CN107886963A - The method, apparatus and electronic equipment of a kind of speech processes - Google Patents
The method, apparatus and electronic equipment of a kind of speech processes Download PDFInfo
- Publication number
- CN107886963A CN107886963A CN201711071260.8A CN201711071260A CN107886963A CN 107886963 A CN107886963 A CN 107886963A CN 201711071260 A CN201711071260 A CN 201711071260A CN 107886963 A CN107886963 A CN 107886963A
- Authority
- CN
- China
- Prior art keywords
- voice
- speech parameter
- pending
- parameter value
- processing
- 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
- G10L21/003—Changing voice quality, e.g. pitch or formants
- G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
-
- G10L21/0202—
-
- 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
- G10L21/003—Changing voice quality, e.g. pitch or formants
- G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
- G10L21/013—Adapting to target pitch
- G10L2021/0135—Voice conversion or morphing
Abstract
The present embodiments relate to communication technical field, discloses a kind of method of speech processing, device and electronic equipment.The method of wherein described speech processes includes：Obtain pending voice；Receive the voice revision directive to the pending voice；According to the voice revision directive, default speech parameter value is obtained；If the default speech parameter value and the speech parameter of the pending voice mismatch, according to the default speech parameter value, the speech parameter of the pending voice is modified, the voice after being handled；Voice after the processing is sent to the electronic equipment of communication party.By being modified with upper type, the embodiment of the present invention the voice of user, the voice of beautification is generated, effectively meets demand of the user to beautification voice, drastically increases the auditory perception of speech play.
Description
Technical field
The present invention relates to communication technical field, and in particular to the method, apparatus and electronic equipment of a kind of speech processes.
Background technology
With the development of intelligent terminal and various social softwares, the exchange between people is more and more, wherein, word and language
Sound exchange is the most universal.The mode of speech exchange has a lot, such as telephone relation, voice-enabled chat, transmission voice etc..In voice
During exchange, sound represents the image of individual to a certain degree.Pleasing to the ear euphony allows people to feel pleasant happy, can find pleasure in
In further being talked with speaker.Therefore, dulcet sound can be people's bonus point, the welcome degree of lifting people.
Everybody is intended to possess the gentle full sound as announcer, but under reality, except normally speaking
Intonation, everyone is when just getting up, flu when sound can be hoarse, when special occasions mumbles, sound can not enough become clear etc.
Deng, in this case, can cause user to speech exchange produce rejection feeling.
Inventor has found that the speech processes of correlation technique can not effectively meet during the embodiment of the present invention is realized
User polishes the voice of oneself according to the hobby of oneself to correct, and is transmitted further to the demand of peer user.
The content of the invention
The embodiment of the present invention provides a kind of method, apparatus and electronic equipment of speech processes, to be carried out to the voice of user
Modification, the voice of beautification is generated, effectively meet demand of the user to beautification voice, drastically increase listening for speech play
Feel impression.
To achieve these goals, the embodiment of the invention discloses following technical scheme：
In a first aspect, the embodiments of the invention provide a kind of method of speech processes, including：Obtain pending voice；Connect
Receive the voice revision directive to the pending voice；According to the voice revision directive, default speech parameter value is obtained；If institute
State default speech parameter value and the speech parameter of the pending voice mismatches, according to the default speech parameter value, to institute
The speech parameter for stating pending voice is modified, the voice after being handled；Voice after the processing is sent to communication
The electronic equipment of side.
Wherein, methods described also includes：Receive sample voice；Speech parameter is extracted from the sample voice, and will be carried
The speech parameter got is stored as the default speech parameter value.
Wherein, after the pending voice of acquisition, methods described also includes：The pending voice is located in advance
Reason, the pretreatment include noise reduction.
Wherein, if being mismatched in the speech parameter of the default speech parameter value and the pending voice, according to
The default speech parameter value, is modified to the speech parameter of the pending voice, after the voice after being handled, institute
Stating method also includes：The adjust instruction to the voice after the processing is received, and according to the adjust instruction, after the processing
Voice be adjusted.
Wherein, before the voice by after the processing sends the electronic equipment to communication party, methods described is also wrapped
Include：The audition instruction to the voice after the processing is received, and according to the audition instruction, plays the voice after the processing.
Wherein, the speech parameter of the pending voice includes decibel, frequency and/or waveform.
Second aspect, the embodiments of the invention provide a kind of device of speech processes, including：Voice acquiring unit, is used for
Obtain pending voice；Revision directive receiving unit, for receiving the voice revision directive to the pending voice；Default ginseng
Number acquiring unit, for according to the voice revision directive, obtaining default speech parameter value；Amending unit, if for described pre-
If speech parameter value and the speech parameter of the pending voice mismatch, according to the default speech parameter value, treated to described
The speech parameter of processing voice is modified, the voice after being handled；Transmitting element, for the voice after the processing to be sent out
Deliver to the electronic equipment of communication party.
