CN103077725A - Speech processing method and device - Google Patents

Speech processing method and device Download PDF

Info

Publication number
CN103077725A
CN103077725A CN2012105933608A CN201210593360A CN103077725A CN 103077725 A CN103077725 A CN 103077725A CN 2012105933608 A CN2012105933608 A CN 2012105933608A CN 201210593360 A CN201210593360 A CN 201210593360A CN 103077725 A CN103077725 A CN 103077725A
Authority
CN
China
Prior art keywords
voice signal
processing module
noise reduction
speech processing
speech
Prior art date
Application number
CN2012105933608A
Other languages
Chinese (zh)
Other versions
CN103077725B (en
Inventor
李长宁
Original Assignee
东莞宇龙通信科技有限公司
宇龙计算机通信科技(深圳)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 东莞宇龙通信科技有限公司, 宇龙计算机通信科技(深圳)有限公司 filed Critical 东莞宇龙通信科技有限公司
Priority to CN201210593360.8A priority Critical patent/CN103077725B/en
Publication of CN103077725A publication Critical patent/CN103077725A/en
Application granted granted Critical
Publication of CN103077725B publication Critical patent/CN103077725B/en

Links

Abstract

The embodiment of the invention discloses a speech processing method and device, relating to the field of electronic information technology and solving the problems of the prior art that the speech enhancement mode in terminal equipment of a mobile phone and the like is single, speech signals after being subjected to speech enhancement are single. The method comprises the steps of: receiving a conversation speech signal; and after one of a plurality of speech processing modules prearranged in the mobile terminal equipment is activated, conducting noise reduction processing on the conversation speech signal according to the speech processing module, wherein the speech processing modules have different noise reduction capabilities to the conversation speech signal. The speech processing method and device are applicable to mobile terminal equipment such as an intelligent mobile phone.

Description

The method of speech processes and device

Technical field

The present invention relates to electronic information technical field, relate in particular to a kind of method and device of speech processes.

Background technology

The voice enhancing is called again speech de-noising or voice de-noising, its objective is to extract clean voice signal from the voice signal with noise, thereby improves speech tonequality, improves the intelligibility of voice, reduces obedient person's auditory fatigue sense.Current, the voice enhancing has obtained application in actual industrial or consumer products, flourish along with mobile terminal devices such as mobile phones, when under various abominable natures or man-made environment, conversing, a large amount of environmental noises can be superimposed together with speaker's voice signal, pass in obedient person's ear, so that voice quality reduces greatly, also this situation has promoted speech enhancement technique developing rapidly in mobile phone just.In order to improve good speech quality to the user, speech enhancement technique is widely used in mobile phone.

Current speech enhancement technique generally is that voice signal is carried out noise reduction, to improve the sharpness of voice.If but noise reduction is excessive, might damage the voice signal that the user needs, thereby reduce the intelligibility of voice, also may produce some disgusting single frequency tone simultaneously.

Because everyone sense of hearing and psychology there are differences perception and the understanding of sound, so the effect after speech de-noising is also had to different impressions, the same section voice signal after speech enhancement technique is processed, the somebody may think that denoising effect is pretty good, the somebody may think that effect is generally even bad, and the somebody may feel denoising method on the damage of the voice signal of needs affected he to voice signal understanding, also the somebody may think that the single frequency tone set that denoising method brings is comparatively irritated

In the process that realizes the embodiment of the invention, the inventor finds that there are the following problems at least in the prior art:

Voice enhancement method in the current mobile terminal devices such as mobile phone is comparatively single, and the voice signal after strengthening through voice is comparatively single.

Summary of the invention

Embodiments of the invention provide a kind of method and device of speech processes, can solve in the prior art because the voice enhancement method in the mobile terminal devices such as mobile phone is comparatively single, through the comparatively single problem of voice signal after the voice enhancing.

For achieving the above object, the present invention adopts following technical scheme:

A kind of method of speech processes comprises:

Receive the call voice signal;

After in a plurality of speech processing module that set in advance one is activated, according to described speech processing module described call voice signal is carried out noise reduction process in mobile terminal device; Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.

A kind of device of speech processes comprises:

Receiving element is used for receiving the call voice signal;

Noise reduction processing unit after being used in a plurality of speech processing module that mobile terminal device sets in advance one and being activated, is carried out noise reduction process according to described speech processing module to described call voice signal; Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.

The method of speech processes provided by the invention and device, owing to be provided with a plurality of speech processing module in the mobile terminal device, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal, by described a plurality of speech processing module noise reduction process the effect of call voice signal have difference.And voice enhancement method of the prior art is comparatively single, and general same mobile terminal device only has a kind of voice enhancement method, and the voice signal after strengthening through voice is also comparatively single.Therefore, the present invention has diversity through the call voice signal behind the noise reduction, can adapt to varying environment and different user to the requirement of voice signal.

Description of drawings

In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, the below will do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art, apparently, accompanying drawing in the following describes only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.

The process flow diagram of the method for the speech processes that Fig. 1 (a) provides for the embodiment of the invention;

The synoptic diagram of a kind of mobile terminal device in the method for the speech processes that Fig. 1 (b) provides for the embodiment of the invention;

The process flow diagram of the method for the speech processes that Fig. 2 (a) provides for further embodiment of this invention;

The synoptic diagram of a kind of mobile terminal device in the method for the speech processes that Fig. 2 (b) provides for further embodiment of this invention;

The process flow diagram of the method for the speech processes that Fig. 3 provides for yet another embodiment of the invention;

The structural representation one of the device of the speech processes that Fig. 4 provides for the embodiment of the invention;

The structural representation two of the device of the speech processes that Fig. 5 provides for the embodiment of the invention.

Embodiment

Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.

For the advantage that makes technical solution of the present invention is clearer, below in conjunction with drawings and Examples the present invention is elaborated.

Shown in Fig. 1 (a), the method for the speech processes that the embodiment of the invention provides comprises:

101, receive the call voice signal.

Concrete, the voice signal when described call voice signal is conversed by mobile terminal device for the user.

102, after in a plurality of speech processing module that set in advance one is activated, according to described speech processing module described call voice signal is carried out noise reduction process in mobile terminal device.

Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.

Concrete, can be provided with a plurality of speech processing module in the described mobile terminal device, described a plurality of speech processing module can when mobile terminal device is produced, set in advance in described mobile terminal device.For example set in advance three kinds of selections " severe noise reduction ", " moderate noise reduction ", " slight noise reduction ", wherein the noise part can be effectively removed in " severe noise reduction " expression from Noisy Speech Signal, make the call voice signal sound comparatively clean, but might damage the call voice signal, thereby reduce the intelligibility of call voice, also may be with simultaneously and serve unpleasant single frequency tone set; May also can comprise the part noise in the call voice signal of " moderate noise reduction " expression after the noise reduction process, effective but the voice intelligibility may be than " severe noise reduction ", simultaneously single frequency tone set is less; And " slight noise reduction " is the noise in the slight reduction signal, but can itself damage do not arranged to former voice signal.For example, such as the design sketch of the described mobile terminal device of Fig. 1 (b).

In addition, described a plurality of speech processing module can also be that the demands of individuals according to the user arrange, and its concrete mode can be seen as among Fig. 2 (a), the embodiment shown in Figure 3, be repeated no more herein.

What deserves to be explained is that above-mentioned mobile terminal device can be the equipment that can carry out the mobile call business such as smart mobile phone etc.

The method of the speech processes that the embodiment of the invention provides, owing to be provided with a plurality of speech processing module in the mobile terminal device, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal, by described a plurality of speech processing module noise reduction process the effect of call voice signal have difference.And voice enhancement method of the prior art is comparatively single, general same mobile terminal device only has a kind of voice enhancement method, also comparatively single through the voice signal after the voice enhancing, different user is not necessarily identical for the impression of this voice signal like this, might cause the individual user comparatively to be sick of the single voice signal of this kind.Therefore, the present invention has diversity through the call voice signal behind the noise reduction, can adapt to varying environment and different user to the requirement of voice signal.

Shown in Fig. 2 (a), the method for the speech processes that further embodiment of this invention provides comprises:

201, receive voice signal to be measured.

Concrete, the signal in the recording file that described voice signal to be measured can be the frequent residing environment of user.For example, the user works in factory, and this user need to be general just in this factory with the environment that mobile terminal device is conversed.Therefore, after described mobile terminal device is recorded to described residing environment, will be with the signal in the recording file that generates as voice signal to be measured, but not only be confined to this.

202, described voice signal to be measured is input in a plurality of phonetic algorithm modules that set in advance in the mobile terminal device carries out noise reduction process, to form a plurality of the first effect voice signals.

Concrete, described phonetic algorithm comprises can comprise four large classes: the method that subtracts based on frequency spectrum, based on the method for sef-adapting filter, based on the method for statistical model and the method for subspace-based, each class has comprised again a variety of algorithms, and they have characteristics separately.Described phonetic algorithm module is based on the formed module of various algorithms in the above-mentioned four large class methods.

203, play respectively described the first effect voice signal.

204, behind the first preferred voice signal in determining described the first effect voice signal, phonetic algorithm module corresponding to the described first preferred voice signal is set to speech processing module.

Concrete, with described a plurality of the first effect speech play out, listen to and estimate by the user, thus the first preferred voice signal in definite a plurality of the first effect voice.Like this, represent that the described first preferred voice signal is more suitable for the user and listens to, therefore just can phonetic algorithm module corresponding to the described first preferred voice signal be set to speech processing module.

205, receive the call voice signal.

Concrete, the voice signal when described call voice signal is conversed by mobile terminal device for the user.

206, show speech processing module information and described activation sign.

Concrete, described speech processing module information is used for the outwards effect of the described speech processing module of prompting, but not only is confined to this.For example, described speech processing module information can be the prompting of the expression environment such as " factory ", " office ", " highway ".Described activation sign is corresponding one by one with described speech processing module information, is used for carrying out the selection of speech processing module.

For example, the design sketch of the mobile terminal device shown in Fig. 2 (b) can comprise the speech processing module information of multiple environment and activate sign.

207, after in a plurality of activation sign that sets in advance one is clicked, according to the corresponding speech processing module of described sign information described call voice signal is carried out noise reduction process in mobile terminal device.

What deserves to be explained is that mobile terminal device of the present invention can be the smart mobile phone of outfit single microphone or a plurality of microphones etc., but not only is confined to this.

The method of the speech processes that further embodiment of this invention provides, owing to be provided with a plurality of speech processing module in the mobile terminal device, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal, by described a plurality of speech processing module noise reduction process the effect of call voice signal have difference.And voice enhancement method of the prior art is comparatively single, general same mobile terminal device only has a kind of voice enhancement method, also comparatively single through the voice signal after the voice enhancing, different user is not necessarily identical for the impression of this voice signal like this, might cause the individual user comparatively to be sick of the single voice signal of this kind.Therefore, the present invention has diversity through the call voice signal behind the noise reduction, can adapt to varying environment and different user to the requirement of voice signal.

As shown in Figure 3, the method for the speech processes that yet another embodiment of the invention provides specifically comprises:

301, receive voice signal to be measured.

Concrete, the signal in the recording file that described voice signal to be measured can be the frequent residing environment of user.For example, the user works in factory, and this user need to be general just in this factory with the environment that mobile terminal device is conversed.Therefore, after described mobile terminal device is recorded to described residing environment, will be with the signal in the recording file that generates as voice signal to be measured, but not only be confined to this.

302, described voice signal to be measured is input in a plurality of phonetic algorithm modules that set in advance in the mobile terminal device carries out noise reduction process, to form a plurality of the first effect voice signals.

Concrete, described phonetic algorithm comprises can comprise four large classes: the method that subtracts based on frequency spectrum, based on the method for sef-adapting filter, based on the method for statistical model and the method for subspace-based, each class has comprised again a variety of algorithms, and they have characteristics separately.Described phonetic algorithm module is based on the formed module of various algorithms in the above-mentioned four large class methods.

303, play respectively described the first effect voice signal.

304, behind the first preferred voice signal in determining described the first effect voice signal, adjust the parameter of the parameter sets in phonetic algorithm module corresponding to the described first preferred voice signal.

Wherein, carry the key parameter of the described noise reduction capability of impact in the described parameter sets.

Concrete, described parameter sets comprises concerning each phonetic algorithm, determine the key parameter of its anti-acoustic capability, concrete can offer the user by cell phone manufacturer, for the user easy to use, such parameter is unsuitable too much, preferably one or two, for example for the method that subtracts based on frequency spectrum, in the theoretical algorithm to behind the signal subsection, the amplitude of multistage on average will affect the effect of noise reduction, mainly is to select how many segment signals to average meeting better, so just the signal hop count can be supplied user selection as an important parameter, can establish 2 sections, 3 sections, 4 sections, 5 sections these 4 selections; In addition, in noise reduction process, the reduction degree of the noise part of non-speech segment will have a strong impact on user's auditory perception, in general realize by going to reduce this part with a decay factor, this factor can not be too little can not be too large, so can arrange 0.1,0.2,0.3 0.4 several numerals are for user selection.For the method that subtracts based on frequency spectrum, just can offer above these two parameters of user for you to choose so, specifically can regulate to select the parameter sets of an optimization.

305, by the phonetic algorithm module after the parameter of adjusting described parameter sets described voice signal to be measured is carried out noise reduction process, to form a plurality of the second effect voice signals.

306, play respectively described the second effect voice signal.

307, behind the second preferred voice signal in determining described the second effect voice signal, according to the parameter of parameter sets corresponding to the described second preferred voice signal, dispose phonetic algorithm module corresponding to the described first preferred voice signal.

Concrete, with described a plurality of the second effect speech play out, listen to and estimate by the user, thus the second preferred voice signal in definite a plurality of the second effect voice.Like this, represent that the described second preferred voice signal is more suitable for the user and listens to, therefore can according to the parameter of parameter sets corresponding to the described second preferred voice signal, dispose phonetic algorithm module corresponding to the described first preferred voice signal.

308, phonetic algorithm module corresponding to the described first preferred voice signal is set to speech processing module.

309, receive the call voice signal.

Concrete, the voice signal when described call voice signal is conversed by mobile terminal device for the user.

310, show described speech processing module information and described activation sign.

Concrete, described speech processing module information is used for the outwards effect of the described speech processing module of prompting, but not only is confined to this.For example, described speech processing module information can be the prompting of the expression environment such as " factory ", " office ", " highway ".Described activation sign is corresponding one by one with described speech processing module information, is used for carrying out the selection of speech processing module.

311, after in a plurality of activation sign that sets in advance one is clicked, according to the corresponding speech processing module of described sign information described call voice signal is carried out noise reduction process in mobile terminal device.

What deserves to be explained is that mobile terminal device of the present invention can be the smart mobile phone of outfit single microphone or a plurality of microphones etc., but not only is confined to this.

The method of the speech processes that yet another embodiment of the invention provides, owing to be provided with a plurality of speech processing module in the mobile terminal device, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal, by described a plurality of speech processing module noise reduction process the effect of call voice signal have difference.And voice enhancement method of the prior art is comparatively single, general same mobile terminal device only has a kind of voice enhancement method, also comparatively single through the voice signal after the voice enhancing, different user is not necessarily identical for the impression of this voice signal like this, might cause the individual user comparatively to be sick of the single voice signal of this kind.Therefore, the present invention has diversity through the call voice signal behind the noise reduction, can adapt to varying environment and different user to the requirement of voice signal.

As shown in Figure 4, the device of the speech processes that the embodiment of the invention provides comprises:

Receiving element 41 is used for receiving the call voice signal.Its specific implementation repeats no more referring to shown in the step 101 among Fig. 1 (a) herein.

Noise reduction processing unit 42 after being used in a plurality of speech processing module that mobile terminal device sets in advance one and being activated, is carried out noise reduction process according to described speech processing module to described call voice signal.

Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.Its specific implementation repeats no more referring to shown in the step 102 among Fig. 1 (a) herein.

Further, as shown in Figure 5, described device also comprises:

Setting unit 43 is used at mobile terminal device a plurality of speech processing module being set.

Further, as shown in Figure 5, described receiving element 41 also is used for receiving voice signal to be measured.

Described noise reduction processing unit 42 also is used for described voice signal to be measured is input in a plurality of phonetic algorithm modules that mobile terminal device sets in advance and carries out noise reduction process, to form a plurality of the first effect voice signals.

As shown in Figure 5, described device also comprises:

Broadcast unit 44 is used for playing respectively described the first effect voice signal.

Described setting unit 43, concrete being used for behind the first preferred voice signal of determining described the first effect voice signal, phonetic algorithm module corresponding to the described first preferred voice signal is set to speech processing module.

Further, as shown in Figure 5, described device also comprises:

Adjustment unit 45 is for the parameter of the parameter sets of adjusting phonetic algorithm module corresponding to the described first preferred voice signal.

Wherein, carry the key parameter of the described noise reduction capability of impact in the described parameter sets.

Described noise reduction processing unit 42 also is used for by the phonetic algorithm module after the parameter of adjusting described parameter sets described voice signal to be measured being carried out noise reduction process, to form a plurality of the second effect voice signals.

Described broadcast unit 44 also is used for playing respectively described the second effect voice signal.

Described setting unit 43 also is used for according to the parameter of parameter sets corresponding to the described second preferred voice signal, disposing phonetic algorithm module corresponding to the described first preferred voice signal behind the second preferred voice signal of determining described the second effect voice signal.

Concrete, as shown in Figure 5, described speech processing module carries and activates sign and sign information.

Described device also comprises:

Display unit 46 is used for showing described speech processing module information and described activation sign.

Described noise reduction processing unit 42 specifically is used for:

After in a plurality of activation sign that sets in advance one is clicked, according to the corresponding speech processing module of described sign information described call voice signal is carried out noise reduction process in mobile terminal device.

The device of the speech processes that the embodiment of the invention provides, owing to be provided with a plurality of speech processing module in the mobile terminal device, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal, by described a plurality of speech processing module noise reduction process the effect of call voice signal have difference.And voice enhancement method of the prior art is comparatively single, general same mobile terminal device only has a kind of voice enhancement method, also comparatively single through the voice signal after the voice enhancing, different user is not necessarily identical for the impression of this voice signal like this, might cause the individual user comparatively to be sick of the single voice signal of this kind.Therefore, the present invention has diversity through the call voice signal behind the noise reduction, can adapt to varying environment and different user to the requirement of voice signal.

The above; be the specific embodiment of the present invention only, but protection scope of the present invention is not limited to this, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion by described protection domain with claim.

Claims (10)

1. the method for a speech processes is characterized in that, comprising:
Receive the call voice signal;
After in a plurality of speech processing module that set in advance one is activated, according to described speech processing module described call voice signal is carried out noise reduction process in mobile terminal device; Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.
2. the method for speech processes according to claim 1 is characterized in that, before obtaining the call voice signal, comprising:
At mobile terminal device a plurality of speech processing module are set.
3. the method for speech processes according to claim 2 is characterized in that, describedly at mobile terminal device a plurality of speech processing module is set, and comprising:
Receive voice signal to be measured;
Described voice signal to be measured is input in a plurality of phonetic algorithm modules that set in advance in the mobile terminal device carries out noise reduction process, to form a plurality of the first effect voice signals;
Play respectively described the first effect voice signal;
Behind the first preferred voice signal in determining described the first effect voice signal, phonetic algorithm module corresponding to the described first preferred voice signal is set to speech processing module.
4. the method for speech processes according to claim 3 is characterized in that, before phonetic algorithm module corresponding to the described first preferred voice signal was set to speech processing module, described method comprised:
Adjust the parameter of the parameter sets in phonetic algorithm module corresponding to the described first preferred voice signal; Carry the key parameter of the described noise reduction capability of impact in the described parameter sets;
By the phonetic algorithm module after the parameter of adjusting described parameter sets described voice signal to be measured is carried out noise reduction process, to form a plurality of the second effect voice signals;
Play respectively described the second effect voice signal;
Behind the second preferred voice signal in determining described the second effect voice signal, according to the parameter of parameter sets corresponding to the described second preferred voice signal, dispose phonetic algorithm module corresponding to the described first preferred voice signal.
5. each described method is characterized in that according to claim 1-4, and described speech processing module carries and activates sign and sign information;
Before in a plurality of speech processing module that set in advance in described mobile terminal device one is activated, comprising:
Show described speech processing module information and described activation sign;
After in the described a plurality of speech processing module that set in advance one is activated, according to described speech processing module described call voice signal is carried out noise reduction process in mobile terminal device, comprising:
After in a plurality of activation sign that sets in advance one is clicked, according to the corresponding speech processing module of described sign information described call voice signal is carried out noise reduction process in mobile terminal device.
6. the device of a speech processes is characterized in that, comprising:
Receiving element is used for receiving the call voice signal;
Noise reduction processing unit after being used in a plurality of speech processing module that mobile terminal device sets in advance one and being activated, is carried out noise reduction process according to described speech processing module to described call voice signal; Wherein, described a plurality of speech processing module is not identical to the noise reduction capability of described call voice signal.
7. the device of speech processes according to claim 6 is characterized in that, described device also comprises:
Setting unit is used at mobile terminal device a plurality of speech processing module being set.
8. the device of speech processes according to claim 7 is characterized in that, described receiving element also is used for receiving voice signal to be measured;
Described noise reduction processing unit also is used for described voice signal to be measured is input in a plurality of phonetic algorithm modules that mobile terminal device sets in advance and carries out noise reduction process, to form a plurality of the first effect voice signals;
Described device also comprises:
Broadcast unit is used for playing respectively described the first effect voice signal;
Described setting unit, concrete being used for behind the first preferred voice signal of determining described the first effect voice signal, phonetic algorithm module corresponding to the described first preferred voice signal is set to speech processing module.
9. the device of speech processes according to claim 8 is characterized in that, described device also comprises:
Adjustment unit is for the parameter of the parameter sets of adjusting phonetic algorithm module corresponding to the described first preferred voice signal; Carry the key parameter of the described noise reduction capability of impact in the described parameter sets;
Described noise reduction processing unit also is used for by the phonetic algorithm module after the parameter of adjusting described parameter sets described voice signal to be measured being carried out noise reduction process, to form a plurality of the second effect voice signals;
Described broadcast unit also is used for playing respectively described the second effect voice signal;
Described setting unit also is used for according to the parameter of parameter sets corresponding to the described second preferred voice signal, disposing phonetic algorithm module corresponding to the described first preferred voice signal behind the second preferred voice signal of determining described the second effect voice signal.
10. each described device is characterized in that according to claim 6-9, and described speech processing module carries and activates sign and sign information;
Described device also comprises:
Display unit is used for showing described speech processing module information and described activation sign;
Described noise reduction processing unit specifically is used for:
After in a plurality of activation sign that sets in advance one is clicked, according to the corresponding speech processing module of described sign information described call voice signal is carried out noise reduction process in mobile terminal device.
CN201210593360.8A 2012-12-31 2012-12-31 The method of speech processes and device CN103077725B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210593360.8A CN103077725B (en) 2012-12-31 2012-12-31 The method of speech processes and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210593360.8A CN103077725B (en) 2012-12-31 2012-12-31 The method of speech processes and device

Publications (2)

Publication Number Publication Date
CN103077725A true CN103077725A (en) 2013-05-01
CN103077725B CN103077725B (en) 2015-12-23

Family

ID=48154232

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210593360.8A CN103077725B (en) 2012-12-31 2012-12-31 The method of speech processes and device

Country Status (1)

Country Link
CN (1) CN103077725B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103456305A (en) * 2013-09-16 2013-12-18 东莞宇龙通信科技有限公司 Terminal and speech processing method based on multiple sound collecting units
CN104217728A (en) * 2014-09-09 2014-12-17 联想(北京)有限公司 Audio processing method and electronic device
CN106375584A (en) * 2016-09-13 2017-02-01 珠海市魅族科技有限公司 Voice signal control method and device
CN108766454A (en) * 2018-06-28 2018-11-06 浙江飞歌电子科技有限公司 A kind of voice noise suppressing method and device

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101583996A (en) * 2006-12-30 2009-11-18 摩托罗拉公司 A method and noise suppression circuit incorporating a plurality of noise suppression techniques
CN101661753A (en) * 2008-08-27 2010-03-03 富士通株式会社 Noise suppressing device, mobile phone and noise suppressing method
CN101727912A (en) * 2008-10-24 2010-06-09 雅马哈株式会社 Noise suppression device and noise suppression method
CN102088521A (en) * 2009-12-07 2011-06-08 宏达国际电子股份有限公司 Method for improving communication quality based on ambient noise sensing and electronic device
WO2012153294A2 (en) * 2011-05-11 2012-11-15 Silentium Ltd. Device, system and method of noise control

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101583996A (en) * 2006-12-30 2009-11-18 摩托罗拉公司 A method and noise suppression circuit incorporating a plurality of noise suppression techniques
CN101661753A (en) * 2008-08-27 2010-03-03 富士通株式会社 Noise suppressing device, mobile phone and noise suppressing method
CN101727912A (en) * 2008-10-24 2010-06-09 雅马哈株式会社 Noise suppression device and noise suppression method
CN102088521A (en) * 2009-12-07 2011-06-08 宏达国际电子股份有限公司 Method for improving communication quality based on ambient noise sensing and electronic device
WO2012153294A2 (en) * 2011-05-11 2012-11-15 Silentium Ltd. Device, system and method of noise control

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103456305A (en) * 2013-09-16 2013-12-18 东莞宇龙通信科技有限公司 Terminal and speech processing method based on multiple sound collecting units
CN103456305B (en) * 2013-09-16 2016-03-09 东莞宇龙通信科技有限公司 Terminal and the method for speech processing based on multiple sound collection unit
CN104217728A (en) * 2014-09-09 2014-12-17 联想(北京)有限公司 Audio processing method and electronic device
CN106375584A (en) * 2016-09-13 2017-02-01 珠海市魅族科技有限公司 Voice signal control method and device
CN108766454A (en) * 2018-06-28 2018-11-06 浙江飞歌电子科技有限公司 A kind of voice noise suppressing method and device

Also Published As

Publication number Publication date
CN103077725B (en) 2015-12-23

Similar Documents

Publication Publication Date Title
CN104954555B (en) A kind of volume adjusting method and system
CN106416290B (en) The system and method for the performance of audio-frequency transducer is improved based on the detection of energy converter state
US9716939B2 (en) System and method for user controllable auditory environment customization
CN103841491B (en) Adaptable System for managing multiple microphones and loud speaker
JP5007442B2 (en) System and method using level differences between microphones for speech improvement
US9392381B1 (en) Hearing aid attached to mobile electronic device
EP1738567B1 (en) Glasses frame with integrated acoustic communication system for communication with a mobile phone and respective method
JP6285367B2 (en) Method and apparatus for wind noise detection
KR100800725B1 (en) Automatic volume controlling method for mobile telephony audio player and therefor apparatus
US8976988B2 (en) Audio processing device, system, use and method
EP2352312B1 (en) A method for dynamic suppression of surrounding acoustic noise when listening to electrical inputs
US7243060B2 (en) Single channel sound separation
EP1912474B1 (en) Method for operating a hearing aid and hearing aid
US9508335B2 (en) Active noise control and customized audio system
CN103259898B (en) The method of Automatic adjusument frequency response and terminal
CN104685563B (en) The audio signal shaping of playback in making an uproar for noisy environment
AU2008361614B2 (en) Method for sound processing in a hearing aid and a hearing aid
EP2833645A1 (en) Wired and wireless earset using ear-insertion-type microphone
CN101502089B (en) Method for carrying out an audio conference, audio conference device, and method for switching between encoders
EP1298959A2 (en) Hearing aid with parasitic signal control
EP2603018B1 (en) Hearing aid with speaking activity recognition and method for operating a hearing aid
CN104883437B (en) The method and system of speech analysis adjustment reminding sound volume based on environment
CN100392723C (en) System and method for speech processing using independent component analysis under stability restraints
CN105229737A (en) Noise cancelling microphone device
US20060053002A1 (en) System and method for speech processing using independent component analysis under stability restraints

Legal Events

Date Code Title Description
PB01 Publication
C06 Publication
SE01 Entry into force of request for substantive examination
C10 Entry into substantive examination
GR01 Patent grant
C14 Grant of patent or utility model