CN105931647A - Noise suppression method and apparatus - Google Patents
Noise suppression method and apparatus Download PDFInfo
- Publication number
- CN105931647A CN105931647A CN201610211263.6A CN201610211263A CN105931647A CN 105931647 A CN105931647 A CN 105931647A CN 201610211263 A CN201610211263 A CN 201610211263A CN 105931647 A CN105931647 A CN 105931647A
- Authority
- CN
- China
- Prior art keywords
- audio signals
- recorded audio
- noise reduction
- noise
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000001629 suppression Effects 0.000 title abstract 4
- 230000009467 reduction Effects 0.000 claims abstract description 88
- 230000005236 sound signal Effects 0.000 claims description 111
- 238000011946 reduction process Methods 0.000 claims description 27
- 230000007613 environmental effect Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 7
- 230000004899 motility Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Telephone Function (AREA)
Abstract
The present invention provides a noise suppression method and apparatus. The noise suppression method includes the following steps that: sound recording signals are acquired; whether the sound recording signals satisfy a preset noise reduction condition is judged; and if it is judged that the sound recording signals satisfy the preset noise reduction condition, noise reduction processing is performed on the sound recording signals. According to the noise suppression method and apparatus of the invention, since whether the sound recording signals require noise reduction is judged before noise reduction, and a noise reduction algorithm is called if the noise reduction is required, and therefore, flexibility can be improved, and the power consumption of a terminal can be reduced.
Description
Technical field
The present invention relates to field of terminal technology, particularly relate to the method and device of a kind of noise suppressed.
Background technology
Along with the development of terminal, the available function of terminal get more and more, such as sound-recording function, to
User provides easily simultaneously, also makes user more and more higher to the requirement of sound-recording function, particularly, to record
The speech recognition degree of sound function requires higher.
The mode of existing raising terminal speech resolution is that recording is carried out noise reduction.Current noise reduction mode is logical
Cross dual microphone collection recording, use noise reduction algorithm that recording is processed afterwards；Such as, to voice signal
Carry out Mel decomposition, then take some rank transformation algorithms to carry out noise reduction；Or voice signal is carried out framing,
Windowed filtering scheduling algorithm processes.Owing to when terminal gets recording, noise reduction algorithm can be called always,
But sometimes in Recording Process, within a period of time, do not have noise, or noise does not interferes with recording
Resolution, if terminal calls noise reduction algorithm the most always, increases the power consumption of terminal unavoidably.Visible, existing
The noise-reduction method of terminal, motility is poor, causes power consumption bigger.
Summary of the invention
The embodiment of the present invention provides the method and device of a kind of noise suppressed, to solve the side of existing noise suppressed
Method motility is poor, causes the technical problem that power consumption is bigger.
For solving the problems referred to above, the technical scheme that the present invention provides is as follows:
The embodiment of the present invention provides a kind of method of noise suppressed, comprising:
Gathering recorded audio signals, described recorded audio signals includes voice signal；
Judge whether described recorded audio signals meets and preset noise reduction condition；
If it is determined that described recorded audio signals meets described default noise reduction condition, then described recorded audio signals is carried out noise reduction
Process.
The embodiment of the present invention also provides for the device of a kind of noise suppressed, comprising:
Acquisition module, is used for gathering recorded audio signals, and described recorded audio signals includes voice signal；
Judge module, is used for judging whether described recorded audio signals meets and presets noise reduction condition；
When described judge module, noise reduction module, for judging that described recorded audio signals meets described default noise reduction condition
Time, described recorded audio signals is carried out noise reduction process.
Compared to prior art, the method and device of the noise suppressed of the present embodiment, gather recorded audio signals；Sentence
Whether this recorded audio signals disconnected meets is preset noise reduction condition；If it is determined that this recorded audio signals meets this default noise reduction condition,
Then this recorded audio signals is carried out noise reduction process.Owing to, before noise reduction, first judging that recorded audio signals is the need of fall
Make an uproar, if needing noise reduction to recall noise reduction algorithm；Thus improve motility, reduce the power consumption of terminal.
Accompanying drawing explanation
The flow chart of the method for the noise suppressed that Fig. 1 provides for the embodiment of the present invention one；
The flow chart of the method for the noise suppressed that Fig. 2 provides for the embodiment of the present invention two；
The flow chart of the method for the noise suppressed that Fig. 3 provides for the embodiment of the present invention three；
The oscillogram of the recorded audio signals of the t0 period that Fig. 4 provides for the embodiment of the present invention three；
The oscillogram of the ambient noise signal of the t1 period that Fig. 5 provides for the embodiment of the present invention three；
The oscillogram of the filtered recorded audio signals that Fig. 6 provides for the embodiment of the present invention three；
The structural representation of the device of the noise suppressed that Fig. 7 provides for the embodiment of the present invention four；
The preferred structure schematic diagram of the device of the noise suppressed that Fig. 8 provides for the embodiment of the present invention four.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those skilled in the art are not making creative labor
The every other embodiment obtained under dynamic premise, broadly falls into the scope of protection of the invention.
Refer to the flow chart of the method for the noise suppressed that Fig. 1, Fig. 1 provide for the embodiment of the present invention one.
The method of the noise suppressed of this preferred embodiment, including:
Step S101, gathers recorded audio signals.
Such as, when the sound-recording function that user opens a terminal starts to record, terminal is recorded by mike collection,
This recorded audio signals includes voice signal and environmental noise；Such as gathering the recording of preset duration, this terminal is permissible
For the equipment such as mobile phone, panel computer.
Step S102, it is judged that whether this recorded audio signals meets is preset noise reduction condition.
Such as, whether the environmental noise in the recording that terminal judges collects can affect the resolution of voice signal,
If this environmental noise does not interferes with the resolution of voice signal, recorded audio signals is not carried out noise reduction process,
If this environmental noise can affect the resolution of voice signal, then perform step S103.
Step S103, if it is determined that this recorded audio signals meets this default noise reduction condition, is then carried out this recorded audio signals
Noise reduction process.
Such as, when terminal judges the resolution that environmental noise can affect voice signal, terminal is called preset
Noise reduction algorithm carries out noise reduction, to improve the resolution of voice signal to the recording gathered.
The method of the noise suppressed of this preferred embodiment, owing to, before recorded audio signals is carried out noise reduction, first sentencing
Whether disconnected recorded audio signals meets is preset noise reduction condition, if recorded audio signals meets presets noise reduction condition, recalls
Noise reduction algorithm；Thus improve motility, reduce the power consumption of terminal.
Refer to the flow chart of the method for the noise suppressed that Fig. 2, Fig. 2 provide for the embodiment of the present invention two.
The method of the noise suppressed of this preferred embodiment, including:
Step S201, gathers the recorded audio signals of preset duration.
Such as, when the sound-recording function that user opens a terminal starts to record, when terminal is preset by mike collection
Long recording, this recorded audio signals includes voice signal and environmental noise；This terminal can be mobile phone, flat board electricity
The equipment such as brain.
Step S202, obtains this recorded audio signals average amplitude in this preset duration；
Such as, this recorded audio signals has multiple amplitude in preset duration, and terminal obtains each amplitude, and calculates
The summation of all amplitudes and the total quantity of all amplitudes.Terminal by the summation of all amplitudes divided by total quantity,
Obtain the average amplitude of recorded audio signals.
Step S203, it is judged that whether this average amplitude is more than presetting noise reduction threshold value；
Such as, average amplitude is compared by terminal with default noise reduction threshold value, to judge current recording signal
In environmental noise the biggest.This default noise reduction threshold value can set, based on experience value if terminal is sentenced
This average amplitude fixed less than or equal to presetting noise reduction threshold value, then shows the environmental noise ratio in current recording signal
Less, then perform step S204；If terminal judges that this average amplitude more than presetting noise reduction threshold value, then shows
Environmental noise in current recording signal is bigger, then perform step S205.
Step S204, if it is determined that this average amplitude is less than or equal to this default noise reduction threshold value, does not deals with.
Such as, when terminal judges this average amplitude less than or equal to this default noise reduction threshold value, not to recording letter
Number carry out noise reduction process.
Step S205, if it is determined that this average amplitude is more than this default noise reduction threshold value, is then carried out this recorded audio signals
Noise reduction process.
Such as, when terminal judges this average amplitude more than this default noise reduction threshold value, terminal calls preset fall
Algorithm of making an uproar carries out noise reduction, to improve the resolution of voice signal to the recording gathered.
This noise reduction algorithm can be existing noise reduction algorithm, of course for the power consumption of reduction terminal further, and should
The step that this recorded audio signals carries out noise reduction process includes:
(1) when this recorded audio signals starts to gather, obtain the recorded audio signals of preset period of time, obtain initial signal；
Such as, terminal is divided into multiple preset period of time, terminal by collecting preset duration corresponding to recorded audio signals
Obtain the recorded audio signals of initial time period, obtain this initial signal.
(2) when having gathered the recorded audio signals of this preset period of time, the environment noise letter of next preset period of time is gathered
Number；
Such as, at the end of this preset period of time, obtain the ambient noise signal of ensuing preset period of time.
(3) according to this ambient noise signal, this initial signal is filtered, so that this recorded audio signals is dropped
Make an uproar process.
Such as, initial signal being deducted ambient noise signal, the difference obtained is the recorded audio signals after noise reduction.When
Time so it is understood that the recorded audio signals of remaining preset period of time is carried out noise reduction, it is possible to use with its phase
The ambient noise signal of next adjacent preset period of time is filtered.
For the ease of extracting voice signal, after this carries out the step of noise reduction process to this recorded audio signals, should
Method also includes:
Recorded audio signals after noise reduction process is carried out speech recognition, to obtain voice signal.
Such as, terminal uses preset speech recognition algorithm, identifies the recorded audio signals after noise reduction process
In voice signal.
The method of the noise suppressed of this preferred embodiment, owing to gathering the recorded audio signals of preset duration, and obtains
The average amplitude of this recorded audio signals, it is judged that whether average amplitude is more than is preset noise reduction threshold value, if it is, right
Recorded audio signals carries out noise reduction process, and after noise reduction, carries out speech recognition, extracts the language in recorded audio signals
Tone signal, reduce further the power consumption of terminal.
Refer to the flow chart of the method for the noise suppressed that Fig. 3, Fig. 3 provide for the embodiment of the present invention three.
The present embodiment is described in detail as a example by terminal is as smart mobile phone, the noise suppressed of this preferred embodiment
Method, including:
Step S301, smart mobile phone gathers the recorded audio signals of preset duration.
Such as, user opens the sound-recording function of smart mobile phone when starting to record, and smart mobile phone passes through Mike's elegance
The recording of collection preset duration, this recorded audio signals includes voice signal and environmental noise.
Step S302, smart mobile phone obtains this recorded audio signals average amplitude in this preset duration.
Such as, this recorded audio signals has multiple amplitude in preset duration, and smart mobile phone obtains each amplitude, and
Calculate summation and the total quantity of all amplitudes of all amplitudes.Smart mobile phone with the summation of all amplitudes divided by
Total quantity, obtains the average amplitude of recorded audio signals.
Step S303, smart mobile phone judges that whether this average amplitude is more than presetting noise reduction threshold value；
Such as, average amplitude is compared by smart mobile phone with default noise reduction threshold value, to judge that current recording is believed
Environmental noise in number is the biggest.This default noise reduction threshold value can set based on experience value, if intelligence
Can judge that this average amplitude less than or equal to presetting noise reduction threshold value, then shows the ring in current recording signal by mobile phone
Border noise is smaller, then perform step S304；If smart mobile phone judges this average amplitude more than presetting noise reduction
Threshold value, then show that the environmental noise in current recording signal is bigger, then perform step S305.
Step S304, if smart mobile phone judges that this average amplitude is less than or equal to this default noise reduction threshold value, the most not
Deal with.
Such as, when smart mobile phone judges this average amplitude less than or equal to this default noise reduction threshold value, the most not
Recorded audio signals is carried out noise reduction process.
Step S305, if smart mobile phone judges that this average amplitude is more than this default noise reduction threshold value, then smart mobile phone
Recorded audio signals is carried out noise reduction process.
Such as, preset duration corresponding for the recorded audio signals collected is divided into multiple preset period of time by smart mobile phone,
Such as t0-t2, smart mobile phone obtains the recorded audio signals of t0 period, obtains this initial signal, the recording of t0 period
As shown in Figure 4, wherein Fig. 4 abscissa express time, vertical coordinate represents amplitude to the oscillogram of signal.
Such as, at the end of this t0 period, obtain the ambient noise signal of t1 period, the environment of t1 period
The oscillogram of noise signal is as it is shown in figure 5, wherein Fig. 5 abscissa express time, and vertical coordinate represents amplitude.
Such as, the recorded audio signals of t0 period be the ambient noise signal of F (a), t1 period be N (f), after filtering
Recorded audio signals be U (a), the most as shown in Equation 1:
U (a)=F (a)-N (f) formula 1
That is, the oscillogram of filtered signal U (a) is as shown in Figure 6, wherein Fig. 6 abscissa express time,
Vertical coordinate represents amplitude.
Afterwards, when the recorded audio signals of t1 period is carried out noise reduction, obtain the recorded audio signals of t1 period, and obtain
Take the ambient noise signal of t2 period, the ambient noise signal of the use t2 period recorded audio signals to the t1 period
It is filtered.When the recorded audio signals of t2 period is carried out noise reduction, obtain the environment of subsequent period with the t2 period
Noise signal, is filtered the recorded audio signals of t2 period, concrete mode processing mode and the recording of t0 period
The noise reduction mode of signal is identical, does not repeats them here, thus completes the recorded audio signals in whole preset duration
Noise reduction.
The method of the noise suppressed of this preferred embodiment, owing to gathering the recording of preset duration by smart mobile phone
Signal, and obtain the average amplitude of this recorded audio signals, it is judged that whether average amplitude is more than is preset noise reduction threshold value,
If it is, recorded audio signals is carried out noise reduction process, and after noise reduction, carry out speech recognition, extract record
Voice signal in tone signal, reduce further the power consumption of smart mobile phone.
Refer to the structural representation of the device of the noise suppressed that Fig. 7, Fig. 7 provide for the embodiment of the present invention four.
The device 40 of the noise suppressed of this preferred embodiment includes: acquisition module 41, judge module 42, noise reduction module
43；
Acquisition module 41, is used for gathering recorded audio signals；
Judge module 42, is used for judging whether this recorded audio signals meets and presets noise reduction condition；
Noise reduction module 43, is used for when this judge module judges that this recorded audio signals meets this default noise reduction condition,
This recorded audio signals is carried out noise reduction process.
This acquisition module 41 specifically for: gather preset duration recorded audio signals.
As shown in Figure 8, this judge module 42 includes: obtains submodule 421, judge submodule 422, true
Stator modules 423；
Obtain submodule 421, for obtaining this recorded audio signals average amplitude in this preset duration；
Judge submodule 422, be used for judging that whether this average amplitude is more than presetting noise reduction threshold value；
Determine submodule 423, for judging that this average amplitude is more than this default noise reduction threshold when this judgement submodule
During value, it is determined that this recorded audio signals meets this default noise reduction condition.
This noise reduction module 43, specifically for:
When this recorded audio signals starts to gather, obtain the recorded audio signals of preset period of time, obtain initial signal；
When having obtained the recorded audio signals of this preset period of time, gather the ambient noise signal of next preset period of time；
According to this ambient noise signal, this initial signal is filtered, so that this recorded audio signals is carried out at noise reduction
Reason.
This device also includes: identification module 44；
Identification module 44, for after carrying out noise reduction process to this recorded audio signals, to the record after noise reduction process
Tone signal carries out speech recognition, to obtain voice signal.
When being embodied as, above modules can realize as independent entity, it is also possible to carries out arbitrarily
Combination, realizes as same or several entities, and being embodied as of above modules can be found in above
Embodiment of the method, does not repeats them here.
The device of the noise suppressed of this preferred embodiment, owing to, before recorded audio signals is carried out noise reduction, first sentencing
Whether disconnected recorded audio signals meets is preset noise reduction condition, if recorded audio signals meets presets noise reduction condition, recalls
Noise reduction algorithm；Thus improve motility, reduce the power consumption of terminal.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment
The program that can be by completes to instruct relevant hardware, and this program can be stored in a computer-readable and deposit
In storage media, storage medium may include that read only memory (ROM, Read Only Memory), with
Machine access/memory body (RAM, Random Access Memory), disk or CD etc..
The method and apparatus of a kind of noise suppressed provided the embodiment of the present invention above has carried out detailed Jie
Continuing, principle and the embodiment of the present invention are set forth by specific case used herein, above enforcement
The explanation of example is only intended to help to understand method and the core concept thereof of the present invention；Simultaneously for this area
Technical staff, according to the thought of the present invention, the most all will change,
In sum, this specification content should not be construed as limitation of the present invention.
Claims (10)
1. the method for a noise suppressed, it is characterised in that including:
Gathering recorded audio signals, described recorded audio signals includes voice signal；
Judge whether described recorded audio signals meets and preset noise reduction condition；
If it is determined that described recorded audio signals meets described default noise reduction condition, then described recorded audio signals is carried out noise reduction
Process.
The method of noise suppressed the most according to claim 1, it is characterised in that described collection recording letter
Number step include:
Gather the recorded audio signals of preset duration.
The method of noise suppressed the most according to claim 2, it is characterised in that the described record of described judgement
Whether tone signal meets the step of default noise reduction condition includes:
Obtain described recorded audio signals average amplitude in described preset duration；
Judge that whether described average amplitude is more than presetting noise reduction threshold value；
If it is determined that described average amplitude is more than described default noise reduction threshold value, then judge that described recorded audio signals meets institute
State default noise reduction condition.
The method of noise suppressed the most according to claim 2, it is characterised in that
The described step that described recorded audio signals carries out noise reduction process includes:
When described recorded audio signals starts to gather, obtain the recorded audio signals of preset period of time, obtain initial signal；
When having obtained the recorded audio signals of described preset period of time, gather the ambient noise signal of next preset period of time；
According to described ambient noise signal, described initial signal is filtered, so that described recorded audio signals is carried out
Noise reduction process.
The method of noise suppressed the most according to claim 1, it is characterised in that
After the described step that described recorded audio signals carries out noise reduction process, described method also includes:
Recorded audio signals after noise reduction process is carried out speech recognition, to obtain voice signal.
6. the device of a noise suppressed, it is characterised in that including:
Acquisition module, is used for gathering recorded audio signals, and described recorded audio signals includes voice signal；
Judge module, is used for judging whether described recorded audio signals meets and presets noise reduction condition；
When described judge module, noise reduction module, for judging that described recorded audio signals meets described default noise reduction condition
Time, described recorded audio signals is carried out noise reduction process.
The device of noise suppressed the most according to claim 6, it is characterised in that described acquisition module has
Body is used for: gather the recorded audio signals of preset duration.
The device of noise suppressed the most according to claim 7, it is characterised in that described judge module bag
Include:
Obtain submodule, for obtaining described recorded audio signals average amplitude in described preset duration；
Judge submodule, be used for judging that whether described average amplitude is more than presetting noise reduction threshold value；
Determine submodule, for judging that described average amplitude is more than described default noise reduction when described judgement submodule
During threshold value, it is determined that described recorded audio signals meets described default noise reduction condition.
The device of noise suppressed the most according to claim 7, it is characterised in that
Described noise reduction module, specifically for:
When described recorded audio signals starts to gather, obtain the recorded audio signals of preset period of time, obtain initial signal；
When having obtained the recorded audio signals of described preset period of time, gather the ambient noise signal of next preset period of time；
According to described ambient noise signal, described initial signal is filtered, so that described recorded audio signals is carried out
Noise reduction process.
The device of noise suppressed the most according to claim 6, it is characterised in that described device also wraps
Include: identification module；
Described identification module, for after carrying out noise reduction process to described recorded audio signals, after noise reduction process
Recorded audio signals carry out speech recognition, to obtain described voice signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610211263.6A CN105931647B (en) | 2016-04-05 | 2016-04-05 | Method and device for noise suppression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610211263.6A CN105931647B (en) | 2016-04-05 | 2016-04-05 | Method and device for noise suppression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105931647A true CN105931647A (en) | 2016-09-07 |
| CN105931647B CN105931647B (en) | 2020-01-14 |
Family
ID=56840204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610211263.6A Expired - Fee Related CN105931647B (en) | 2016-04-05 | 2016-04-05 | Method and device for noise suppression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105931647B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107483736A (en) * | 2017-08-23 | 2017-12-15 | 广东小天才科技有限公司 | Message processing method and device for instant messaging application program |
| CN108260054A (en) * | 2018-01-11 | 2018-07-06 | 上海展扬通信技术有限公司 | Method for improving, device and the computer readable storage medium of FM mass |
| CN108847221A (en) * | 2018-06-19 | 2018-11-20 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
| WO2019024278A1 (en) * | 2017-08-04 | 2019-02-07 | 歌尔科技有限公司 | Audio noise reduction method and apparatus |
| CN109389979A (en) * | 2018-12-05 | 2019-02-26 | 广东美的制冷设备有限公司 | Voice interactive method, voice interactive system and household electrical appliance |
| CN112053702A (en) * | 2020-09-30 | 2020-12-08 | 北京大米科技有限公司 | Voice processing method and device and electronic equipment |
| CN112309419A (en) * | 2020-10-30 | 2021-02-02 | 浙江蓝鸽科技有限公司 | Noise reduction and output method and system for multi-channel audio |
| CN112885366A (en) * | 2021-01-18 | 2021-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Active noise reduction method and device, storage medium and terminal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859568A (en) * | 2009-04-10 | 2010-10-13 | 比亚迪股份有限公司 | Method and device for eliminating voice background noise |
| CN104167209A (en) * | 2014-08-06 | 2014-11-26 | 华为软件技术有限公司 | Method and device for detecting audio distortion |
| CN104505095A (en) * | 2014-12-22 | 2015-04-08 | 上海语知义信息技术有限公司 | Voice control system and voice control method for alarm clock |
| WO2015141180A1 (en) * | 2014-03-17 | 2015-09-24 | Sharp Kabushiki Kaisha | Voice activity detection method and bioacoustic sensor |
-
2016
- 2016-04-05 CN CN201610211263.6A patent/CN105931647B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859568A (en) * | 2009-04-10 | 2010-10-13 | 比亚迪股份有限公司 | Method and device for eliminating voice background noise |
| WO2015141180A1 (en) * | 2014-03-17 | 2015-09-24 | Sharp Kabushiki Kaisha | Voice activity detection method and bioacoustic sensor |
| CN104167209A (en) * | 2014-08-06 | 2014-11-26 | 华为软件技术有限公司 | Method and device for detecting audio distortion |
| CN104505095A (en) * | 2014-12-22 | 2015-04-08 | 上海语知义信息技术有限公司 | Voice control system and voice control method for alarm clock |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019024278A1 (en) * | 2017-08-04 | 2019-02-07 | 歌尔科技有限公司 | Audio noise reduction method and apparatus |
| CN107483736A (en) * | 2017-08-23 | 2017-12-15 | 广东小天才科技有限公司 | Message processing method and device for instant messaging application program |
| CN107483736B (en) * | 2017-08-23 | 2020-05-15 | 广东小天才科技有限公司 | Message processing method and device for instant messaging application program |
| CN108260054A (en) * | 2018-01-11 | 2018-07-06 | 上海展扬通信技术有限公司 | Method for improving, device and the computer readable storage medium of FM mass |
| CN108847221A (en) * | 2018-06-19 | 2018-11-20 | Oppo广东移动通信有限公司 | Audio recognition method, device, storage medium and electronic equipment |
| 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 |
| CN109389979A (en) * | 2018-12-05 | 2019-02-26 | 广东美的制冷设备有限公司 | Voice interactive method, voice interactive system and household electrical appliance |
| CN112053702A (en) * | 2020-09-30 | 2020-12-08 | 北京大米科技有限公司 | Voice processing method and device and electronic equipment |
| CN112053702B (en) * | 2020-09-30 | 2024-03-19 | 北京大米科技有限公司 | Voice processing method and device and electronic equipment |
| CN112309419A (en) * | 2020-10-30 | 2021-02-02 | 浙江蓝鸽科技有限公司 | Noise reduction and output method and system for multi-channel audio |
| CN112885366A (en) * | 2021-01-18 | 2021-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Active noise reduction method and device, storage medium and terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105931647B (en) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105931647A (en) | Noise suppression method and apparatus | |
| CN106911996A (en) | The detection method of microphone state, device and terminal device | |
| CN108305637B (en) | Earphone voice processing method, terminal equipment and storage medium | |
| CN104602162B (en) | External denoising device and its noise-reduction method for mobile terminal | |
| CN103491488A (en) | Echo cancellation method and device for microphone | |
| CN106210219A (en) | Noise-reduction method and device | |
| CN108345676A (en) | Information-pushing method and Related product | |
| CN107622773B (en) | Audio feature extraction method and device and electronic equipment | |
| CN110556125B (en) | Feature extraction method and device based on voice signal and computer storage medium | |
| CN103347070B (en) | Push method, terminal, server and the system of speech data | |
| CN103886860A (en) | Information processing method and electronic device | |
| CN106448696A (en) | Adaptive high-pass filtering speech noise reduction method based on background noise estimation | |
| CN105848052A (en) | Microphone switching method and terminal | |
| CN111323783A (en) | Scene recognition method and device, storage medium and electronic equipment | |
| CN103888610A (en) | Method for achieving telephone conversation and sound recording simultaneously and communication terminal | |
| CN105657203B (en) | Noise-reduction method and system in smart machine voice communication | |
| CN105872909A (en) | Method and device for achieving audio signal processing | |
| CN112562712A (en) | Recording data processing method and system, electronic equipment and storage medium | |
| CN106708461A (en) | Information processing method and electronic equipment | |
| CN105718174B (en) | Interface switching method and system | |
| CN111370034A (en) | Method and device for synchronous recording and wireless earphone charging equipment | |
| CN104869232A (en) | Terminal | |
| CN104469250A (en) | Information processing method and electronic devices | |
| CN105374364B (en) | Signal processing method and electronic equipment | |
| CN106531180B (en) | Noise detecting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200114 |