CN110164425A - A kind of noise-reduction method, device and the equipment that can realize noise reduction - Google Patents
A kind of noise-reduction method, device and the equipment that can realize noise reduction Download PDFInfo
- Publication number
- CN110164425A CN110164425A CN201910457370.0A CN201910457370A CN110164425A CN 110164425 A CN110164425 A CN 110164425A CN 201910457370 A CN201910457370 A CN 201910457370A CN 110164425 A CN110164425 A CN 110164425A
- Authority
- CN
- China
- Prior art keywords
- noise
- signal
- sound
- noise reduction
- external
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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 OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Abstract
The invention discloses a kind of noise-reduction method, device and the equipment that can realize noise reduction, this method comprises: obtaining the audio input signal that target device receives；Using the external noise signals of the target device, noise reduction process is carried out to the audio input signal, obtains external object voice signal；Using the internal noise signal of the target device, noise reduction process is carried out to the external object voice signal, obtains the target sound signal.The present invention can not only avoid influence of the device external noise to accuracy of speech recognition, it is thus also avoided that influence of the equipment internal noise to equipment accuracy of speech recognition improves the effect of noise reduction process and the intelligence of equipment.
Description
Technical field
This application involves sound processing techniques field more particularly to a kind of noise-reduction method, device and it can realize setting for noise reduction
It is standby.
Background technique
With the development of artificial intelligence technology, more and more intelligent sound equipment occur in people's lives.In order to
The intelligence for guaranteeing the accuracy to speech recognition, improving equipment, smart machine need to carry out at noise reduction the voice received
Reason.However, existing smart machine still has the bad problem of noise reduction effect, the intelligence of equipment is influenced.
Summary of the invention
In view of this, the embodiment of the present application provides a kind of noise-reduction method, device and the equipment that can realize noise reduction, can solve
The certainly bad problem of noise reduction effect in the prior art.
The embodiment of the present application first aspect provides a kind of noise-reduction method, comprising:
Obtain the audio input signal that target device receives；
Using the external noise signals of the target device, noise reduction process is carried out to the audio input signal, is obtained outer
Portion's target sound signal；
Using the internal noise signal of the target device, noise reduction process is carried out to the external object voice signal, is obtained
To the target sound signal.
Optionally, the audio input signal for obtaining target device and receiving, specifically includes:
Obtain the initial voice signal of target device described in external input；
Noise reduction process is carried out to the initial voice signal, obtains the audio input signal.
Optionally, the noise reduction process is carried out using fixed beam form or sef-adapting filter.
Optionally, the internal noise signal obtains module via the first sound being arranged inside the target device and obtains
?；First sound obtains the external sound insulation of module and the target device.
Optionally, the target device outer cover is equipped with shell；The shell sound insulation.
The embodiment of the present application second aspect provides a kind of denoising device, comprising: signal acquiring unit, the first noise reduction process
Unit and the second noise reduction processing unit；
The signal acquiring unit, the audio input signal received for obtaining target device；
First noise reduction processing unit, it is defeated to the sound for the external noise signals using the target device
Enter signal and carry out noise reduction process, obtains external object voice signal；
Second noise reduction processing unit, for the internal noise signal using the target device, to the external mesh
It marks voice signal and carries out noise reduction process, obtain the target sound signal.
The embodiment of the present application third aspect provides a kind of equipment of achievable noise reduction, comprising: the first sound acquisition module,
Second sound obtains module, shell and noise processed module；
First sound obtains the inside that the shell is arranged in module, and first sound obtains module and sets with described
Standby external sound insulation；First sound obtains module, for obtaining the internal noise signal inside the equipment, and will be described
Internal noise signal is sent to the noise processed module；
The second sound obtains module, for obtaining the audio input signal of the device external, and by the sound
Input signal is sent to the noise processed module；It is also used to obtain the external noise signals of the device external, and will be described
External noise signals are sent to the noise processed module；
The noise processed module carries out noise reduction to the audio input signal for utilizing the external noise signals
Processing, obtains external object voice signal；The internal noise signal is recycled, the external object voice signal is dropped
It makes an uproar processing, obtains the target sound signal.
Optionally, the shell sound insulation.
Optionally, the second sound obtains module, is specifically used for receiving externally input initial voice signal, and to institute
It states initial voice signal and carries out noise reduction process, obtain the audio input signal.
Optionally, the noise processed module carries out noise reduction process using fixed beam form or sef-adapting filter.
Compared with prior art, the application has at least the following advantages:
In the embodiment of the present application, the audio input signal that target device receives is obtained first, and recycling is obtained ahead of time
Target device external noise signals, to audio input signal carry out noise reduction process, obtain outer target sound signal.Then, sharp
With the internal noise signal of target device, external target sound signal carries out noise reduction process, obtains target sound signal.The application
Embodiment can not only avoid influence of the device external noise to accuracy of speech recognition, it is thus also avoided that equipment internal noise is to setting
The influence of standby accuracy of speech recognition, improves the effect of noise reduction process and the intelligence of equipment.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of flow diagram of noise-reduction method provided by the embodiments of the present application；
Fig. 2 is a kind of structural schematic diagram of denoising device provided by the embodiments of the present application；
Fig. 3 is a kind of structural schematic diagram of the equipment of achievable noise reduction provided by the embodiments of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
It should be appreciated that in this application, " at least one (item) " refers to one or more, and " multiple " refer to two or two
More than a."and/or" indicates may exist three kinds of relationships, for example, " A and/or B " for describing the incidence relation of affiliated partner
It can indicate: only exist A, only exist B and exist simultaneously tri- kinds of situations of A and B, wherein A, B can be odd number or plural number.Word
Symbol "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or"." at least one of following (a) " or its similar expression, refers to
Any combination in these, any combination including individual event (a) or complex item (a).At least one of for example, in a, b or c
(a) can indicate: a, b, c, " a and b ", " a and c ", " b and c ", or " a and b and c ", and wherein a, b, c can be individually, can also
To be multiple.
Smart machine generally can carry out noise reduction process to the voice of input when realizing speech recognition, to guarantee that voice is known
Other accuracy.However, present inventor has found under study for action, when smart machine internal noise is larger, inside equipment
Noise is larger to the interference of speech recognition, and existing smart machine still has the bad problem of noise reduction effect, not can guarantee language
The accuracy of sound identification, causes the intelligence degree of equipment low.
For this purpose, the embodiment of the present application provides a kind of noise-reduction method, device and the equipment that can realize noise reduction, can not only disappear
Except the noise of device external, the inside that module obtains inside equipment can also be obtained using the second sound being arranged inside equipment and made an uproar
Acoustical signal improves the accuracy of effect and speech recognition that noise is eliminated, guarantees the height of equipment to eliminate the noise inside equipment
It is intelligent.
Based on above-mentioned thought, in order to make the above objects, features, and advantages of the present application more apparent, below with reference to
Attached drawing is described in detail the specific embodiment of the application.
Referring to Fig. 1, which is a kind of flow diagram of noise-reduction method provided by the embodiments of the present application.
A kind of noise-reduction method provided by the embodiments of the present application, comprising:
S101: the audio input signal that target device receives is obtained.
It should be noted that target device specifically can be any one equipment that can carry out voice input, as recording is set
Equipment that is standby, having speech recognition and can voice control equipment etc., including but not limited to recording pen, video camera, smart phone,
Intelligent sound, smart home device (such as sweeping robot, air purifier, air-conditioning, fan), intelligent translation machine etc., herein
Without limiting.
In the embodiment of the present application, the audio input signal received not only includes external noise signals, further includes expectation
The target sound signal (such as phonetic order of user's typing) of identification, the embodiment of the present application to the form of target sound signal and
The acquisition pattern of audio input signal is without limiting.
As an example, audio input signal can use the of setting on the target device or outside target device
Two sound obtain module and obtain.In the specific implementation, second sound obtain module may include one or more radio equipments (such as
The microphone etc. of arbitrary structures).In practical applications, can according to the actual situation and need, to second sound obtain module institute
Including radio equipment position on the target device and arrangement mode specifically set.For example, second sound obtains module
It can be external microphone, be also possible to the microphone being arranged on target device shell, second sound obtains module and may be used also
To include multiple microphones, etc. to be arranged in a manner of on target device shell, will not enumerate here.
It, can be to practical reception in order to improve the effect of noise reduction in some possible implementations of the embodiment of the present application
The voice signal (i.e. initial voice signal) arrived carries out pre-noise reduction.Then, step S101 can specifically include:
S1011: the initial voice signal of external input target device is obtained.
S1012: noise reduction process is carried out to initial voice signal, obtains audio input signal.
It is understood that initial voice signal can be the original sound signal that target device directly receives.In reality
In the application of border, noise reduction can be carried out to initial voice signal using any one noise reduction process algorithm, such as the noise reduction process can
It is carried out in the form of using fixed beam.So-called fixed beam formation refers in beam forming process that filter weights immobilize.
Once the geometry of microphone array, target direction determine, beam modes characteristic will also be determined.This method have it is simple,
The low advantage of operand.The mode of noise reduction process is described in detail in citing below, does not repeat first here.
S102: using the external noise signals of target device, noise reduction process is carried out to audio input signal, obtains external mesh
Mark voice signal.
In the embodiment of the present application, external noise signals can be the interference signal outside target device, such as ambient noise
Deng.Noise reduction process is carried out using external noise signals as the reference signal for eliminating target device external noise, target can be eliminated
Influence of the device external noise to voice input or recognition accuracy.It is understood that external noise signals also can use
Second sound obtains module and obtains.For example, second sound obtains module and receives when user is not to target device typing voice
Voice signal can be used as external noise signals.
In practical applications, it can use any one noise reduction algorithm and carry out noise reduction process, such as fixed beam or adaptive
It should wait, here without limiting.As an example, noise processed module 140 can use lowest mean square (least mean
Square, LMS) sef-adapting filter, normalization minimum mean-square (normalized least mean square, NLMS) be adaptive
Filter, recursion lowest mean square (recursive least square, RLS) sef-adapting filter etc. is answered to carry out at noise reduction
Reason.
Wherein, the principle of LMS sef-adapting filter is: utilizing the acquired filter parameter of eve, automatic adjustment is worked as
Pre-filter parameter, so that input signal sequence x (n) and desired output signal d (n) are approached, it is unknown to adapt to signal and noise
Or random variation statistical property, to realize optimal filter.
The error signal e (n) that input signal sequence is x (n) and desired output signal be d (n) such as following formula (1),
In formula, ωiFor weight coefficient, n ∈ [1, M].
The essence of LMS algorithm is exactly to find optimal weight coefficient, and by a series of derivations, following formula (2) finally can be obtained,
ωk(n)=ωk(n-1)+μe(n)x(n) (2)
In formula, μ is convergence factor, and the size of μ decides the stability and convergence rate of system.Other sef-adapting filters
Principle it is similar with LMS, difference be only that so that the standard approached of input signal sequence x (n) and desired output signal d (n) not
Together, it no longer repeats one by one here.
S103: using the internal noise signal of target device, noise reduction process is carried out to external target sound signal, obtains mesh
Mark voice signal.
In the embodiment of the present application, internal noise signal can be the interference signal inside target device, such as target device
Running noises etc..Internal noise signal is carried out internal noise signal as the reference signal for eliminating target device internal noise
Noise reduction can eliminate influence of the target device internal noise (such as motor operation noise) to voice input or identification accuracy.
Since the reference signal first with external noise signals as noise reduction carries out noise reduction, the influence of external noise, then benefit are reduced
The reference signal for using internal noise signal as noise reduction carries out secondary noise reduction, and reduces the influence of internal noise, improves drop
The effect and accuracy made an uproar, ensure that the intelligence of target device.
In practical applications, internal noise signal can use the acquisition of any one radio equipment.In the embodiment of the present application
In some possible implementations, internal noise signal can obtain module via the first sound being arranged inside target device and obtain
, in order to guarantee the accuracy of noise reduction, which obtains the external sound insulation of module and target device.As an example,
Sound insulation shell can be set by the shell being arranged outside target device, alternatively, the enclosure interior in target device is added to first
Sound obtains the noise insulation mechanism etc. of module, so that the first sound obtains module and only receives the voice signal inside target device
(i.e. internal noise signal).
In the specific implementation, it may include at least one radio equipment (wheat of such as arbitrary structures that the first sound, which obtains module,
Gram wind etc.), at least one radio equipment can be according to practical feelings in the position of target device enclosure interior and arrangement mode
Condition is specifically set, such as it may include multiple to surround the Mike being arranged in inside target device that the first sound, which obtains module,
Wind also will not enumerate without limiting here.
It is understood that it is similar with step S102, in practical applications, it is external to can use any one noise reduction algorithm
Portion's target sound signal carries out noise reduction process, such as fixed beam or adaptive etc., here without limiting.
In the embodiment of the present application, the audio input signal that target device receives is obtained first, and recycling is obtained ahead of time
Target device external noise signals, to audio input signal carry out noise reduction process, obtain outer target sound signal.Then, sharp
With the internal noise signal of target device, external target sound signal carries out noise reduction process, obtains target sound signal.The application
Embodiment can not only avoid influence of the device external noise to accuracy of speech recognition, it is thus also avoided that equipment internal noise is to setting
The influence of standby accuracy of speech recognition, improves the effect of noise reduction process and the intelligence of equipment.
The noise-reduction method provided based on the above embodiment, the embodiment of the present application also provides a kind of denoising devices.
Referring to fig. 2, which is a kind of structural schematic diagram of denoising device provided by the embodiments of the present application.
A kind of denoising device provided by the embodiments of the present application, comprising: signal acquiring unit 201, the first noise reduction processing unit
202 and second noise reduction processing unit 203；
Signal acquiring unit 201, the audio input signal received for obtaining target device.
First noise reduction processing unit 202 carries out audio input signal for the external noise signals using target device
Noise reduction process obtains external object voice signal.
Second noise reduction processing unit 203, for the internal noise signal using target device, to external target sound signal
Noise reduction process is carried out, target sound signal is obtained.
In some possible implementations of the embodiment of the present application, signal acquisition list 201 may include:
Subelement is obtained, for obtaining the initial voice signal of external input target device；
Noise reduction subelement carries out noise reduction process for initial voice signal, obtains audio input signal.
In the embodiment of the present application, the audio input signal that target device receives is obtained first, and recycling is obtained ahead of time
Target device external noise signals, to audio input signal carry out noise reduction process, obtain outer target sound signal.Then, sharp
With the internal noise signal of target device, external target sound signal carries out noise reduction process, obtains target sound signal.The application
Embodiment can not only avoid influence of the device external noise to accuracy of speech recognition, it is thus also avoided that equipment internal noise is to setting
The influence of standby accuracy of speech recognition, improves the effect of noise reduction process and the intelligence of equipment.
The noise-reduction method and device provided based on the above embodiment, the embodiment of the present application also provides a kind of achievable noise reductions
Equipment.
Referring to Fig. 3, which is a kind of structural schematic diagram of the equipment of achievable noise reduction provided by the embodiments of the present application.
The equipment of a kind of achievable noise reduction provided by the embodiments of the present application, comprising: the first sound obtains module 301, second
Sound obtains module 302, shell 303 and noise processed module 304；
First sound obtains the inside that shell 303 is arranged in module 301, and the first sound obtains module 301 and this and can be achieved
The external sound insulation of the equipment of noise reduction；
First sound obtains module 301, for obtaining the internal noise signal inside the equipment that noise reduction can be achieved, and will
Internal noise signal is sent to noise processed module 304；
Second sound obtains module 302, for obtaining the audio input signal of the device external that noise reduction can be achieved, and will
Audio input signal is sent to noise processed module 304；It is also used to obtain the external noise of the device external that noise reduction can be achieved
Signal, and external noise signals are sent to noise processed module 304；
Noise processed module 304, the external noise signals of the equipment for noise reduction to can be achieved using this, believes voice input
Number carry out noise reduction process, obtain external object voice signal；Recycle this that the internal noise signal of the equipment of noise reduction can be achieved, it is right
External object voice signal carries out noise reduction process, obtains target sound signal.
As an example, noise processed module is carried out at noise reduction using fixed beam form or sef-adapting filter
Reason.
It is understood that the first sound obtains module 301 and second sound obtains module 302 and above method embodiment
Described in the first sound obtain module and second sound and obtain that module is similar, and illustrating can refer in above method embodiment
Related content, which is not described herein again.Noise processed module 304 is for executing in noise-reduction method provided by the above embodiment
Any one, be specifically referred to related description.
In practical applications, noise processed module 304 can specifically include memory and processor, and wherein memory is used for
Program code is stored, and the program code is sent to processor, which realizes as above for executing the program code
Any one in the noise-reduction method of embodiment offer is provided.
It, can be by order to further increase the effect of noise reduction in some possible implementations of the embodiment of the present application
One sound obtains module 301 and is set as that the external voice high isolation of the equipment of noise reduction can be achieved with this, such as sets shell 303 to
Sound insulation shell, alternatively, the noise insulation mechanism etc. for obtaining module 301 to the first sound is added in the inside of shell 303, so that the first sound
Sound obtains module 301 and only receives the voice signal (i.e. internal noise signal) inside equipment.
In some possible implementations of the embodiment of the present application, in order to improve the effect of noise reduction, second sound obtains mould
Block 302 is specifically used for receiving externally input initial voice signal, and carries out noise reduction process to initial voice signal, obtains sound
Sound input signal.Specific noise-reduction method can be chosen according to actual needs, here without limiting.
In the embodiment of the present application, the enclosure interior of equipment is provided with the first sound and obtains module, the first sound obtains
The external sound insulation of module and equipment then obtains the internal noise signal inside module acquisition equipment, and benefit using the first sound
The external noise signals and audio input signal that module obtains device external, the voice input that will acquire are obtained with second sound
Signal, external noise signals and internal noise signal are sent to noise processed module, so that noise processed module is made an uproar according to outside
Acoustical signal and internal noise signal carry out noise reduction process to audio input signal and obtain target sound signal, avoid in equipment
Influence of portion's noise to equipment accuracy of speech recognition, improves the effect of noise reduction process and the intelligence of equipment.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment emphasis is said
Bright is the difference from other embodiments, and the same or similar parts in each embodiment may refer to each other.For reality
For applying system or device disclosed in example, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, it is related
Place is referring to method part illustration.
It should also be noted that, herein, relational terms such as first and second and the like are used merely to one
Entity or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The above is only the preferred embodiment of the application, not makes any form of restriction to the application.Though
Right the application has been disclosed in a preferred embodiment above, however is not limited to the application.It is any to be familiar with those skilled in the art
Member, in the case where not departing from technical scheme ambit, all using the methods and technical content of the disclosure above to the application
Technical solution makes many possible changes and modifications or equivalent example modified to equivalent change.Therefore, it is all without departing from
The content of technical scheme, any simple modification made to the above embodiment of the technical spirit of foundation the application are equal
Variation and modification, still fall within technical scheme protection in the range of.
Claims (10)
1. a kind of noise-reduction method, which is characterized in that the described method includes:
Obtain the audio input signal that target device receives；
Using the external noise signals of the target device, noise reduction process is carried out to the audio input signal, obtains external mesh
Mark voice signal；
Using the internal noise signal of the target device, noise reduction process is carried out to the external object voice signal, obtains institute
State target sound signal.
2. the method according to claim 1, wherein the voice input letter for obtaining target device and receiving
Number, it specifically includes:
Obtain the initial voice signal of target device described in external input；
Noise reduction process is carried out to the initial voice signal, obtains the audio input signal.
3. method according to claim 1 or 2, which is characterized in that the noise reduction process using fixed beam form or
Sef-adapting filter carries out.
4. method according to claim 1 or 2, which is characterized in that the internal noise signal is via the target device
First sound of inside setting obtains module and obtains；First sound obtains the external sound insulation of module and the target device.
5. according to the method described in claim 4, it is characterized in that, the target device outer cover is equipped with shell；The shell
Sound insulation.
6. a kind of denoising device, which is characterized in that described device includes: signal acquiring unit, the first noise reduction processing unit and
Two noise reduction processing units；
The signal acquiring unit, the audio input signal received for obtaining target device；
First noise reduction processing unit believes the voice input for the external noise signals using the target device
Number carry out noise reduction process, obtain external object voice signal；
Second noise reduction processing unit, for the internal noise signal using the target device, to the external object sound
Sound signal carries out noise reduction process, obtains the target sound signal.
7. a kind of equipment of achievable noise reduction characterized by comprising the first sound obtains module, second sound obtains module,
Shell and noise processed module；
First sound obtains the inside that the shell is arranged in module, and first sound obtains module and the equipment
External sound insulation；First sound obtains module, for obtaining the internal noise signal inside the equipment, and by the inside
Noise signal is sent to the noise processed module；
The second sound obtains module, for obtaining the audio input signal of the device external, and by the voice input
Signal is sent to the noise processed module；It is also used to obtain the external noise signals of the device external, and by the outside
Noise signal is sent to the noise processed module；
The noise processed module carries out noise reduction process to the audio input signal for utilizing the external noise signals,
Obtain external object voice signal；The internal noise signal is recycled, the external object voice signal is carried out at noise reduction
Reason, obtains the target sound signal.
8. equipment according to claim 7, which is characterized in that the shell sound insulation.
9. equipment according to claim 7, which is characterized in that the second sound obtains module, is specifically used for receiving outer
The initial voice signal of portion's input, and noise reduction process is carried out to the initial voice signal, obtain the audio input signal.
10. equipment according to any one of claims 7 to 9, which is characterized in that the noise processed module utilizes fixed wave
Beam form or sef-adapting filter carry out noise reduction process.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910457370.0A CN110164425A (en) | 2019-05-29 | 2019-05-29 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
| PCT/CN2019/129930 WO2020238203A1 (en) | 2019-05-29 | 2019-12-30 | Noise reduction method, noise reduction apparatus, and device capable of reducing noise |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910457370.0A CN110164425A (en) | 2019-05-29 | 2019-05-29 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110164425A true CN110164425A (en) | 2019-08-23 |
Family
ID=67629691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910457370.0A Pending CN110164425A (en) | 2019-05-29 | 2019-05-29 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110164425A (en) |
| WO (1) | WO2020238203A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111341304A (en) * | 2020-02-28 | 2020-06-26 | 广州国音智能科技有限公司 | Method, device and equipment for training speech characteristics of speaker based on GAN |
| WO2020238203A1 (en) * | 2019-05-29 | 2020-12-03 | 北京声智科技有限公司 | Noise reduction method, noise reduction apparatus, and device capable of reducing noise |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120259629A1 (en) * | 2011-04-11 | 2012-10-11 | Kabushiki Kaisha Audio-Technica | Noise reduction communication device |
| CN103959814A (en) * | 2011-12-08 | 2014-07-30 | 索尼公司 | Earhole attachment-type sound pickup device, signal processing device, and sound pickup method |
| CN103959813A (en) * | 2011-12-08 | 2014-07-30 | 索尼公司 | Earhole attachment-type sound pickup device, signal processing device, and sound pickup method |
| CN104424953A (en) * | 2013-09-11 | 2015-03-18 | 华为技术有限公司 | Speech signal processing method and device |
| CN104952458A (en) * | 2015-06-09 | 2015-09-30 | 广州广电运通金融电子股份有限公司 | Noise suppression method, device and system |
| US9401158B1 (en) * | 2015-09-14 | 2016-07-26 | Knowles Electronics, Llc | Microphone signal fusion |
| CN206713019U (en) * | 2017-02-10 | 2017-12-05 | 万魔声学科技有限公司 | Active noise reducing device and earphone |
| CN107452368A (en) * | 2017-08-14 | 2017-12-08 | 海尔优家智能科技（北京）有限公司 | The noise-reduction method and device of a kind of home appliance |
| CN108088064A (en) * | 2018-01-15 | 2018-05-29 | 青岛理工大学 | Arranged on ventilation nozzle and it is capable of active noise reducing device and the control method that acoustics interacts |
| CN109243453A (en) * | 2018-10-29 | 2019-01-18 | 珠海格力电器股份有限公司 | The processing method and processing device of voice messaging, storage medium, electronic device |
| CN109478409A (en) * | 2016-07-11 | 2019-03-15 | 微软技术许可有限责任公司 | For calculating the microphone noise suppressed of equipment |
| CN109599107A (en) * | 2018-12-07 | 2019-04-09 | 珠海格力电器股份有限公司 | A kind of method, apparatus and computer storage medium of speech recognition |
| CN208905198U (en) * | 2018-09-30 | 2019-05-24 | 科大讯飞股份有限公司 | Electronic equipment with full isolation Dolby circuit |
| CN210667779U (en) * | 2019-05-29 | 2020-06-02 | 北京声智科技有限公司 | Equipment capable of reducing noise |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7215786B2 (en) * | 2000-06-09 | 2007-05-08 | Japan Science And Technology Agency | Robot acoustic device and robot acoustic system |
| CN106388700B (en) * | 2016-06-06 | 2020-07-28 | 北京小米移动软件有限公司 | Active noise reduction device for automatic cleaning equipment and automatic cleaning equipment |
| CN107277690B (en) * | 2017-08-02 | 2020-07-24 | 北京地平线信息技术有限公司 | Sound processing method and device and electronic equipment |
| CN209310172U (en) * | 2018-03-07 | 2019-08-27 | 北京三五二环保科技有限公司 | Air purifier with voice control function |
| CN108847221B (en) * | 2018-06-19 | 2021-06-15 | Oppo广东移动通信有限公司 | Voice recognition method, voice recognition device, storage medium and electronic equipment |
| CN108682428A (en) * | 2018-08-27 | 2018-10-19 | 珠海市微半导体有限公司 | The processing method of robot voice control system and robot to voice signal |
| CN110164425A (en) * | 2019-05-29 | 2019-08-23 | 北京声智科技有限公司 | A kind of noise-reduction method, device and the equipment that can realize noise reduction |
-
2019
- 2019-05-29 CN CN201910457370.0A patent/CN110164425A/en active Pending
- 2019-12-30 WO PCT/CN2019/129930 patent/WO2020238203A1/en active Application Filing
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120259629A1 (en) * | 2011-04-11 | 2012-10-11 | Kabushiki Kaisha Audio-Technica | Noise reduction communication device |
| CN103959814A (en) * | 2011-12-08 | 2014-07-30 | 索尼公司 | Earhole attachment-type sound pickup device, signal processing device, and sound pickup method |
| CN103959813A (en) * | 2011-12-08 | 2014-07-30 | 索尼公司 | Earhole attachment-type sound pickup device, signal processing device, and sound pickup method |
| CN104424953A (en) * | 2013-09-11 | 2015-03-18 | 华为技术有限公司 | Speech signal processing method and device |
| CN104952458A (en) * | 2015-06-09 | 2015-09-30 | 广州广电运通金融电子股份有限公司 | Noise suppression method, device and system |
| CN108028049A (en) * | 2015-09-14 | 2018-05-11 | 美商楼氏电子有限公司 | Microphone signal merges |
| US9401158B1 (en) * | 2015-09-14 | 2016-07-26 | Knowles Electronics, Llc | Microphone signal fusion |
| CN109478409A (en) * | 2016-07-11 | 2019-03-15 | 微软技术许可有限责任公司 | For calculating the microphone noise suppressed of equipment |
| CN206713019U (en) * | 2017-02-10 | 2017-12-05 | 万魔声学科技有限公司 | Active noise reducing device and earphone |
| CN107452368A (en) * | 2017-08-14 | 2017-12-08 | 海尔优家智能科技（北京）有限公司 | The noise-reduction method and device of a kind of home appliance |
| CN108088064A (en) * | 2018-01-15 | 2018-05-29 | 青岛理工大学 | Arranged on ventilation nozzle and it is capable of active noise reducing device and the control method that acoustics interacts |
| CN208905198U (en) * | 2018-09-30 | 2019-05-24 | 科大讯飞股份有限公司 | Electronic equipment with full isolation Dolby circuit |
| CN109243453A (en) * | 2018-10-29 | 2019-01-18 | 珠海格力电器股份有限公司 | The processing method and processing device of voice messaging, storage medium, electronic device |
| CN109599107A (en) * | 2018-12-07 | 2019-04-09 | 珠海格力电器股份有限公司 | A kind of method, apparatus and computer storage medium of speech recognition |
| CN210667779U (en) * | 2019-05-29 | 2020-06-02 | 北京声智科技有限公司 | Equipment capable of reducing noise |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020238203A1 (en) * | 2019-05-29 | 2020-12-03 | 北京声智科技有限公司 | Noise reduction method, noise reduction apparatus, and device capable of reducing noise |
| CN111341304A (en) * | 2020-02-28 | 2020-06-26 | 广州国音智能科技有限公司 | Method, device and equipment for training speech characteristics of speaker based on GAN |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020238203A1 (en) | 2020-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luo et al. | FaSNet: Low-latency adaptive beamforming for multi-microphone audio processing | |
| JP5587396B2 (en) | System, method and apparatus for signal separation | |
| Mertins et al. | Room impulse response shortening/reshaping with infinity-and $ p $-norm optimization | |
| US8583428B2 (en) | Sound source separation using spatial filtering and regularization phases | |
| WO2022012206A1 (en) | Audio signal processing method, device, equipment, and storage medium | |
| JP6450139B2 (en) | Speech recognition apparatus, speech recognition method, and speech recognition program | |
| US20060106601A1 (en) | Noise elimination method, apparatus and medium thereof | |
| WO2015065682A1 (en) | Selective audio source enhancement | |
| CN110164425A (en) | A kind of noise-reduction method, device and the equipment that can realize noise reduction | |
| JP6987075B2 (en) | Audio source separation | |
| CN111863020B (en) | Voice signal processing method, device, equipment and storage medium | |
| CN111261179A (en) | Echo cancellation method and device and intelligent equipment | |
| CN110660404B (en) | Voice communication and interactive application system and method based on null filtering preprocessing | |
| CN110660407A (en) | Audio processing method and device | |
| CN114171041A (en) | Voice noise reduction method, device and equipment based on environment detection and storage medium | |
| KR20210153919A (en) | Joint training method and apparatus for deep neural network-based dereverberation and beamforming for sound event detection in multi-channel environment | |
| CN109389978A (en) | A kind of audio recognition method and device | |
| US11164591B2 (en) | Speech enhancement method and apparatus | |
| Li et al. | A robust and self-reconfigurable design of spherical microphone array for multi-resolution beamforming | |
| WO2023103693A1 (en) | Audio signal processing method and apparatus, device, and storage medium | |
| CN210667779U (en) | Equipment capable of reducing noise | |
| CN113077803B (en) | Voice processing method and device, readable storage medium and electronic equipment | |
| CN114333817A (en) | Remote controller and remote controller voice recognition method | |
| CN112002340A (en) | Voice acquisition method and device based on multiple users | |
| CN112397079A (en) | Filter, adaptive filtering method thereof and computer readable storage medium |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40008274 Country of ref document: HK |