CN108447494A - A kind of voice communication intelligent processing method - Google Patents
A kind of voice communication intelligent processing method Download PDFInfo
- Publication number
- CN108447494A CN108447494A CN201810099025.XA CN201810099025A CN108447494A CN 108447494 A CN108447494 A CN 108447494A CN 201810099025 A CN201810099025 A CN 201810099025A CN 108447494 A CN108447494 A CN 108447494A
- Authority
- CN
- China
- Prior art keywords
- voice
- voice communication
- speech processing
- voice signal
- noise reduction
- 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.)
- Withdrawn
Links
- 238000004891 communication Methods 0.000 title claims abstract description 52
- 238000003672 processing method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000009467 reduction Effects 0.000 claims abstract description 25
- 238000011946 reduction process Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims description 28
- 230000004913 activation Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 abstract description 3
- 239000004568 cement Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000001228 spectrum Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
Classifications
-
- G10L21/0202—
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- 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
- G10L2021/02087—Noise filtering the noise being separate speech, e.g. cocktail party
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Environmental & Geological Engineering (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a kind of voice communication intelligent processing methods, belong to voice communication technology field, the method includes：Obtain voice communication signals；After one in the multiple speech processing modules being set in advance in terminal device is activated, noise reduction process is carried out to the voice communication signals using the speech processing module；Wherein, the multiple speech processing module differs the noise reduction capability of the voice communication signals.Before obtaining voice communication signals, further include：Multiple speech processing modules are set on the terminal device.Using the embodiment of the present invention, the voice communication signals after noise reduction have diversity, can adapt to the requirement of varying environment and different user to voice signal.
Description
Technical field
The invention belongs to voice communication technology fields, more particularly to a kind of voice communication intelligent processing method.
Background technology
Speech enhan-cement is also referred to as speech de-noising or voice de-noising, dry the purpose is to be extracted from the voice signal with noise
Net voice signal improves the intelligibility of voice so as to improve speech sound quality, reduces the auditory fatigue sense for the person that understands.Currently,
Speech enhan-cement is applied in actual industrial or consumer products, with flourishing for the terminal devices such as mobile phone, when each
When being conversed under kind severe nature or man-made environment, a large amount of environmental noises can be added to one with the voice signal of speaker
It rises, passes in obedient person's ear so that voice quality substantially reduces, and also exactly this situation has pushed speech enhancement technique in hand
Rapid development in machine.For the speech quality improved to user, speech enhancement technique has obtained in mobile phone extensively
Application.
Current speech enhancement technique is usually to carry out noise reduction to voice signal, to improve the clarity of voice.If but dropping
It makes an uproar excessively, it is possible to which the voice signal that can damage user's needs to reduce the intelligibility of voice, while may also will produce
Some disgusting single frequency tones.
Since everyone sense of hearing and psychology have differences the perception and understanding of sound, so to the effect after speech de-noising
Fruit also has different impressions, the same section of voice signal after speech enhancement technique is handled, and somebody may feel
Denoising effect is pretty good, and somebody may think that effect is general or even bad, and somebody may feel denoising method to needing
The damage for the voice signal wanted affects his understanding to voice signal, and also somebody may think that denoising method is brought
The terminal devices such as the more irritated and current mobile phone of single frequency tone set in speech enhan-cement mode it is more single, by language
The enhanced voice signal of sound is more single.
Invention content
Technical problems to be solved by the inivention
It is more single and voice signal after speech enhan-cement is more single asks for the speech enhan-cement mode of the prior art
Topic, the present invention provides a kind of voice communication intelligent processing methods.
Technical solution
To solve the above problems, technical solution provided by the invention is：
A kind of voice communication intelligent processing method, the method includes：
Obtain voice communication signals；
After one in the multiple speech processing modules being set in advance in terminal device is activated, the speech processes are utilized
Module carries out noise reduction process to the voice communication signals；Wherein, the multiple speech processing module believes the voice communication
Number noise reduction capability differ.
Optionally, before obtaining voice communication signals, including：
Multiple speech processing modules are set on the terminal device.
Optionally, described that multiple speech processing modules are set on the terminal device, including：
Obtain voice signal to be measured；
The voice signal to be measured is input in terminal device in pre-set multiple phonetic algorithm modules and is carried out at noise reduction
Reason, to form multiple first effect voice signals；
Optionally, described that multiple speech processing modules are set on the terminal device, including：The first effect voice is played respectively
Signal；
After the first preferred voice signal in determining the first effect voice signal, by the described first preferred voice signal pair
The phonetic algorithm module answered is set as speech processing module.
Optionally, by the corresponding phonetic algorithm module of the described first preferred voice signal be set as speech processing module it
Before, the method includes：
Adjust the parameter of the corresponding phonetic algorithm mould parameter sets in the block of the described first preferred voice signal；The parameter sets
It is middle to carry the key parameter for having an impact the noise reduction capability；
Noise reduction process is carried out to the voice signal to be measured by adjusting the phonetic algorithm module after the parameter of the parameter sets,
To form multiple second effect voice signals；
Optionally, before setting the corresponding phonetic algorithm module of the described first preferred voice signal to speech processing module,
The method includes：The second effect voice signal is played respectively；
After the second preferred voice signal in determining the second effect voice signal, according to the described second preferred voice signal
The parameter of corresponding parameter sets, the corresponding phonetic algorithm module of the described first preferred voice signal of configuration.
Optionally, the speech processing module carries activation mark and mark prompt message；
Before one in the terminal device in pre-set multiple speech processing modules is activated, including：Display institute
State speech processing module prompt message and activation mark；
After one when in the multiple speech processing modules being set in advance in terminal device is activated, the voice is utilized
Processing module carries out noise reduction process to the voice communication signals, including：
After one in terminal device in pre-set multiple activation marks is clicked, according to mark prompt message institute
Corresponding speech processing module carries out noise reduction process to the voice communication signals.
Advantageous effect
Using technical solution provided by the invention, compared with prior art, have the advantages that：
The present invention is due to being provided with multiple speech processing modules in terminal device, the multiple speech processing module is to the voice
The noise reduction capability of signal of communication differs, and passes through the voice communication signals of the multiple speech processing module noise reduction process
Effect has difference.And speech enhan-cement mode in the prior art is more single, general same terminal device only has a kind of language
Sound enhancement method, the voice signal after speech enhan-cement are also more single.Therefore, voice communication of the present invention after noise reduction
Signal has diversity, can adapt to the requirement of varying environment and different user to voice signal.
Description of the drawings
Fig. 1 is a kind of flow diagram of voice communication intelligent processing method provided by the invention.
Fig. 2 is another flow diagram of voice communication intelligent processing method provided by the invention.
Fig. 3 is a kind of flow diagram of S100 provided by the invention.
Fig. 4 is another flow diagram of S100 provided by the invention.
Specific implementation mode
To further appreciate that present disclosure, in conjunction with accompanying drawings and embodiments, the present invention is described in detail.
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of voice communication intelligent processing method provided by the invention, the side
Method includes：
S101 obtains voice communication signals；
S102 utilizes institute's predicate after one in the multiple speech processing modules being set in advance in terminal device is activated
Sound processing module carries out noise reduction process to the voice communication signals；Wherein, the multiple speech processing module is to the voice
The noise reduction capability of signal of communication differs.
Specifically, Fig. 2 is another flow diagram of voice communication intelligent processing method provided by the invention, obtaining
Before voice communication signals, the method further includes：
Multiple speech processing modules are arranged in S100 on the terminal device.
Specifically, Fig. 3 is a kind of flow diagram of the S100 provided in the embodiment of the present invention.The S100, including：
S301 obtains voice signal to be measured；
Specifically, the voice signal to be measured can be signal of the user often in the recording file of residing environment.For example, with
In factory work, which needs the environment conversed with terminal device general just in the factory at family.Therefore, at the end
After end equipment records to the residing environment, by the signal in the recording file using generation as voice signal to be measured,
But it is not only limited to this.
S302, by the voice signal to be measured be input in terminal device in pre-set multiple phonetic algorithm modules into
Row noise reduction process, to form multiple first effect voice signals；
Specifically, it may include four major class that the phonetic algorithm, which includes,：Based on the method that frequency spectrum subtracts, it is based on adaptive-filtering
The method of device, the method based on statistical model and the method based on subspace include again a variety of algorithms per one kind, it
Have the characteristics that it is respective.The phonetic algorithm module is to be formed by mould based on the various algorithms in above-mentioned four major class method
Block.
S303 plays the first effect voice signal respectively；
S304, after the first preferred voice signal in determining the first effect voice signal, by the described first preferred voice
The corresponding phonetic algorithm module of signal is set as speech processing module.
Specifically, Fig. 4 is another flow diagram of the S100 provided in the embodiment of the present invention, implementation shown in Fig. 3
On the basis of example, before setting the corresponding phonetic algorithm module of the described first preferred voice signal to speech processing module,
Further include：
S305, the parameter of the corresponding phonetic algorithm mould parameter sets in the block of the described first preferred voice signal of adjustment；The ginseng
Manifold carries the key parameter for having an impact the noise reduction capability in closing；
Specifically, the parameter sets include for each phonetic algorithm, the key parameter of its anti-acoustic capability is determined, specifically
Can user be supplied to by cell phone manufacturer, in order to which user is easy to use, such parameter should not be excessive, preferably one or
For two, such as the method for being subtracted based on frequency spectrum, in theoretical algorithm to signal subsection after, the amplitude of multistage averagely will
The effect for influencing noise reduction mainly selects how many segment signal to carry out average meeting more preferably, so can be using signal hop count as one
A important parameter is selected for user, can set 2 sections, 3 sections, 4 sections, 5 sections this 4 select；In addition, in noise reduction process,
The reduction degree of the noise components of non-speech segment will seriously affect user's auditory perception, in general be by being decayed with one
The factor goes to reduce this part to realize, this factor cannot it is too small can not be too big, it is possible to be arranged 0.1,0.2,0.3,
0.4 several numbers are selected for user.So it is directed to the method subtracted based on frequency spectrum, so that it may to provide the user with the two ginsengs
Number is for selection, can specifically be adjusted to select the parameter sets of an optimization.
S306 carries out the voice signal to be measured by adjusting the phonetic algorithm module after the parameter of the parameter sets
Noise reduction process, to form multiple second effect voice signals；
S307 plays the second effect voice signal respectively；
S308, after the second preferred voice signal in determining the second effect voice signal, according to the described second preferred language
The parameter of the corresponding parameter sets of sound signal, the corresponding phonetic algorithm module of the described first preferred voice signal of configuration.
Specifically, the multiple second effect speech play is come out, listened to by user and evaluated, to really
The second preferred voice signal in fixed multiple second effect voices.In this way, indicating that the second preferred voice signal is more suitable for using
Family is listened to, therefore can be according to the parameter of the corresponding parameter sets of the described second preferred voice signal, configuration described first
It is preferred that the corresponding phonetic algorithm module of voice signal.
Specifically, the speech processing module carries activation mark and mark prompt message；
Before one in the terminal device in pre-set multiple speech processing modules is activated, including：Display institute
State speech processing module prompt message and activation mark；
After one when in the multiple speech processing modules being set in advance in terminal device is activated, the voice is utilized
Processing module carries out noise reduction process to the voice communication signals, including：
After one in terminal device in pre-set multiple activation marks is clicked, according to mark prompt message institute
Corresponding speech processing module carries out noise reduction process to the voice communication signals.
Wherein, the multiple speech processing module differs the noise reduction capability of the voice communication signals.The terminal
Multiple speech processing modules can be provided in equipment, the multiple speech processing module can be when terminal device produces, in advance
It is first set in the terminal device.Such as three kinds of selections " severe noise reduction ", " moderate noise reduction ", " slight noise reductions " are pre-set,
Wherein " severe noise reduction " expression can effectively remove noise components from Noisy Speech Signal, and voice communication signals is made to sound more
Totally, it is possible that voice communication signals can be damaged, to reduce the intelligibility of call voice, while may also can bring
Some unpleasant single frequency tone set；May can also include in voice communication signals after " moderate noise reduction " expression noise reduction process
Partial noise, but voice intelligibility may be better than the effect of " severe noise reduction ", while single frequency tone set is less；And it is " slight
Noise reduction " is the noise in slight reduction signal, but not has damage to primitive sound signal itself.In addition, the multiple voice
Processing module can also be the demands of individuals according to user to be configured.It is worth noting that above-mentioned terminal device, Ke Yishi
Such as the equipment that smart mobile phone etc. can carry out mobile call business.
The present invention is due to being provided with multiple speech processing modules in terminal device, the multiple speech processing module is to described
The noise reduction capability of voice communication signals differs, and passes through the voice communication signals of the multiple speech processing module noise reduction process
Effect have difference.And speech enhan-cement mode in the prior art is more single, general same terminal device only has one kind
Speech enhan-cement mode, the voice signal after speech enhan-cement is also more single, and such different user is for the voice signal
Impression is not necessarily identical, it is possible to individual user be caused more to be sick of such single voice signal.Therefore, the present invention is by drop
Voice communication signals after making an uproar have diversity, can adapt to the requirement of varying environment and different user to voice signal.
Schematically the present invention and embodiments thereof are described above, description is not limiting, institute in attached drawing
What is shown is also one of embodiments of the present invention, and actual structure is not limited to this.So if the common skill of this field
Art personnel are enlightened by it, without departing from the spirit of the invention, are not inventively designed and the technical solution
Similar frame mode and embodiment, are within the scope of protection of the invention.
Claims (7)
1. a kind of voice communication intelligent processing method, which is characterized in that the method includes：
Obtain voice communication signals；
After one in the multiple speech processing modules being set in advance in terminal device is activated, the speech processes are utilized
Module carries out noise reduction process to the voice communication signals；Wherein, the multiple speech processing module believes the voice communication
Number noise reduction capability differ.
2. voice communication intelligent processing method according to claim 1, which is characterized in that obtain voice communication signals it
Before, including：
Multiple speech processing modules are set on the terminal device.
3. voice communication intelligent processing method according to claim 1, which is characterized in that described to be arranged on the terminal device
Multiple speech processing modules, including：
Obtain voice signal to be measured；
The voice signal to be measured is input in terminal device in pre-set multiple phonetic algorithm modules and is carried out at noise reduction
Reason, to form multiple first effect voice signals.
4. voice communication intelligent processing method according to claim 1, which is characterized in that described to be arranged on the terminal device
Multiple speech processing modules further include：
The first effect voice signal is played respectively；
After the first preferred voice signal in determining the first effect voice signal, by the described first preferred voice signal pair
The phonetic algorithm module answered is set as speech processing module.
5. voice communication intelligent processing method according to claim 1, which is characterized in that by the described first preferred voice
The corresponding phonetic algorithm module of signal is set as before speech processing module, the method includes：
Adjust the parameter of the corresponding phonetic algorithm mould parameter sets in the block of the described first preferred voice signal；The parameter sets
It is middle to carry the key parameter for having an impact the noise reduction capability；
Noise reduction process is carried out to the voice signal to be measured by adjusting the phonetic algorithm module after the parameter of the parameter sets,
To form multiple second effect voice signals.
6. voice communication intelligent processing method according to claim 1, which is characterized in that by the described first preferred voice
The corresponding phonetic algorithm module of signal is set as before speech processing module, the method includes：
The second effect voice signal is played respectively；
After the second preferred voice signal in determining the second effect voice signal, according to the described second preferred voice signal
The parameter of corresponding parameter sets, the corresponding phonetic algorithm module of the described first preferred voice signal of configuration.
7. voice communication intelligent processing method according to claim 1, which is characterized in that the speech processing module carries
There is activation to identify and identify prompt message；
Before one in the terminal device in pre-set multiple speech processing modules is activated, including：Display institute
State speech processing module prompt message and activation mark；
After one when in the multiple speech processing modules being set in advance in terminal device is activated, the voice is utilized
Processing module carries out noise reduction process to the voice communication signals, including：
After one in terminal device in pre-set multiple activation marks is clicked, according to mark prompt message institute
Corresponding speech processing module carries out noise reduction process to the voice communication signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810099025.XA CN108447494A (en) | 2018-01-31 | 2018-01-31 | A kind of voice communication intelligent processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810099025.XA CN108447494A (en) | 2018-01-31 | 2018-01-31 | A kind of voice communication intelligent processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108447494A true CN108447494A (en) | 2018-08-24 |
Family
ID=63191510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810099025.XA Withdrawn CN108447494A (en) | 2018-01-31 | 2018-01-31 | A kind of voice communication intelligent processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108447494A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448708A (en) * | 2018-10-15 | 2019-03-08 | 四川长虹电器股份有限公司 | Far field voice wakes up system |
| CN110211598A (en) * | 2019-05-17 | 2019-09-06 | 北京华控创为南京信息技术有限公司 | Intelligent sound noise reduction communication means and device |
-
2018
- 2018-01-31 CN CN201810099025.XA patent/CN108447494A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448708A (en) * | 2018-10-15 | 2019-03-08 | 四川长虹电器股份有限公司 | Far field voice wakes up system |
| CN110211598A (en) * | 2019-05-17 | 2019-09-06 | 北京华控创为南京信息技术有限公司 | Intelligent sound noise reduction communication means and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103139351B (en) | Method for controlling volume, device and communication terminal | |
| CN104640054B (en) | Mobile terminal receiver/loudspeaker method of testing and system | |
| CN109545233A (en) | System and method for handling audio signal to be reset on audio devices | |
| CN104980337A (en) | Method and device for improving audio processing performance | |
| CN102611965A (en) | Method for eliminating influence of distance between dual-microphone de-noising mobilephone and mouth on sending loudness of dual-microphone de-noising mobilephone | |
| CN105187602B (en) | A kind of adjusting method and device of terminal volume | |
| US10204637B2 (en) | Noise reduction methodology for wearable devices employing multitude of sensors | |
| CN103077725B (en) | The method of speech processes and device | |
| US11978469B1 (en) | Ambient noise aware dynamic range control and variable latency for hearing personalization | |
| CN108447494A (en) | A kind of voice communication intelligent processing method | |
| CN1988734A (en) | Audio system with varying time delay and method for processing audio signals | |
| KR20240007168A (en) | Optimizing speech in noisy environments | |
| CN105141729A (en) | Noise reduction method, noise reduction device and mobile phone | |
| CN102118676A (en) | Digital hearing aid and method for adjusting parameters thereof by using sound from dual-tone multi-frequency key | |
| Grimault et al. | A real time hearing loss simulator | |
| CN110010144A (en) | Voice signals enhancement method and device | |
| KR100888049B1 (en) | A method for reinforcing speech using partial masking effect | |
| CN101699837B (en) | Telephone voice output gain adjustment method, device and communication terminal | |
| CN103002094B (en) | Method and device for suppressing environmental noise | |
| CN103152686B (en) | A kind of digital deaf-aid of customizable functionality pattern and its implementation | |
| US20060087380A1 (en) | Method for limiting the dynamic range of audio signals, and circuit arrangement for this purpose | |
| Sun et al. | An RNN-based speech enhancement method for a binaural hearing aid system | |
| CN113411456A (en) | Voice quality assessment method and device based on speech recognition | |
| CN108564961A (en) | A kind of voice de-noising method of mobile communication equipment | |
| CN107945814A (en) | A kind of method of speech processing |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180824 |
|
| WW01 | Invention patent application withdrawn after publication |