | Noise rejection apparatus and noise rejection method |
| CN103310794A (en) * | 2012-03-11 | 2013-09-18 | 闻泰通讯股份有限公司 | Method filtering conversation noise and device filtering conversation noise |
| CN102737646A (en) * | 2012-06-21 | 2012-10-17 | 佛山市瀚芯电子科技有限公司 | Real-time dynamic voice noise reduction method for single microphone |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105374364A (en) * | 2014-08-25 | 2016-03-02 | 联想(北京)有限公司 | Signal processing method and electronic device |
| CN105374364B (en) * | 2014-08-25 | 2019-08-27 | 联想(北京)有限公司 | Signal processing method and electronic equipment |
| CN104409081A (en) * | 2014-11-25 | 2015-03-11 | 广州酷狗计算机科技有限公司 | Speech signal processing method and device |
| CN106486130A (en) * | 2015-08-25 | 2017-03-08 | 百度在线网络技术（北京）有限公司 | Noise elimination, audio recognition method and device |
| CN105719657A (en) * | 2016-02-23 | 2016-06-29 | 惠州市德赛西威汽车电子股份有限公司 | Human voice extracting method and device based on microphone |
| CN108766453A (en) * | 2018-05-24 | 2018-11-06 | 江西午诺科技有限公司 | Voice de-noising method, device, readable storage medium storing program for executing and mobile terminal |
| CN109389970A (en) * | 2018-12-28 | 2019-02-26 | 合肥凯捷技术有限公司 | A kind of speech analysis recognition methods |
| CN110191397A (en) * | 2019-06-28 | 2019-08-30 | 歌尔科技有限公司 | A kind of noise-reduction method and bluetooth headset |
| CN110191397B (en) * | 2019-06-28 | 2021-10-15 | 歌尔科技有限公司 | Noise reduction method and Bluetooth headset |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103594092A (en) | Single microphone voice noise reduction method and device | |
| CN103152546B (en) | Based on pattern recognition and the video conference echo suppressing method postponing feedfoward control | |
| MX2010008372A (en) | Apparatus and method for computing filter coefficients for echo suppression. | |
| CN105657110B (en) | Echo cancellation method and device for voice communication | |
| GB2577450A (en) | Methods, apparatus and systems for biometric processes | |
| WO2016127506A1 (en) | Voice processing method, voice processing device, and terminal | |
| CN101938610A (en) | Novel voiceprint recognition-based television device | |
| CN102946493B (en) | A kind of mobile terminal call ambient sound adjusting method | |
| CN105931647B (en) | Method and device for noise suppression | |
| CN103325378A (en) | Terminal voice noise reducing method and terminal | |
| US20190318720A1 (en) | Time-based frequency tuning of analog-to-information feature extraction | |
| CN104978955A (en) | Voice control method and system | |
| WO2007018802A3 (en) | Method and system for operation of a voice activity detector | |
| CN110277103A (en) | Noise-reduction method and terminal based on speech recognition | |
| KR20170044689A (en) | Voice wake-up method and device | |
| CN103778915A (en) | Speech recognition method and mobile terminal | |
| CN102694891A (en) | System and method for removing conversation noises | |
| US20150212792A1 (en) | Method, System and Computer Storage Medium for Detecting an Audio Input Interface | |
| CN110191397B (en) | Noise reduction method and Bluetooth headset | |
| CN104978956A (en) | Voice control method and system | |
| CN107274895A (en) | A kind of speech recognition apparatus and method | |
| CN103366758A (en) | Method and device for reducing noises of voice of mobile communication equipment | |
| CN104157289A (en) | Bluetooth headset voice recognition method | |
| CN104867498A (en) | Mobile communication terminal and voice enhancement method and module thereof | |
| DE102013002963A1 (en) | Control using temporally and / or spectrally compact audio commands |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140219 |
|
| RJ01 | Rejection of invention patent application after publication |