Wherein, described device also includes：Sample reception unit, for receiving sample voice；Parameter extraction unit, for from
The sample voice extracts speech parameter, and the speech parameter extracted is stored as into the default speech parameter value.
Wherein, after the voice acquiring unit, described device also includes：Pretreatment unit, for waiting to locate to described
Reason voice is pre-processed, and the pretreatment includes noise reduction.
Wherein, after the amending unit, described device also includes：Adjustment unit, after receiving to the processing
Voice adjust instruction, and according to the adjust instruction, the voice after the processing is adjusted.
Wherein, before the transmitting element, described device also includes：Audition unit, after receiving to the processing
Voice audition instruction, and according to the audition instruction, play the voice after the processing.
Wherein, the speech parameter of the pending voice includes decibel, frequency and/or waveform.
The third aspect, the embodiments of the invention provide a kind of electronic equipment of speech processes, including：
At least one processor；And
The memory being connected with least one processor communication；Wherein,
The memory storage has can be by the instruction of at least one computing device, and the instruction is by described at least one
Individual computing device, so that the method that at least one processor is able to carry out speech processes as described above.
Fourth aspect, the embodiment of the present invention additionally provide a kind of non-volatile computer readable storage medium storing program for executing, the calculating
Machine readable storage medium storing program for executing is stored with computer executable instructions, and the computer executable instructions are used to enable electronic equipment to hold
The method of row speech processes as described above.
5th aspect, the embodiment of the present invention additionally provide a kind of computer program product, the computer program product bag
The computer program being stored on non-transient computer readable storage medium storing program for executing is included, the computer program includes programmed instruction, when
When described program instruction is computer-executed, make the method for computer execution speech processes as described above.
The beneficial effect of the embodiment of the present invention is：In the case of being different from prior art, provided in an embodiment of the present invention one
The method of kind speech processes is by obtaining pending voice；Receive the voice revision directive to the pending voice；According to institute
Predicate sound revision directive, obtain default speech parameter value；If the default speech parameter value and the voice of the pending voice
Parameter mismatches, and according to the default speech parameter value, the speech parameter of the pending voice is modified, handled
Voice afterwards；Voice after the processing is sent to the electronic equipment of communication party.By with upper type, entering to the voice of user
Row modification, the voice of beautification is generated, effectively meet demand of the user to beautification voice, drastically increase speech play
Auditory perception.
Brief description of the drawings
One or more embodiments are illustrative by the picture in corresponding accompanying drawing, these exemplary theorys
The bright restriction not formed to embodiment, the element for having same reference numbers label in accompanying drawing are expressed as similar element, removed
Non- have a special statement, and composition does not limit the figure in accompanying drawing.
Fig. 1 is a kind of schematic flow sheet of the method for speech processes provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of the method for speech processes that another embodiment of the present invention provides；
Fig. 3 is a kind of application example schematic flow sheet of the method for speech processes provided in an embodiment of the present invention；
Fig. 4 is a kind of operation interface schematic diagram of smart mobile phone speech processes provided in an embodiment of the present invention；
Fig. 5 is that the embodiment of the present invention provides a kind of structural representation of the device of speech processes；
Fig. 6 is the structural representation of a kind of electronic equipment provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In addition, as long as technical characteristic involved in each embodiment of invention described below is each other not
Conflict can is formed to be mutually combined.
The embodiment of the present invention provides a kind of method, apparatus and electronic equipment of speech processes, and methods described and device can be with
Meet to modify the voice of user, generate the demand of the voice of beautification, drastically increase the auditory perception of speech play.
The method of the speech processes of the embodiment of the present invention, can have user interaction means and fortune in any suitable type
Performed in the user terminal of the processor of calculation ability, such as desktop computer, smart mobile phone, tablet personal computer and other users are whole
In end.
The device of the speech processes of the embodiment of the present invention can be used as one of software or hardware function units, independent
It is arranged in above-mentioned user terminal, it is real can also performs the present invention as the one of functional module integrated within a processor
The method for applying the speech processes of example.
In an embodiment of the present invention, electronic equipment can be smart mobile phone, it is computer, intelligent watch, Intelligent bracelet, flat
Plate computer, palm PC etc. have the electronic equipment of phonetic function.Above-mentioned electronic equipment supports various multipads
Install, one or more multipad in such as following multipad：Instant message application program, phone should
With program, video application, email application, digital video recorder application program and etc..
Specifically, below in conjunction with the accompanying drawings, the embodiment of the present invention is further elaborated.
Embodiment one
Fig. 1 is a kind of schematic flow sheet of the method for speech processes provided in an embodiment of the present invention.Referring to Fig. 1, voice
The method of processing is applied to electronic equipment, wherein, the method for the speech processes includes：
110th, pending voice is obtained；
In the present embodiment, above-mentioned " pending voice " can be that the user of the electronic equipment is defeated when sending instant message
The voice entered, such as the phonetic entry of wechat, voice-enabled chat etc.；Can also be the local audio file of the electronic equipment, such as
Recording file, music etc.；Voice when can also be telephone communication etc..The embodiment for obtaining pending voice can be with
For：The voice of instant message input is read from register；Or obtained by reading the audio-frequency information in memory or internal memory
Local audio file；Or voice of telephone communication etc. is read from register.
120th, the voice revision directive to the pending voice is received；
In the present embodiment, voice revision directive includes according to associative operation being distributed by electronic equipment and is used to perform such as
The instruction of " obtaining default speech parameter value " shown in next step, electronic equipment is according to corresponding to performing the voice revision directive
Event.Wherein, associative operation can be soft operation or hard operation, and soft operation can be that electronic equipment touches according to the output of advance logic
Signal, so that electronic equipment further distributes voice revision directive.Hard operation can be the outside correlation to electronic equipment
Hardware is operated and electronic equipment is distributed voice revision directive, for example, it may be touch-screen of the user in electronic equipment
The touch operation of progress, can be the operation of the button progress to electronic equipment, and etc..
When electronic equipment receives voice revision directive, the execution of next step is completed again according to logic of propositions.
130th, according to the voice revision directive, default speech parameter value is obtained；
In the present embodiment, the term of reference that speech parameter value is used for the amendment as pending voice, Ke Yiwei are preset
The parameter value for one section of oneself preferable sound that user prerecords, or the parameter value of the sound set for User Defined, or
Person is parameter value of system default sound, etc..Wherein, parameter value include but is not limited to the decibel of default voice, frequency and/or
Waveform.
Voice revision directive triggers electronic equipment, electronic equipment is obtained default speech parameter value.In acquisition process, electricity
Sub- equipment can preset speech parameter value according to corresponding to obtaining the type of the speech parameter of pending voice, if for example, waiting to locate
The speech parameter of reason voice includes decibel and frequency, then obtains the decibel of default voice and frequency is used as default speech parameter value.
Wherein, designer can voluntarily be joined according to business demand to component corresponding to electronic equipment and method with obtaining default voice
Numerical value.
If the 140th, the default speech parameter value and the speech parameter of the pending voice mismatch, according to described default
Speech parameter value, the speech parameter of the pending voice is modified, the voice after being handled；
In the present embodiment, the speech parameter of pending voice includes but is not limited to decibel, frequency and/or waveform, wherein,
The volume of decibel reflection sound, frequency reflect the tone of sound, and waveform reflects the tone color of sound.According to the voice of pending voice
Parameter, matched respectively with corresponding default speech parameter value, i.e., it is and default by the decibel of pending voice, frequency, waveform
Decibel, frequency, the waveform of voice are matched one by one.Wherein, " matching " can be that the speech parameter for judging pending voice is
It is no in the range of default speech parameter value, if in the range of, for matching；If not in the range of, to mismatch.For example,
The decibel of pending voice is 20dB, and the decibel range for presetting speech parameter value is 50-60dB, then the voice ginseng of pending voice
Number mismatches with default speech parameter value.
In the present embodiment, the speech parameter of pending voice being modified can be to join the voice of pending voice
Number is adjusted in the range of default speech parameter value, for example, the decibel of pending voice is 20dB, presets point of speech parameter value
Shellfish scope is 50-60dB, and the decibel of pending voice is adjusted into 55dB.Therefore, when default speech parameter value and pending language
When the speech parameter of sound mismatches, according to default speech parameter value, the speech parameter of pending voice is modified, obtained everywhere
Voice after reason, embodiment can be：The speech parameter of pending voice and default speech parameter value are respectively compared, is sentenced
Whether the speech parameter of disconnected pending voice is in the range of default speech parameter value, if it is not, then by the voice of pending voice
Parameter is modified to the numerical value in the range of default speech parameter value, the voice after being handled respectively.Such as：Point of pending voice
Shellfish is 20dB, and frequency 100Hz, waveform is x (t), and the decibel for presetting speech parameter value is 50-60dB, frequency 500-
700Hz, waveform are y (t), the decibel of pending voice are modified into 55dB, frequency is modified to 500Hz, and calculates x (t) and y
(t) dependency number Pxy, adjustment waveform x (t), until dependency number Pxy in the range of 0.6-1, then completes the language of pending voice
The amendment of sound parameter, the voice after being handled.
Wherein, the speech parameter of pending voice can also include word speed, phoneme etc..For example, to pending voice
Word speed is modified, and makes the speech speed after processing more appropriate, steady, so that it is more melodious.For example, pre-set default language
The standard phoneme of sound parameter value, it can be mandarin phoneme, Guangdong language phoneme, English phoneme etc., according to standard phoneme, treat place
The phoneme of reason voice is modified, so that the mandarin of voice, Guangdong language or English more standard.
150th, the voice after the processing is sent to the electronic equipment of communication party.
In the present embodiment, above-mentioned communication party can be the sending object of the instant message of user, the object of call, meeting
Object, the object that attends a lecture etc..The electronic equipment of communication party can be smart mobile phone, computer, intelligent watch, intelligent hand
Ring, tablet personal computer, palm PC or sound equipment etc..After user pleases oneself to the voice after processing, the transmission of user is received
Instruction, the transmission instruction user can click or long-press send button by way of input, then by after processing voice send out
The electronic equipment of communication party is delivered to, so as to bring good auditory perception to communication party.
The method for a kind of speech processes that the present embodiment provides, by obtaining pending voice；Receive to described pending
The voice revision directive of voice；According to the voice revision directive, default speech parameter value is obtained；If the default speech parameter
Value and the speech parameter of the pending voice mismatch, according to the default speech parameter value, to the pending voice
Speech parameter is modified, the voice after being handled；Voice after the processing is sent to the electronic equipment of communication party.It is logical
Cross with upper type, the voice of user is modified, generate the voice of beautification, effectively meet need of the user to beautification voice
Ask, drastically increase the auditory perception of speech play.
Embodiment two
Fig. 2 is a kind of schematic flow sheet of the method for speech processes that another embodiment of the present invention provides, as shown in Fig. 2
The method of speech processes is applied to electronic equipment, wherein, the method for the speech processes includes：
210th, sample voice is received；
In the present embodiment, user can pre-set default speech parameter value by recording sample voice.Sample voice
Can be user feel sound status it is good when one section of voice recording；Or can be that the hope that user records is imitated
Other people one section of voice, such as the voice of star, the voice etc. of host；Or can also be one section of language of cartoon character
Sound, such as the just following voice of sound, the voice etc. of RNB.
Wherein, user can record multiple sample voices, different default speech parameter values be pre-set, as different
Voice packet preserves.
220th, speech parameter is extracted from the sample voice, and the speech parameter extracted is stored as the default language
Sound parameter value；
In the present embodiment, can be from the embodiment of sample voice extraction speech parameter：Receiving
After sample voice, the electronic equipment stores the sample voice, then carries out signal transacting to the sample voice, extracts the sample
The speech parameter of voice.Wherein, speech parameter can include decibel, frequency, waveform etc..
230th, pending voice is obtained；
240th, the pending voice is pre-processed, the pretreatment includes noise reduction；
In the present embodiment, electronic equipment is after pending voice is obtained, because the user of electronic equipment is in input voice
When, the environment of surrounding may be more noisy, either user input speech volume may it is too small or due to Equipment make it is defeated
There is noise etc. in the voice entered, it is therefore desirable to which pending voice is pre-processed.Pretreatment can be noise reduction, and noise reduction refers to subtract
Few noise, such as ambient noise etc..Noise reduction can be realized by Digital Signal Processing, such as frequency-domain transform, wavelet transformation etc..
Pretreatment can also be amplification, and when the volume of pending voice is too small, voice is carried out to pending voice by signal transacting
Identification, and vocal sections are amplified.
250th, the voice revision directive to the pending voice is received；
260th, according to the voice revision directive, default speech parameter value is obtained；
If the 270th, the default speech parameter value and the speech parameter of the pending voice mismatch, according to described default
Speech parameter value, the speech parameter of the pending voice is modified, the voice after being handled；
280th, the adjust instruction to the voice after the processing is received, and according to the adjust instruction, after the processing
Voice be adjusted；
In the present embodiment, voice after user is to processing is still dissatisfied, it is desirable to when slightly being adjusted, unrestricted choice
Input adjust instruction is adjusted to the voice after processing.Adjust instruction can be inputted setting value, including decibel adjustment by user
Instruction, frequency adjust instruction etc..
281st, the audition instruction to the voice after the processing is received, and according to the audition instruction, plays the processing
Voice afterwards；
In the present embodiment, when user wish audition processing after voice, by triggering audition instruction, can be to processing after
Voice plays out.
Wherein, step 280 and step 281 can circulate progress, such as：Adjust instruction is received, receives audition instruction, is continued
Adjust instruction is received, continues to audition instruction ...
290th, the voice after the processing is sent to the electronic equipment of communication party.
A kind of method for speech processes that the present embodiment provides, by pre-setting default speech parameter value, obtains and waits to locate
Reason voice is simultaneously pre-processed, and is received the voice revision directive to pending voice and is obtained default speech parameter value；It is if default
Speech parameter value and the speech parameter of pending voice are mismatched, and the speech parameter of pending voice is modified, obtained everywhere
Voice after reason, audition, adjustment are carried out to the voice after processing, the voice after processing is sent to the electronic equipment of communication party.
By with upper type, the voice of user is modified, adjusted, customer satisfaction system voice is generated, effectively meets user
To the demand of beautification voice or conversion voice, the auditory perception of speech play is drastically increased, adds interest.
Embodiment three
Fig. 3 is a kind of application example schematic flow sheet of the method for speech processes provided in an embodiment of the present invention, the application
Example is illustrated for the method for the speech processes of smart mobile phone, as shown in figure 3, this method includes：
310th, receive sample voice and extract speech parameter, the speech parameter extracted is stored as default speech parameter
Value；
Also referring to Fig. 4, the smart mobile phone clicks on the button on screen by user, receives sample voice input and refers to
Order, user starts to input the good voice of one section of sound status, while is connect according to the sample voice input instruction, the smart mobile phone
Receive sample voice.After sample voice is received, the smart mobile phone stores the sample voice, and then the sample voice is entered
Row signal transacting, extract the speech parameter (including decibel, frequency, waveform) of the sample voice, and the speech parameter that will be extracted
It is stored as default speech parameter value.In the present embodiment, three default speech parameter values of the user preset of the smart mobile phone, point
These three are not preset into speech parameter value and saves as different voice packets：Beautify, be overcast, cheerful and light-hearted.
320th, grasped in the phonetic entry interface of the instant message application program of the smart mobile phone, the user for receiving input voice
Make, operated according to shown user and obtain pending voice, and the pending voice is pre-processed；
When user opens instant message application program, and the chat conversations frame of opening and contact person's first, it is desirable to send one
Duan Yuyin gives contact person's first, and user clicks on the button " pin and speak " on screen, the voice of a length of 10 seconds when starting to input one section,
The smart mobile phone obtains the voice as pending voice simultaneously, then noise reduction process is carried out to the pending voice, to reduce
Ambient noise.
330th, the voice revision directive to the pending voice is received, and according to the voice revision directive, is obtained pre-
If speech parameter value；
When user is dissatisfied to the sound status of the voice of input, it is desirable to when beautifying to the voice of input, at this
The voice revision directive of " beautification sound " is triggered on smart mobile phone, the smart mobile phone then obtains the default speech parameter of " beautification ".
If the 340th, the default speech parameter value and the speech parameter of the pending voice mismatch, according to described default
Speech parameter value, the speech parameter of the pending voice is modified, the voice after being handled；
Whether the smart mobile phone is matched by the default speech parameter of more pending voice and " beautification ", to unmatched
Pending voice segments are modified, and the speech parameter of pending voice is obtained in the range of the default speech parameter of " beautification "
Voice after processing.
350th, the audition instruction to the voice after the processing is received, and according to the audition instruction, plays the processing
Voice afterwards；
User wishes to be known a priori by the voice after " beautification " is handled, and audition is then triggered on the smart mobile phone refers to
Order, the smart mobile phone is according to the audition instruction, the voice after playback process.
360th, the adjust instruction to the voice after the processing is received, and according to the adjust instruction, after the processing
Voice be adjusted；
After voice after user is to processing carries out audition, it is believed that the speech volume after processing is too small, to result still
It is so dissatisfied, " volume+" adjust instruction then is triggered in the smart mobile phone, the smart mobile phone is right according to " volume+" adjust instruction
Voice after processing is amplified processing, to improve volume.
370th, the voice after the processing is sent to the electronic equipment of communication party.
After user pleases oneself to the voice after processing, the transmission instruction of user's triggering is received, by the voice after processing
Contact person's first is sent to, so as to bring different auditory perception on sense organ to contact person's first.
The present embodiment is by obtaining pending voice；Receive the voice revision directive to the pending voice；According to institute
Predicate sound revision directive, obtain default speech parameter value；If the default speech parameter value and the voice of the pending voice
Parameter mismatches, and according to the default speech parameter value, the speech parameter of the pending voice is modified, handled
Voice afterwards；Voice after the processing is sent to the electronic equipment of communication party.By with upper type, entering to the voice of user
Row modification, the voice of beautification is generated, effectively meet demand of the user to beautification voice, drastically increase speech play
Auditory perception.
Example IV
Fig. 5 is that the embodiment of the present invention provides a kind of structural representation of the device of speech processes.As shown in figure 5, the voice
Processing unit 500 is applied to electronic equipment, wherein, the voice processing apparatus 50 includes voice acquiring unit 510, revision directive connects
Receive unit 520, parameter preset acquiring unit 530, amending unit 540 and transmitting element 550.Voice acquiring unit 510 is used to obtain
Take pending voice；Revision directive receiving unit 520 is used to receive the voice revision directive to the pending voice；Default ginseng
Number acquiring unit 530 is used for according to the voice revision directive, obtains default speech parameter value；If amending unit 540 is used for institute
State default speech parameter value and the speech parameter of the pending voice mismatches, according to the default speech parameter value, to institute
The speech parameter for stating pending voice is modified, the voice after being handled；Transmitting element 550 is used for after the processing
Voice is sent to the electronic equipment of communication party.
Alternatively, device 500 also includes：Sample reception unit 560 is used to receive sample voice；Parameter extraction unit 561
For extracting speech parameter from the sample voice, and the speech parameter extracted is stored as the default speech parameter
Value.
Alternatively, after the voice acquiring unit 510, device 500 also includes：Pretreatment unit 570 is used for institute
State pending voice to be pre-processed, the pretreatment includes noise reduction.
Alternatively, after amending unit 540, device 500 also includes：Adjustment unit 570 is used to receive to the processing
The adjust instruction of voice afterwards, and according to the adjust instruction, the voice after the processing is adjusted.
Alternatively, before the transmitting element 550, device 500 also includes：Audition unit 580 is used to receive to described
The audition instruction of voice after processing, and according to the audition instruction, play the voice after the processing.
Alternatively, the speech parameter of the pending voice includes decibel, frequency and/or waveform.
Because device embodiment and embodiment of the method are to be based on same design, on the premise of content does not conflict mutually, dress
The content for putting embodiment can be will not be described here with quoting method embodiment.
The voice processing apparatus 500 that the present embodiment provides can be modified the voice of user, generate the voice of beautification,
Demand of the user to beautification voice is effectively met, drastically increases the auditory perception of speech play.
Embodiment five
Fig. 6 is the structural representation of a kind of electronic equipment provided in an embodiment of the present invention, as shown in fig. 6, the electronic equipment
600 include：
One or more processors 610 and memory 620, in Fig. 6 by taking a processor 610 as an example.
Processor 610 can be connected with memory 620 by bus or other modes, to be connected by bus in Fig. 6
Exemplified by.
Memory 620 is used as a kind of non-volatile computer readable storage medium storing program for executing, available for storage non-volatile software journey
Sequence, non-volatile computer executable program and module, as corresponding to the instant message based reminding method in the embodiment of the present invention
Programmed instruction/module is (for example, the voice acquiring unit 510, revision directive receiving unit 520, parameter preset shown in accompanying drawing 5 obtain
Take unit 530, amending unit 540 and transmitting element 550).Processor 610 is stored in non-easy in memory 620 by operation
The property lost software program, instruction and module, so as to perform the various function application of the user terminal and data processing, that is, are realized
The method of the speech processes of above method embodiment.
Memory 620 can include storing program area and storage data field, wherein, storing program area can store operation system
Application program required for system, at least one function；Storage data field can store uses institute according to instant message alarm set
Data of establishment etc..In addition, memory 620 can include high-speed random access memory, non-volatile memories can also be included
Device, for example, at least a disk memory, flush memory device or other non-volatile solid state memory parts.In some embodiments
In, memory 620 is optional including that can pass through net relative to the remotely located memory of processor 610, these remote memories
Network is connected to instant message alarm set.The example of above-mentioned network include but is not limited to internet, intranet, LAN,
Mobile radio communication and combinations thereof.
One or more of modules are stored in the memory 620, when by one or more of processors
During 610 execution, the method for the speech processes in above-mentioned any means embodiment is performed, for example, performing in Fig. 1 described above
Method and step 110 realizes the function of the modules or unit described in the unit 510-550 in Fig. 4 to step 150.
The embodiment of the present invention additionally provides a kind of nonvolatile computer storage media, the computer-readable storage medium storage
There are computer executable instructions, the computer executable instructions are executed by one or more processors, such as at one in Fig. 6
Device 610 is managed, may be such that said one or the method that multiple processors can perform the speech processes in above-mentioned any means embodiment,
For example, the method for the speech processes in above-mentioned any means embodiment is performed, for example, performing shown in Fig. 1 described above to Fig. 3
Each step；Also the function of the modules or unit described in accompanying drawing 4 can be realized.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can
To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list
Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs
In some or all of module realize the purpose of this embodiment scheme.
Through the above description of the embodiments, those of ordinary skill in the art can be understood that each embodiment
The mode of general hardware platform can be added by software to realize, naturally it is also possible to pass through hardware.Those of ordinary skill in the art can
To understand that all or part of flow realized in above-described embodiment method is can to instruct the hard of correlation by computer program
Part is completed, and described program can be stored in a computer read/write memory medium, the program is upon execution, it may include as above
State the flow of the embodiment of each method.Wherein, described storage medium can be magnetic disc, CD, read-only memory (Read-
Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；At this
Under the thinking of invention, it can also be combined between the technical characteristic in above example or different embodiments, step can be with
Realized with random order, and many other changes of the different aspect of the present invention as described above be present, for simplicity, they do not have
Have and provided in details；Although the present invention is described in detail with reference to the foregoing embodiments, the ordinary skill people of this area
Member should be understood：It can still modify to the technical scheme described in foregoing embodiments, or to which part skill
Art feature carries out equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from each reality of the present invention
Apply the scope of a technical scheme.
Claims (14)
1. a kind of method of speech processes, applied to electronic equipment, including：
Obtain pending voice；
Receive the voice revision directive to the pending voice；
According to the voice revision directive, default speech parameter value is obtained；
If the default speech parameter value and the speech parameter of the pending voice mismatch, according to the default speech parameter
Value, is modified, the voice after being handled to the speech parameter of the pending voice；
Voice after the processing is sent to the electronic equipment of communication party.
2. according to the method for claim 1, it is characterised in that methods described also includes：
Receive sample voice；
Speech parameter is extracted from the sample voice, and the speech parameter extracted is stored as the default speech parameter
Value.
3. according to the method for claim 2, it is characterised in that after the pending voice of acquisition, methods described is also
Including：
The pending voice is pre-processed, the pretreatment includes noise reduction.
4. according to the method for claim 2, it is characterised in that if waiting to locate with described in the default speech parameter value
The speech parameter for managing voice is mismatched, and according to the default speech parameter value, the speech parameter of the pending voice is carried out
Correct, after the voice after being handled, methods described also includes：
The adjust instruction to the voice after the processing is received, and according to the adjust instruction, the voice after the processing is entered
Row adjustment.
5. according to the method for claim 4, it is characterised in that sent in the voice by after the processing to communication party
Electronic equipment before, methods described also includes：
The audition instruction to the voice after the processing is received, and according to the audition instruction, plays the voice after the processing.
6. according to the method described in claim 1-5, it is characterised in that the speech parameter of the pending voice include decibel,
Frequency and/or waveform.
A kind of 7. device of speech processes, applied to electronic equipment, it is characterised in that including：
Voice acquiring unit, for obtaining pending voice；
Revision directive receiving unit, for receiving the voice revision directive to the pending voice；
Parameter preset acquiring unit, for according to the voice revision directive, obtaining default speech parameter value；
Amending unit, if being mismatched for the speech parameter of the default speech parameter value and the pending voice, according to institute
Default speech parameter value is stated, the speech parameter of the pending voice is modified, the voice after being handled；
Transmitting element, for the voice after the processing to be sent to the electronic equipment of communication party.
8. device according to claim 7, it is characterised in that described device also includes：
Sample reception unit, for receiving sample voice；
Parameter extraction unit, for extracting speech parameter from the sample voice, and the speech parameter extracted is stored as
The default speech parameter value.
9. device according to claim 8, it is characterised in that after the voice acquiring unit, described device is also wrapped
Include：
Pretreatment unit, for being pre-processed to the pending voice, the pretreatment includes noise reduction.
10. device according to claim 8, it is characterised in that after the amending unit, described device also includes：
Adjustment unit, for receiving the adjust instruction to the voice after the processing, and according to the adjust instruction, to the place
Voice after reason is adjusted.
11. device according to claim 10, it is characterised in that before the transmitting element, described device also includes：
Audition unit, for receiving to the audition instruction of the voice after the processing, and according to the audition instruction, described in broadcasting
Voice after processing.
12. according to the device described in claim any one of 7-11, it is characterised in that the speech parameter bag of the pending voice
Include decibel, frequency and/or waveform.
13. a kind of electronic equipment, it is characterised in that including：
At least one processor；And
The memory being connected with least one processor communication；Wherein,
The memory storage has can be by the instruction of at least one computing device, and the instruction is by least one place
Manage device to perform, so that at least one processor is able to carry out the method described in claim any one of 1-6.
14. a kind of non-volatile computer readable storage medium storing program for executing, the computer-readable recording medium storage have computer to hold
Row instruction, the computer executable instructions are used to make user terminal be able to carry out the method described in claim any one of 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711071260.8A CN107886963B (en) | 2017-11-03 | 2017-11-03 | A kind of method, apparatus and electronic equipment of speech processes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711071260.8A CN107886963B (en) | 2017-11-03 | 2017-11-03 | A kind of method, apparatus and electronic equipment of speech processes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107886963A true CN107886963A (en) | 2018-04-06 |
| CN107886963B CN107886963B (en) | 2019-10-11 |
Family
ID=61778818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711071260.8A Active CN107886963B (en) | 2017-11-03 | 2017-11-03 | A kind of method, apparatus and electronic equipment of speech processes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107886963B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108965967A (en) * | 2018-05-25 | 2018-12-07 | 苏州浪潮智能软件有限公司 | TV control method and device, computer readable storage medium, terminal |
| CN110677521A (en) * | 2019-10-24 | 2020-01-10 | 北京九狐时代智能科技有限公司 | Fixed-line equipment and audio signal processing method |
| WO2020232578A1 (en) * | 2019-05-17 | 2020-11-26 | Xu Junli | Memory, microphone, audio data processing method and apparatus, and device and system |
| CN112216275A (en) * | 2019-07-10 | 2021-01-12 | 阿里巴巴集团控股有限公司 | Voice information processing method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103903627A (en) * | 2012-12-27 | 2014-07-02 | 中兴通讯股份有限公司 | Voice-data transmission method and device |
| CN104144097A (en) * | 2013-05-07 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Voice message transmission system, sending end, receiving end and voice message transmission method |
| CN104538011A (en) * | 2014-10-30 | 2015-04-22 | 华为技术有限公司 | Tone adjusting method and device and terminal device |
| CN105448300A (en) * | 2015-11-12 | 2016-03-30 | 小米科技有限责任公司 | Method and device for calling |
| CN105989832A (en) * | 2015-02-10 | 2016-10-05 | 阿尔卡特朗讯 | Method of generating personalized voice in computer equipment and apparatus thereof |
-
2017
- 2017-11-03 CN CN201711071260.8A patent/CN107886963B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103903627A (en) * | 2012-12-27 | 2014-07-02 | 中兴通讯股份有限公司 | Voice-data transmission method and device |
| CN104144097A (en) * | 2013-05-07 | 2014-11-12 | 百度在线网络技术（北京）有限公司 | Voice message transmission system, sending end, receiving end and voice message transmission method |
| CN104538011A (en) * | 2014-10-30 | 2015-04-22 | 华为技术有限公司 | Tone adjusting method and device and terminal device |
| CN105989832A (en) * | 2015-02-10 | 2016-10-05 | 阿尔卡特朗讯 | Method of generating personalized voice in computer equipment and apparatus thereof |
| CN105448300A (en) * | 2015-11-12 | 2016-03-30 | 小米科技有限责任公司 | Method and device for calling |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108965967A (en) * | 2018-05-25 | 2018-12-07 | 苏州浪潮智能软件有限公司 | TV control method and device, computer readable storage medium, terminal |
| WO2020232578A1 (en) * | 2019-05-17 | 2020-11-26 | Xu Junli | Memory, microphone, audio data processing method and apparatus, and device and system |
| CN112216275A (en) * | 2019-07-10 | 2021-01-12 | 阿里巴巴集团控股有限公司 | Voice information processing method and device and electronic equipment |
| CN110677521A (en) * | 2019-10-24 | 2020-01-10 | 北京九狐时代智能科技有限公司 | Fixed-line equipment and audio signal processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107886963B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977183A (en) | voice interactive method, device and equipment | |
| CN107886963B (en) | A kind of method, apparatus and electronic equipment of speech processes | |
| CN108198569B (en) | Audio processing method, device and equipment and readable storage medium | |
| US11475897B2 (en) | Method and apparatus for response using voice matching user category | |
| CN109326289A (en) | Exempt to wake up voice interactive method, device, equipment and storage medium | |
| CN108922525B (en) | Voice processing method, device, storage medium and electronic equipment | |
| CN106992008A (en) | Processing method and electronic equipment | |
| CN107293300A (en) | Audio recognition method and device, computer installation and readable storage medium storing program for executing | |
| JP2015517709A (en) | A system for adaptive distribution of context-based media | |
| US20210125610A1 (en) | Ai-driven personal assistant with adaptive response generation | |
| CN110047484A (en) | A kind of speech recognition exchange method, system, equipment and storage medium | |
| CN106791024A (en) | Voice messaging player method, device and terminal | |
| CN109994106A (en) | A kind of method of speech processing and equipment | |
| CN107465818A (en) | The method and terminal of a kind of virtual incoming call | |
| WO2017172655A1 (en) | Analysis of a facial image to extract physical and emotional characteristics of a user | |
| CN107515765A (en) | A kind of method for closing of quarter-bell, system and terminal device | |
| CN107632813A (en) | A kind of method and device for closing alarm clock function | |
| CN108364346B (en) | Method, apparatus and computer readable storage medium for constructing three-dimensional face model | |
| CN109887509A (en) | A kind of control method of ordering, electronic equipment and storage medium based on vocal print | |
| CN115312079A (en) | Information display method and device, electronic equipment and computer readable medium | |
| CN107656923A (en) | Voice translation method and device | |
| WO2019242415A1 (en) | Position prompt method, device, storage medium and electronic device | |
| CN116016779A (en) | Voice call translation assisting method, system, computer equipment and storage medium | |
| CN109725798A (en) | The switching method and relevant apparatus of Autonomous role | |
| CN108833688A (en) | Position reminding method, apparatus, storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |