CN107910013A - The output processing method and device of a kind of voice signal - Google Patents
The output processing method and device of a kind of voice signal Download PDFInfo
- Publication number
- CN107910013A CN107910013A CN201711104384.1A CN201711104384A CN107910013A CN 107910013 A CN107910013 A CN 107910013A CN 201711104384 A CN201711104384 A CN 201711104384A CN 107910013 A CN107910013 A CN 107910013A
- Authority
- CN
- China
- Prior art keywords
- voice signal
- signal
- magnitude difference
- noise
- reduction process
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal 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
Abstract
The present invention is suitable for signal processing technology field, there is provided the output processing method and device of a kind of voice signal, including method include：Voice signal and ambient noise signal are identified from the voice signal obtained in real time；Obtain the Magnitude Difference of the voice signal and the ambient noise signal；Noise reduction process is carried out to the voice signal based on the Magnitude Difference.So that the processing to voice signal is more targeted, avoids and be controlled the problem of signal-to-noise ratio caused by the height for being only based on voice signal is handled is not high to volume by AGC.
Description
Technical field
The invention belongs to the output processing method and device of signal processing technology field, more particularly to a kind of voice signal.
Background technology
User can be conversed when driving under handsfree talk mode using mobile phone, in the prior art by increasing automatically
Benefit control (Automatic Gain Gontrol, AGC) adaptive gain regulating handles mobile phone voice signal, in sound
In the case that signal is very big, it can adaptively reduce voice signal, in the case of voice signal very little, can adaptively increase
Voice signal, so as to keep the voice signal amplitude of output to change in the range of very little automatically.But increased by way of AGC
Noise can also be amplified while voice signal, the voice to-noise ratio of transmission is poor, and user's communication experience is bad.
The content of the invention
In view of this, it is existing to solve an embodiment of the present invention provides the output processing method and device of a kind of voice signal
There is the problem of noise caused by being adjusted in technology using AGC to voice is poor.
The first aspect of the embodiment of the present invention provides a kind of output processing method of voice signal, including：
Voice signal and ambient noise signal are identified from the voice signal obtained in real time；
Obtain the Magnitude Difference of the voice signal and the ambient noise signal；
Noise reduction process is carried out to the voice signal based on the Magnitude Difference.
The second aspect of the embodiment of the present invention provides a kind of output processing apparatus of voice signal, including：
Audio signal acquiring unit, for identifying voice signal and ambient noise letter from the voice signal obtained in real time
Number；
Magnitude Difference computing unit, for obtaining the Magnitude Difference of the voice signal and the ambient noise signal；
Processing unit, for carrying out noise reduction process to the voice signal based on the Magnitude Difference.
The third aspect of the application provides a kind of terminal device, including：
Including memory, processor and it is stored in the computer that can be run in the memory and on the processor
Program, it is characterised in that the processor realizes institute's predicate that the application first aspect provides when performing the computer program
The step of output processing method of sound signal.
The fourth aspect of the application provides a kind of computer-readable recording medium, and the computer-readable recording medium is deposited
Contain computer program, it is characterised in that the computer program realizes that the application first aspect provides when being executed by processor
The voice signal output processing method the step of.
The 5th aspect of the application provides a kind of computer program product, and the computer program product includes computer
Program, the computer program realize the voice letter that the application first aspect provides when being executed by one or more processors
Number output processing method the step of.
Existing beneficial effect is the embodiment of the present invention compared with prior art：The application is by from the sound obtained in real time
Voice signal and ambient noise signal are identified in signal；Obtain the amplitude difference of the voice signal and the ambient noise signal
Value；Noise reduction process is carried out to the voice signal based on the Magnitude Difference.So that the processing to voice signal is more targeted,
Avoid and be controlled caused by the height for being only based on voice signal is handled that signal-to-noise ratio is not high to ask to volume by AGC
Topic.
Brief description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is that the output processing method for the voice signal that the embodiment of the present invention one provides realizes flow diagram；
Fig. 2 is that the output processing method of voice signal provided by Embodiment 2 of the present invention realizes flow diagram；
Fig. 3 is the schematic diagram of the output processing apparatus for the voice signal that the embodiment of the present invention three provides；
Fig. 4 is the schematic diagram for the terminal device that the embodiment of the present invention four provides.
Embodiment
In being described below, in order to illustrate rather than in order to limit, it is proposed that such as tool of particular system structure, technology etc
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that these are specific
The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known system, device, electricity
Road and the detailed description of method, in case unnecessary details hinders description of the invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
It should be appreciated that ought be special described by the instruction of term " comprising " use in this specification and in the appended claims
Sign, entirety, step, operation, the presence of element and/or component, but be not precluded from one or more of the other feature, entirety, step,
Operation, element, component and/or its presence or addition for gathering.
It is also understood that the term used in this description of the invention is merely for the sake of the mesh for describing specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singulative, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combinations and all possible combinations of one or more of the associated item listed, and including these combinations.
As used in this specification and in the appended claims, term " if " can be according to context quilt
Be construed to " when ... " or " once " or " in response to determining " or " in response to detecting ".Similarly, phrase " if it is determined that " or
" if detecting [described condition or event] " can be interpreted to mean according to context " once it is determined that " or " in response to true
It is fixed " or " once detecting [described condition or event] " or " in response to detecting [described condition or event] ".
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Embodiment one
Fig. 1 is that the method for the voice de-noising that the embodiment of the present invention one provides realizes flow diagram, the embodiment of the present application
The voice de-noising method of offer can be applied to cell phone, notebook, tablet computer, onboard system, wearable electronics and set
Standby to wait the electronic equipment with phonetic incepting element, this method may comprise steps of as shown in the figure：
Step S101, voice signal and ambient noise signal are identified from the voice signal obtained in real time.
In the present embodiment, user in driving process, can open hands-free mode and be conversed by mobile phone, due to
Under hands-free mode, mobile phone is generally placed upon on the mobile phone seat of automobile, since mobile phone is apart from the distant of user, mobile phone exists
While receiving the voice signal of user, can also receive automobile reasons for its use noise in the process of running, for example, tire with
Tire caused by the friction of road surface is made an uproar, the air-conditioning noise that air-conditioning draught fan produces, and air and vehicle gap in vehicle travel process,
The wind that corner friction produces is made an uproar.It is smaller that above-mentioned ambient noise belongs to signal amplitude change, and the steady-state noise that repetition rate is higher.
During user's communication, above-mentioned noise generally can all continue to exist, and voice device is carrying out AGC adjustment to voice signal
When, above-mentioned noise can produce significant impact to the quality of voice signal.
In the present embodiment, it is necessary first to signal is known according to the signal characteristic of voice signal and ambient noise signal
Not.Above-mentioned voice and ambient noise can be identified by way of prestoring people's acoustic model and noise model.Institute
State the phonetic feature that model includes the sound, such as frequency, zero-crossing rate, short-time average energy, short-time average magnitude etc..For example,
After being sampled to voice signal, the voice signal is matched with speech model, if containing people in voice signal
All features in acoustic model, that is, show that current someone is speaking, if the voice signal can not match people's acoustic model,
It is too small to be likely to be user voice, or ambient noise is excessive, shows that None- identified goes out voice from the sound currently obtained, this
Shi Shouji can issue the user with error prompting, such as mobile phone can send the prompt message of " can not obtain user voice ".Together
Sample, can be made an uproar according to the tire prestored model, air-conditioning noise model or wind model of making an uproar carry out the voice signal of acquisition
Identification, so as to judge the noise type included in present sound signals.
Step S102, obtains the Magnitude Difference of the voice signal and the ambient noise signal；
In the present embodiment, the voice Model Identification in step S101 goes out in voice signal and makes an uproar comprising voice and background
After sound, the feature that can be directed to above-mentioned model extracts the voice and ambient noise, according to the sound waves that recorded
Shape is believed to calculate the voice signal average amplitude of the representative voice in the voice signal collected in a period of time and ambient noise
Number average amplitude.
Step S103, noise reduction process is carried out based on the Magnitude Difference to the voice signal.
In the present embodiment, exhausted is asked to the voice signal amplitude and ambient noise signal amplitude that are obtained in step S102 first
To value, the difference between the absolute value of voice signal amplitude and the absolute value of ambient noise signal amplitude is then calculated.This implementation
Example selects default processing method so that the processing to voice signal is more targeted, keeps away respectively according to the difference of the difference
Exempted from by AGC be based only upon voice signal height handled caused by signal-to-noise ratio it is not high the problem of.
Optionally, before voice signal and ambient noise signal is identified, including：Pre-flock is carried out to the voice signal
Ripple.
In the present embodiment, it is contemplated that voice signal may receive the interference of random noise, such as Gaussian noise.If
Voice signal with random noise is identified, identification mistake may be produced due to the interference of random noise.Therefore, at this
In embodiment, pre-filtering is first carried out before voice signal is identified.Since the random noise in environment is orthogonal
, high frequency characteristics is shown as in the signal, therefore the voice signal got can be subjected to low-pass filtering in a frequency domain first,
So as to filter out the high frequency section for substantially belonging to noise signal in voice signal, subsequently voice identification and noise are known to improve
Other accuracy.
Embodiment two
The present embodiment based on embodiment one, specifically, it is described based on the Magnitude Difference to the voice signal into
Row noise reduction process, including：If the Magnitude Difference be on the occasion of, and when being greater than or equal to first threshold, to the voice signal into
Row noise reduction process, and the intensity of the noise reduction process is directly proportional to the Magnitude Difference.
In the present embodiment, when the voice signal amplitude of user is more than noise signal amplitude, the difference and the is judged
The size of one threshold value, the present embodiment is by the way that difference compared with the size of first threshold, is adopted respectively according to result of the comparison
Take corresponding noise-reduction method.
Waited and during first threshold when the difference is more than, i.e. amplitude of the amplitude of noise signal significantly less than voice signal.
Show that current speech signal quality is preferable, unobvious affected by noise, can use conventional noise reduction algorithm to voice signal into
Row noise reduction process, such as amplitude spectrum-subtraction commonly used in the art, harmonic signal enhancement method, noise cancellation method, herein not to noise reduction
Processing Algorithm restricts.Specifically used for above-mentioned noise reduction algorithm may be referred to the prior art, and therefore not to repeat here.At this
In embodiment, the intensity of noise reduction process is selected according to the size of the difference.In general, the intensity of noise reduction process more it is big then
It is better to the removal effect of noise, but serious distortion can also be produced to the voice signal that normal user sends.Therefore, may be used
Choosing, when the difference is larger, show that voice signal is affected by noise smaller, aliasing is not serious between noise and voice, because
This can increase the intensity of noise reduction process, and when the difference is smaller, showing noise signal, there are certain shadow to voice signal
Ring, i.e., there are certain aliasing between noise and voice, therefore, correspondingly reduce the intensity of noise reduction process.According to voice signal
The size dynamic of difference adjusts the intensity of noise reduction process between amplitude and noise signal amplitude, improves the sound matter of noise reduction process
Amount.
Optionally, if as shown in Fig. 2, the Magnitude Difference is on the occasion of and the Magnitude Difference is less than or equal to the second threshold
Value, and when the amplitude of the voice signal is more than three threshold values, including：
Step S201, amplifies preset gain by the voice signal, obtains first M signal.
Step S202, carries out noise reduction process to the first M signal, obtains second M signal.
Step S203, according to the preset gain decay second M signal, obtains the sound after noise reduction process
Sound signal.
In the present embodiment, when the difference S be on the occasion of and when being less than second threshold T, show that current noise situation compares
Seriously, wherein, affiliated second threshold T can be equal to first threshold, or might be less that first threshold.If directly to current
Voice signal carries out noise reduction process, and obtained voice signal is not very good.Therefore, in the present embodiment, first by sound
Sound signal is amplified according to default gain A, i.e. voice signal in voice signal and noise signal is carried out according to gain A
Amplification, obtains first M signal.It can be seen from the above that between voice signal amplitude and noise signal amplitude in first M signal
Difference also amplify according to gain A, therefore, after voice signal is amplified according to gain A carry out noise reduction process, can be notable
The influence to normal user voice signal is reduced, the value of the gain A can be counted according to the difference S and second threshold T
Calculate.Specifically：A≥T/S.Pass through the gain A calculated.The difference S ＇ after signal gain adjustment can be caused to be more than second threshold
T, then carries out noise reduction process to affiliated first M signal, obtains second M signal.The second centre letter after noise reduction process
Number decay according still further to gain A, the voice signal after noise reduction process is obtained after decay.In order to ensure the effect of noise reduction,
In the present embodiment, the amplitude of the voice signal, which is more than, to be needed to be more than the 3rd threshold value.Affiliated 3rd threshold value can be according to mobile phone
Performance and used noise reduction algorithm together decide on.The gain A is accordingly no more than a max-thresholds so that after gain
The range value of voice signal be not more than clipping point.Because if the signal after gain has exceeded clipping point, put through gain
Signal after big will be unable to be recorded, even if original signal can not also be obtained again by being decayed by identical gain.
In the present embodiment, when the Magnitude Difference be on the occasion of, and the Magnitude Difference is less than or equal to second threshold, and
When the amplitude of the voice signal is more than three threshold values, by the voice signal amplify preset gain after to the voice signal into
Row noise reduction process, then according to the voice signal after the preset gain decay noise reduction process, not only ensures signal magnitude
It is constant, and the signal-to-noise ratio of voice signal is improved, improve the experience of user.
Optionally, the sound model includes the sound model of specific user, in driving process, may exist except user
Beyond conversing using hands-free mode, may there are other passengers talking, therefore, use sound model recognition of speech signals
When, the sound of specific user is identified according to the sound model of specific user first.Then identify whether to wrap according to sound model
Include the voice in addition to specific user.If also there are the voice beyond specific user, and the signal of the voice beyond specific user
Amplitude is more than the voice signal amplitude of specific user, then through this embodiment in noise-reduction method possibly can not realize to specific use
The enhancing of family voice.In such a case, it is possible to issue the user with prompting, other people current sound of speaking are excessive, may influence logical
Talk about effect.
Optionally, noise-reduction method disclosed above and traditional automatic growth control (AGC) can be combined, specifically,
After the voice signal and ambient noise that voice signal includes user is identified, the voice signal got is first passed through into AGC
Processing so that voice signal amplitude changes in the range of very little, then obtains voice signal amplitude and the back of the body in voice signal
Scape noise signal amplitude；Calculate the difference between voice signal amplitude and ambient noise signal amplitude, when the difference be on the occasion of
And when being more than or equal to first threshold, noise reduction process, and the intensity of the noise reduction process and the difference are carried out to the voice signal
It is worth directly proportional；When the difference be on the occasion of and when being less than first threshold, by after voice signal amplification preset gain to described
Voice signal carries out noise reduction process, the voice signal after the noise reduction process that then decays according to the preset gain.Passing through will
Traditional AGC methods are combined with the noise-reduction method in the present embodiment, can further optimize the effect of voice de-noising.
Embodiment three
The present embodiment based on embodiment one, specifically, it is described based on the Magnitude Difference to the voice signal into
Row noise reduction process, including：If the Magnitude Difference is non-positive value, prompt message is exported, the prompt message is used to prompt user
Close to microphone call or increase speaking volume.
In the present embodiment, when the voice signal amplitude of user and the difference S of noise signal amplitude are 0, i.e. voice signal
It is identical with noise signal；Or the difference S when being negative value, i.e., the amplitude of voice signal is less than noise signal, since background is made an uproar
Sound is additive noise, and in the case that the Magnitude Difference is non-positive value, the voice of user can be covered by noise signal, such a
In the case of to noise signal carry out noise reduction process normal user voice signal can also be handled, so as to cause the language of user
Serious distortion occurs for sound.Therefore, in the present embodiment, when the difference is non-positive value, the audio output of mobile phone can be passed through
Unit issues the user with prompting, for example, prompting user voice is too small, or noise is excessive, prompt user speak close to mobile phone or
Person speaks up.
Optionally, the distance between detection user and mobile phone can be combined to be adjusted to mobile phone suggestion content.
In the present embodiment, as in embodiment one, identify that the voice comprising people is believed in voice signal according to sound model
Number, and noise signal.And specifically identify noise signal for tire is made an uproar, wind is made an uproar, air-conditioning noise.If the voice signal amplitude with
The difference of noise signal amplitude is non-positive value, and when the distance between user and mobile phone are less than preset value, that is, represents that user is current
It is close from mobile phone, it can not lean on and speak close to mobile phone to solve the problems, such as call noise, therefore can not in prompting user voice
While not hearing, the source of user's noise can be prompted at the same time, so that user targetedly solves, such as passes through speech recognition
It is the discovery that air-conditioning noise amplitude is more than the voice signal amplitude of user, then reminds user's air-conditioning noise excessive, and inform that user can
With by reducing air conditioner wind speed.If by speech recognition be the discovery that wind make an uproar amplitude be more than user voice signal amplitude, prompt
User's wind is made an uproar excessive, and suggests that user can reduce speed.The present embodiment is by the noise source that identifies, can not be by connecing
Nearly mobile phone speech is come in the case of solving noise problem, by reminding the main source of user's current noise, so that user can be with
Solution is taken accordingly, allows users to easily and accurately solve the noise for reducing voice, improves the experience of user.
Example IV
Fig. 3 shows the composition structure of the output processing apparatus of voice signal provided in this embodiment, for convenience of description,
It illustrate only part related to the present embodiment.
In the present embodiment, described device is used for realization the output processing method of the voice signal described in Fig. 1 embodiments, can
To be the unit for being built in the software unit of mobile terminal, hardware cell or software and hardware combining.The mobile terminal include but
It is not limited to smart mobile phone, tablet computer, learning machine or intelligent vehicle-carried equipment etc..
As shown in figure 3, the output processing apparatus 3 of the voice signal includes：
Audio signal acquiring unit 301, for identifying that voice signal and background are made an uproar from the voice signal obtained in real time
Acoustical signal；
Magnitude Difference computing unit 302, for obtaining the Magnitude Difference of the voice signal and the ambient noise signal；
Processing unit 303, for carrying out noise reduction process to the voice signal based on the Magnitude Difference.
Optionally, the output processing apparatus of the voice signal further includes：
Prompt unit, if being non-positive value for the Magnitude Difference, exports prompt message, the prompt message is used to prompt
User converses close to microphone or increase speaking volume.
Optionally, the processing unit further includes：
The first processing subelement, if being on the occasion of and the Magnitude Difference is less than or equal to for the Magnitude Difference
Two threshold values, and when the amplitude of the voice signal is more than three threshold values, the voice signal is amplified into preset gain, obtains first
M signal；
Noise reduction process is carried out to the first M signal, obtains second M signal；
According to the preset gain decay second M signal, the voice signal after noise reduction process is obtained.
Optionally, the processing unit further includes：
Second processing subelement, if being on the occasion of and when being greater than or equal to first threshold, to described for the Magnitude Difference
Voice signal carries out noise reduction process, and the intensity of the noise reduction process is directly proportional to the Magnitude Difference.
Optionally, the output processing apparatus of the voice signal, further includes：
Pretreatment unit, it is pre- for being carried out before voice signal and ambient noise signal is identified to the voice signal
Filtering.
It is to be understood that the size of the sequence number of each step is not meant to the priority of execution sequence, each process in above-described embodiment
Execution sequence should determine that the implementation process without tackling the embodiment of the present invention forms any limit with its function and internal logic
It is fixed.
Fig. 4 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 4, the terminal of the embodiment is set
Standby 4 include：Processor 40, memory 41 and it is stored in the meter that can be run in the memory 41 and on the processor 40
Calculation machine program 42.The processor 40 realizes the output processing side of above-mentioned each voice signal when performing the computer program 42
Step in method embodiment, such as step 101 shown in Fig. 1 is to 103.Alternatively, the processor 40 performs the computer journey
The function of each unit in above-mentioned each device embodiment, such as the function of unit 301 to 303 shown in Fig. 3 are realized during sequence 42.
Exemplary, the computer program 42 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 41, and are performed by the processor 40, to complete the present invention.Described one
A or multiple module/units can be the series of computation machine programmed instruction section that can complete specific function, which is used for
Implementation procedure of the computer program 42 in the terminal device 4 is described.For example, the computer program 42 can be divided
Synchronization module, summarizing module, acquisition module, return module (module in virtual bench) are cut into, each module concrete function is as follows：
The terminal device 4 can be that notebook, palm PC, mobile phone, tablet computer and navigator etc. are defeated with voice
Enter the computing device of output function.The terminal device may include, but be not limited only to, processor 40, memory 41.This area skill
Art personnel are appreciated that Fig. 4 is only the example of terminal device 4, do not form the restriction to terminal device 4, can include than
More or fewer components are illustrated, either combine some components or different components, such as the terminal device can also wrap
Include input-output equipment, network access equipment, bus etc..
Alleged processor 40 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 41 can be the internal storage unit of the terminal device 4, such as the hard disk of terminal device 4 or interior
Deposit.The memory 41 can also be the External memory equipment of the terminal device 4, such as be equipped with the terminal device 4
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, dodges
Deposit card (Flash Card) etc..Further, the memory 41 can also both include the storage inside list of the terminal device 4
Member also includes External memory equipment.The memory 41 is used to store needed for the computer program and the terminal device
Other programs and data.The memory 41 can be also used for temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units integrate in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.In addition, each function list
Member, the specific name of module are not limited to the protection domain of the application also only to facilitate mutually distinguish.Said system
The specific work process of middle unit, module, may be referred to the corresponding process in preceding method embodiment, details are not described herein.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and is not described in detail or remembers in some embodiment
The part of load, may refer to the associated description of other embodiments.
Those of ordinary skill in the art may realize that each exemplary list described with reference to the embodiments described herein
Member and algorithm steps, can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical solution.Professional technician
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, can be with
Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, is only a kind of division of logic function, there can be other dividing mode when actually realizing, such as
Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separate, be shown as unit
The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
In network unit.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated module/unit realized in the form of SFU software functional unit and as independent production marketing or
In use, it can be stored in a computer read/write memory medium.Based on such understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer-readable recording medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method..Wherein, the computer program includes computer program code, the computer program
Code can be source code form, object identification code form, executable file or some intermediate forms etc..Computer-readable Jie
Matter can include：Can carry any entity or device of the computer program code, recording medium, USB flash disk, mobile hard disk,
Magnetic disc, CD, computer storage, read-only storage (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It is it should be noted that described
The content that computer-readable medium includes can carry out appropriate increasing according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in some jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier signal and electricity
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those of ordinary skill in the art that：It still can be to foregoing each
Technical solution described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical solution, should all
Within protection scope of the present invention.
Claims (10)
- A kind of 1. output processing method of voice signal, it is characterised in that including：Voice signal and ambient noise signal are identified from the voice signal obtained in real time；Obtain the Magnitude Difference of the voice signal and the ambient noise signal；Noise reduction process is carried out to the voice signal based on the Magnitude Difference.
- 2. the output processing method of voice signal as claimed in claim 1, it is characterised in that described to be based on the Magnitude Difference Noise reduction process is carried out to the voice signal, including：If the Magnitude Difference is non-positive value, prompt message is exported, the prompt message is used to prompt user close to microphone to lead to Words or increase speaking volume.
- 3. the output processing method of voice signal as claimed in claim 1, it is characterised in that described to be based on the Magnitude Difference Noise reduction process is carried out to the voice signal, including：If the Magnitude Difference be on the occasion of, and when being greater than or equal to first threshold, to voice signal progress noise reduction process, and The intensity of the noise reduction process is directly proportional to the Magnitude Difference.
- 4. the output processing method of voice signal as claimed in claim 1, it is characterised in that described to be based on the Magnitude Difference Noise reduction process is carried out to the voice signal, including：If the Magnitude Difference is on the occasion of and the Magnitude Difference is less than or equal to second threshold, and the width of the voice signal When degree is more than three threshold values,The voice signal is amplified into preset gain, obtains first M signal；Noise reduction process is carried out to the first M signal, obtains second M signal；According to the preset gain decay second M signal, the voice signal after noise reduction process is obtained.
- 5. the output processing method of voice signal as claimed in claim 1, it is characterised in that identifying voice signal and the back of the body Before scape noise signal, including：Pre-filtering is carried out to the voice signal.
- A kind of 6. output processing apparatus of voice signal, it is characterised in that including：Audio signal acquiring unit, for identifying voice signal and ambient noise signal from the voice signal obtained in real time；Magnitude Difference computing unit, for obtaining the Magnitude Difference of the voice signal and the ambient noise signal；Processing unit, for carrying out noise reduction process to the voice signal based on the Magnitude Difference.
- 7. the output processing apparatus of voice signal as claimed in claim 6, it is characterised in that the processing unit includes：Prompt unit, if being non-positive value for the Magnitude Difference, exports prompt message, the prompt message is used to prompt user Close to microphone call or increase speaking volume.
- 8. the output processing apparatus of voice signal as claimed in claim 6, it is characterised in that the processing unit includes：First processing subelement, if being on the occasion of and the Magnitude Difference is less than or equal to the second threshold for the Magnitude Difference Value, and when the amplitude of the voice signal is more than three threshold values, voice signal amplification preset gain is obtained among first Signal；Noise reduction process is carried out to the first M signal, obtains second M signal；According to the preset gain decay second M signal, the voice signal after noise reduction process is obtained.
- 9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor The computer program of operation, it is characterised in that the processor realizes such as claim 1 to 5 when performing the computer program The step of any one the method.
- 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, its feature exists In when the computer program is executed by processor the step of realization such as any one of claim 1 to 5 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711104384.1A CN107910013B (en) | 2017-11-10 | 2017-11-10 | Voice signal output processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711104384.1A CN107910013B (en) | 2017-11-10 | 2017-11-10 | Voice signal output processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107910013A true CN107910013A (en) | 2018-04-13 |
| CN107910013B CN107910013B (en) | 2021-09-24 |
Family
ID=61844674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711104384.1A Active CN107910013B (en) | 2017-11-10 | 2017-11-10 | Voice signal output processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107910013B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831500A (en) * | 2018-05-29 | 2018-11-16 | 平安科技（深圳）有限公司 | Sound enhancement method, device, computer equipment and storage medium |
| CN109102800A (en) * | 2018-07-26 | 2018-12-28 | 广州酷狗计算机科技有限公司 | A kind of method and apparatus that the determining lyrics show data |
| CN109637543A (en) * | 2018-12-12 | 2019-04-16 | 平安科技（深圳）有限公司 | The voice data processing method and device of sound card |
| CN109639904A (en) * | 2019-01-25 | 2019-04-16 | 努比亚技术有限公司 | A kind of handset mode method of adjustment, system and computer storage medium |
| CN110097884A (en) * | 2019-06-11 | 2019-08-06 | 大众问问(北京)信息科技有限公司 | A kind of voice interactive method and device |
| CN111383647A (en) * | 2018-12-28 | 2020-07-07 | 展讯通信（上海）有限公司 | Voice signal processing method and device and readable storage medium |
| CN111768794A (en) * | 2019-03-15 | 2020-10-13 | 上海博泰悦臻网络技术服务有限公司 | Voice noise reduction method, voice noise reduction system, equipment and storage medium |
| CN111796790A (en) * | 2019-04-09 | 2020-10-20 | 深圳市冠旭电子股份有限公司 | Sound effect adjusting method and device, readable storage medium and terminal equipment |
| WO2022151657A1 (en) * | 2021-01-18 | 2022-07-21 | 闻泰科技(深圳)有限公司 | Noise cancellation method and apparatus, and audio device and computer-readable storage medium |
| CN116168719A (en) * | 2022-12-26 | 2023-05-26 | 杭州爱听科技有限公司 | Sound gain adjusting method and system based on context analysis |
| US11908456B2 (en) | 2018-08-06 | 2024-02-20 | Tencent Technology (Shenzhen) Company Limited | Azimuth estimation method, device, and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038442A1 (en) * | 2004-07-22 | 2007-02-15 | Erik Visser | Separation of target acoustic signals in a multi-transducer arrangement |
| CN101272131A (en) * | 2007-03-13 | 2008-09-24 | 瑞昱半导体股份有限公司 | Programmable gain amplifier with noise cancellation |
| CN101976566A (en) * | 2010-07-09 | 2011-02-16 | 瑞声声学科技(深圳)有限公司 | Voice enhancement method and device using same |
| US8321215B2 (en) * | 2009-11-23 | 2012-11-27 | Cambridge Silicon Radio Limited | Method and apparatus for improving intelligibility of audible speech represented by a speech signal |
| US8364477B2 (en) * | 2005-05-25 | 2013-01-29 | Motorola Mobility Llc | Method and apparatus for increasing speech intelligibility in noisy environments |
| US8510106B2 (en) * | 2009-04-10 | 2013-08-13 | BYD Company Ltd. | Method of eliminating background noise and a device using the same |
| CN104064185A (en) * | 2013-03-18 | 2014-09-24 | 联想(北京)有限公司 | Information processing method and system and electronic device |
| CN104103278A (en) * | 2013-04-02 | 2014-10-15 | 北京千橡网景科技发展有限公司 | Real time voice denoising method and device |
| US8949120B1 (en) * | 2006-05-25 | 2015-02-03 | Audience, Inc. | Adaptive noise cancelation |
| CN104376848A (en) * | 2013-08-12 | 2015-02-25 | 展讯通信（上海）有限公司 | Voice signal processing method and device |
| CN104810024A (en) * | 2014-01-28 | 2015-07-29 | 上海力声特医学科技有限公司 | Double-path microphone speech noise reduction treatment method and system |
| CN105845151A (en) * | 2016-05-30 | 2016-08-10 | 百度在线网络技术（北京）有限公司 | Audio gain adjustment method and audio gain adjustment device applied to speech recognition front-end |
| CN106782586A (en) * | 2016-11-14 | 2017-05-31 | 阔地教育科技有限公司 | A kind of acoustic signal processing method and device |
| CN106898360A (en) * | 2017-04-06 | 2017-06-27 | 北京地平线信息技术有限公司 | Acoustic signal processing method, device and electronic equipment |
| CN107092461A (en) * | 2017-06-01 | 2017-08-25 | 深圳天珑无线科技有限公司 | The way of recording, device and computer-readable recording medium |
-
2017
- 2017-11-10 CN CN201711104384.1A patent/CN107910013B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070038442A1 (en) * | 2004-07-22 | 2007-02-15 | Erik Visser | Separation of target acoustic signals in a multi-transducer arrangement |
| US8364477B2 (en) * | 2005-05-25 | 2013-01-29 | Motorola Mobility Llc | Method and apparatus for increasing speech intelligibility in noisy environments |
| US8949120B1 (en) * | 2006-05-25 | 2015-02-03 | Audience, Inc. | Adaptive noise cancelation |
| CN101272131A (en) * | 2007-03-13 | 2008-09-24 | 瑞昱半导体股份有限公司 | Programmable gain amplifier with noise cancellation |
| US8510106B2 (en) * | 2009-04-10 | 2013-08-13 | BYD Company Ltd. | Method of eliminating background noise and a device using the same |
| US8321215B2 (en) * | 2009-11-23 | 2012-11-27 | Cambridge Silicon Radio Limited | Method and apparatus for improving intelligibility of audible speech represented by a speech signal |
| CN101976566A (en) * | 2010-07-09 | 2011-02-16 | 瑞声声学科技(深圳)有限公司 | Voice enhancement method and device using same |
| CN104064185A (en) * | 2013-03-18 | 2014-09-24 | 联想(北京)有限公司 | Information processing method and system and electronic device |
| CN104103278A (en) * | 2013-04-02 | 2014-10-15 | 北京千橡网景科技发展有限公司 | Real time voice denoising method and device |
| CN104376848A (en) * | 2013-08-12 | 2015-02-25 | 展讯通信（上海）有限公司 | Voice signal processing method and device |
| CN104810024A (en) * | 2014-01-28 | 2015-07-29 | 上海力声特医学科技有限公司 | Double-path microphone speech noise reduction treatment method and system |
| CN105845151A (en) * | 2016-05-30 | 2016-08-10 | 百度在线网络技术（北京）有限公司 | Audio gain adjustment method and audio gain adjustment device applied to speech recognition front-end |
| CN106782586A (en) * | 2016-11-14 | 2017-05-31 | 阔地教育科技有限公司 | A kind of acoustic signal processing method and device |
| CN106898360A (en) * | 2017-04-06 | 2017-06-27 | 北京地平线信息技术有限公司 | Acoustic signal processing method, device and electronic equipment |
| CN107092461A (en) * | 2017-06-01 | 2017-08-25 | 深圳天珑无线科技有限公司 | The way of recording, device and computer-readable recording medium |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108831500A (en) * | 2018-05-29 | 2018-11-16 | 平安科技（深圳）有限公司 | Sound enhancement method, device, computer equipment and storage medium |
| CN109102800A (en) * | 2018-07-26 | 2018-12-28 | 广州酷狗计算机科技有限公司 | A kind of method and apparatus that the determining lyrics show data |
| US11908456B2 (en) | 2018-08-06 | 2024-02-20 | Tencent Technology (Shenzhen) Company Limited | Azimuth estimation method, device, and storage medium |
| CN109637543A (en) * | 2018-12-12 | 2019-04-16 | 平安科技（深圳）有限公司 | The voice data processing method and device of sound card |
| CN111383647A (en) * | 2018-12-28 | 2020-07-07 | 展讯通信（上海）有限公司 | Voice signal processing method and device and readable storage medium |
| CN109639904A (en) * | 2019-01-25 | 2019-04-16 | 努比亚技术有限公司 | A kind of handset mode method of adjustment, system and computer storage medium |
| CN111768794A (en) * | 2019-03-15 | 2020-10-13 | 上海博泰悦臻网络技术服务有限公司 | Voice noise reduction method, voice noise reduction system, equipment and storage medium |
| CN111796790A (en) * | 2019-04-09 | 2020-10-20 | 深圳市冠旭电子股份有限公司 | Sound effect adjusting method and device, readable storage medium and terminal equipment |
| CN111796790B (en) * | 2019-04-09 | 2023-09-08 | 深圳市冠旭电子股份有限公司 | Sound effect adjusting method and device, readable storage medium and terminal equipment |
| CN110097884A (en) * | 2019-06-11 | 2019-08-06 | 大众问问(北京)信息科技有限公司 | A kind of voice interactive method and device |
| WO2022151657A1 (en) * | 2021-01-18 | 2022-07-21 | 闻泰科技(深圳)有限公司 | Noise cancellation method and apparatus, and audio device and computer-readable storage medium |
| CN116168719A (en) * | 2022-12-26 | 2023-05-26 | 杭州爱听科技有限公司 | Sound gain adjusting method and system based on context analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107910013B (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107910013A (en) | The output processing method and device of a kind of voice signal | |
| US20190206415A1 (en) | Method for processing voice in interior environment of vehicle and electronic device | |
| CN103827965B (en) | Adaptive voice intelligibility processor | |
| CA2382175C (en) | Noisy acoustic signal enhancement | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| CN110197670A (en) | Audio defeat method, apparatus and electronic equipment | |
| US10553236B1 (en) | Multichannel noise cancellation using frequency domain spectrum masking | |
| CN101483414A (en) | Voice intelligibility enhancement system and voice intelligibility enhancement method | |
| CN102197422A (en) | Audio source proximity estimation using sensor array for noise reduction | |
| CN110120225A (en) | A kind of audio defeat system and method for the structure based on GRU network | |
| CN112004177B (en) | Howling detection method, microphone volume adjustment method and storage medium | |
| CN106157967A (en) | Impulse noise mitigation | |
| CN106251856A (en) | A kind of environment noise based on mobile terminal eliminates system and method | |
| EP2752848B1 (en) | Method and apparatus for generating a noise reduced audio signal using a microphone array | |
| CN206312566U (en) | A kind of vehicle intelligent audio devices | |
| CN106448696A (en) | Adaptive high-pass filtering speech noise reduction method based on background noise estimation | |
| CN108305637A (en) | Earphone method of speech processing, terminal device and storage medium | |
| CN108235208A (en) | For running the method for hearing aid apparatus | |
| CN112602150A (en) | Noise estimation method, noise estimation device, voice processing chip and electronic equipment | |
| CN110428835A (en) | A kind of adjusting method of speech ciphering equipment, device, storage medium and speech ciphering equipment | |
| CN103580632A (en) | Automatic loudness control | |
| CN113241085A (en) | Echo cancellation method, device, equipment and readable storage medium | |
| CN110503973B (en) | Audio signal transient noise suppression method, system and storage medium | |
| CN108810746A (en) | A kind of sound quality optimization method, feedback noise reduction system, earphone and storage medium | |
| CN108899041B (en) | Voice signal noise adding method, device and 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 | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: OPPO Guangdong Mobile Communications Co.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |