CN108735224A - Audio modification method based on distributed frame and device - Google Patents
Audio modification method based on distributed frame and device Download PDFInfo
- Publication number
- CN108735224A CN108735224A CN201810322060.3A CN201810322060A CN108735224A CN 108735224 A CN108735224 A CN 108735224A CN 201810322060 A CN201810322060 A CN 201810322060A CN 108735224 A CN108735224 A CN 108735224A
- Authority
- CN
- China
- Prior art keywords
- audio
- terminal
- calculation
- itself
- distributed
- 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
- 238000002715 modification method Methods 0.000 title claims abstract description 27
- 238000004364 calculation method Methods 0.000 claims abstract description 251
- 238000000034 method Methods 0.000 claims abstract description 21
- 230000008439 repair process Effects 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 abstract description 4
- 238000000605 extraction Methods 0.000 description 16
- 230000008859 change Effects 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000033764 rhythmic process Effects 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/003—Changing voice quality, e.g. pitch or formants
- G10L21/007—Changing voice quality, e.g. pitch or formants characterised by the process used
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
This application discloses a kind of terminal audio frequency modification method and device based on distributed frame.This method includes：Obtain the first audio-frequency information of the first user；First, which is obtained, according to first audio-frequency information estimates calculation amount；Judge that described first estimates whether calculation amount exceeds the first of the terminal the itself calculation power；If it is determined that described first estimates first itself calculation power of the calculation amount beyond the terminal, then corrects server to audio and send the request of the first Distributed Calculation；The audio is received to correct the first result of calculation of server return and continue with audio amendment；By the way of judging whether estimate calculation amount exceeds itself calculation power of terminal, Distributed Calculation request is sent by correcting server to audio, reach the result of calculation for receiving audio amendment server return and continues with the modified purpose of audio, to realize the technique effect that operand is reasonably allocated to server end, and then it is low to solve the problems, such as that correlation repaiies sound computational efficiency.
Description
Technical field
This application involves sound field is repaiied, in particular to a kind of audio modification method and dress based on distributed frame
It sets.
Background technology
As communication and the high speed development of information technology, music function have become one in the terminals such as computer or mobile phone
The indispensable application of item, singing on mobile phone also becomes to become more and more popular, but since different people is to the sensing capability of musicality and melody
Irregular, the case where out of tune or rhythm is not caught up with, happens occasionally, and seriously affects the mood of singing, repaiies sound technology thus thus
It generates.
Correlation is repaiied all about calculating for repairing sound in sound technology and is all handled at client (mobile phone)；Implementing this to repair sound side
When method, inventor has found that correlation is repaiied sound technology and had at least the following problems：One, client needs to handle a large amount of calculating, power consumption
Greatly, power consumption, real-time are poor；Two, all types are not adapted to, and sound cannot be repaiied using a key by configuring poor mobile phone；For
Above-mentioned correlation repaiies the problems in sound technology, inventor provides a kind of solution.
Invention content
The main purpose of the application is to provide a kind of audio modification method and device based on distributed frame, to solve
Correlation repaiies the problem of repairing sound inefficiency caused by sound calculating is all placed in terminal.
To achieve the goals above, according to the one side of the application, a kind of terminal based on distributed frame is provided
Audio modification method.
Include according to the terminal audio frequency modification method based on distributed frame of the application：Obtain the first sound of the first user
Frequency information；First, which is obtained, according to first audio-frequency information estimates calculation amount；Judge that described first estimates whether calculation amount exceeds
The first of the terminal itself calculates power；If it is determined that described first estimates first itself calculation power of the calculation amount beyond the terminal,
Then server is corrected to audio send the request of the first Distributed Calculation；It receives the audio and corrects the first calculating that server returns
As a result and audio amendment is continued with.
Further, according to first audio-frequency information, obtain first and estimate calculation amount include：According to first audio
The audio frequency characteristics of information obtain the first audio frequency characteristics and estimate calculation amount；Judge that whether described first estimate calculation amount beyond described
The first of terminal itself itself calculates power：Judge that first audio frequency characteristics estimate whether calculation amount exceeds the terminal itself
First itself calculate power；If it is determined that described first estimate calculation amount beyond the terminal itself first itself calculate power, then to
Audio corrects server transmission the first Distributed Calculation request：Surpass if it is determined that first audio frequency characteristics estimate calculation amount
Go out the terminal itself first itself and calculate power, then correcting server to audio sends the first audio frequency characteristics computation requests.
Further, according to first audio-frequency information, obtain first and estimate calculation amount include：According to first audio
The voice signal of information obtains the first speech recognition and estimates calculation amount；Judge that whether described first estimate calculation amount beyond described
The first of terminal itself itself calculates power：Judge that first speech recognition estimates whether calculation amount exceeds the terminal itself
First itself calculate power；If it is determined that described first estimate calculation amount beyond the terminal itself first itself calculate power, then to
Audio corrects server transmission the first Distributed Calculation request：Surpass if it is determined that calculation amount is estimated in first speech recognition
Go out the terminal itself first itself and calculate power, then correcting server to audio sends the first speech recognition computation requests.
Further, according to first audio-frequency information, obtain first and estimate calculation amount include：According to first audio
What information and preset standard audio template obtained after comparing first repaiies sound parameter, and repaiies sound parameter by described first, obtains the
One, which repaiies sound, estimates calculation amount；Judge that whether described first estimate calculation amount beyond the terminal itself first itself calculation power packet
It includes：Judge described first repair sound estimate calculation amount whether beyond the terminal itself first itself calculate power；If it is determined that described
First estimates calculation amount calculates power beyond the terminal itself first itself, then correcting server to audio sends the first distribution
Computation requests include：If it is determined that described first repair sound estimate calculation amount beyond the terminal itself first itself calculate power, then
Server transmission first, which is corrected, to audio repaiies sound computation requests.
To achieve the goals above, according to the another aspect of the application, a kind of terminal based on distributed frame is provided
Audio correcting device.
Include according to the terminal audio frequency correcting device based on distributed frame of the application：Acquiring unit, for obtaining the
The first audio-frequency information of one user；Computing unit, for according to first audio-frequency information, obtaining first and estimating calculation amount；Sentence
Disconnected unit, for judging that whether described first estimate calculation amount beyond the terminal itself first itself calculation power；Request is sent
Unit, for if it is determined that described first estimate calculation amount beyond the terminal itself first itself calculate power, then repaiied to audio
Positive server sends the request of the first Distributed Calculation；Continue to repair sound unit, corrects what server returned for receiving the audio
First result of calculation simultaneously continues with audio amendment.
To achieve the goals above, according to the one side of the application, a kind of service based on distributed frame is provided
Device end audio modification method.
Include according to the server end audio modification method based on distributed frame of the application：Receive what terminal was sent
First Distributed Calculation is asked；It is asked according to first Distributed Calculation, obtains the first Distributed Calculation result；By described
One Distributed Calculation result is sent to the terminal, so that the terminal is preset according to the first Distributed Calculation result
Repair sound processing.
Further, receiving the first Distributed Calculation request that terminal is sent includes：Receive terminal is sent first
Audio frequency characteristics computation requests；It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：According to institute
The first audio frequency characteristics computation requests are stated, the first audio frequency characteristics value is obtained；The first Distributed Calculation result is sent to described
Terminal, so that the terminal according to the first Distributed Calculation result default repair sound processing and include：By first sound
Frequency characteristic value is sent to the terminal, is handled so that the terminal carries out default sound of repairing according to the first audio frequency characteristics value.
Further, receiving the first Distributed Calculation request that terminal is sent includes：Receive terminal is sent first
Speech recognition computation requests；It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：According to institute
The first speech recognition computation requests are stated, the first voice recognition result is obtained；By first voice recognition result and preset standard
Audio template is compared, and obtains first and repaiies sound parameter；The first Distributed Calculation result is sent to the terminal, so that
The terminal according to the first Distributed Calculation result preset repairing sound and handling：Sound parameter is repaiied by described first to send
To the terminal, so that the terminal according to described first repaiies sound parameter and carries out default sound of repairing and handles.
Further, receiving the first Distributed Calculation request that terminal is sent includes：Receive terminal is sent first
Repair sound computation requests；It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：According to described
One repaiies sound computation requests, obtains revised first audio-frequency information；The first Distributed Calculation result is sent to the end
End, so that the terminal according to the first Distributed Calculation result default repair sound processing and include：It will be described revised
First audio-frequency information is sent to the terminal, so that the terminal is shown broadcasting according to revised first audio-frequency information.
To achieve the goals above, according to the another aspect of the application, a kind of service based on distributed frame is provided
Device end audio correcting device.
Include according to the server end audio correcting device based on distributed frame of the application：Receiving unit, for connecing
Receive the first Distributed Calculation request that terminal is sent；Processing unit is obtained for being asked according to first Distributed Calculation
First Distributed Calculation result；Unit is returned the result, for the first Distributed Calculation result to be sent to the terminal, with
Make the terminal carry out default sound of repairing according to the first Distributed Calculation result to handle.
In the embodiment of the present application, by the way of judging whether estimate calculation amount exceeds itself calculation power of terminal, pass through
To audio correct server send Distributed Calculation request, reached receive audio correct server return result of calculation and after
The continuous processing modified purpose of audio, to realize the technique effect that operand is reasonably allocated to server end, and then solves
Correlation repaiies the problem of repairing sound inefficiency caused by sound calculating is all placed in terminal.
Description of the drawings
The attached drawing constituted part of this application is used for providing further understanding of the present application so that the application's is other
Feature, objects and advantages become more apparent upon.The illustrative examples attached drawing and its explanation of the application is for explaining the application, not
Constitute the improper restriction to the application.In the accompanying drawings：
Fig. 1 is terminal audio frequency modification method schematic diagram according to a first embodiment of the present invention；
Fig. 2 is terminal audio frequency modification method schematic diagram according to a second embodiment of the present invention；
Fig. 3 is terminal audio frequency modification method schematic diagram according to a third embodiment of the present invention；
Fig. 4 is terminal audio frequency modification method schematic diagram according to a fourth embodiment of the present invention；
Fig. 5 is terminal audio frequency correcting device schematic diagram according to a first embodiment of the present invention；
Fig. 6 is server end audio modification method schematic diagram according to a fifth embodiment of the present invention；
Fig. 7 is server end audio modification method schematic diagram according to a sixth embodiment of the present invention；
Fig. 8 is server end audio modification method schematic diagram according to a seventh embodiment of the present invention；
Fig. 9 is server end audio modification method schematic diagram according to a eighth embodiment of the present invention；And
Figure 10 is server end audio correcting device schematic diagram according to a fifth embodiment of the present invention.
Specific implementation mode
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described embodiment is only
The embodiment of the application part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model of the application protection
It encloses.
It should be noted that term " first " in the description and claims of this application and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to embodiments herein described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment those of are not necessarily limited to clearly to list step or unit, but may include without clear
It is listing to Chu or for these processes, method, product or equipment intrinsic other steps or unit.
In this application, term "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on ... shown in the drawings or
Position relationship.These terms are not intended to limit indicated dress primarily to preferably describe the present invention and embodiment
It sets, element or component must have particular orientation, or be constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term "upper" also are likely used for indicating certain relations of dependence or connection relation in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in the present invention can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction；Can be mechanical connection, or electrical connection；It can be direct phase
Even, or indirectly connected through an intermediary, or it is two connections internal between device, element or component.
For those of ordinary skills, the specific meanings of the above terms in the present invention can be understood according to specific conditions.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
As shown in Figure 1, this method includes following step S101 to step S105：
Step S101 obtains the first audio-frequency information of the first user；
Preferably, first audio-frequency information is that can obtain the song sound that user sings by the microphone of mobile terminal
Frequently, which is preferably the dry sound audio for the song that user sings.
Specifically, the mobile terminal can be the electronic equipment with sound-recording function such as mobile phone, tablet computer.
Step S102 obtains first according to first audio-frequency information and estimates calculation amount；
Preferably, carrying out the step of repairing sound to first audio-frequency information includes but not limited to：Recording, extraction voice are special
Sign, speech recognition, matching, the change of voice of recognition result and masterplate, specifically, since the data-interface between each module is bright
It has really been defined, therefore the equipment that sound can be repaiied to execution carries out computing capability assessment, the assessment includes but not limited to：Record
Sound assessment, the assessment of extraction phonetic feature, speech recognition assessment, matching assessment, the change acoustic evaluation of recognition result and masterplate, specifically
, described first, which estimates calculation amount, includes but not limited to：Calculation amount is estimated in recording, extraction phonetic feature estimates calculation amount, voice
Calculation amount is estimated in the matching that calculation amount, recognition result and masterplate are estimated in identification, calculation amount is estimated in the change of voice.
Step S103 judges that described first estimates whether calculation amount exceeds the first of the terminal the itself calculation power；
Preferably, mobile terminal used by a user is had nothing in common with each other, thus the respective manufacture of terminal of every different model
Operational capability is also not quite similar, and the power of terminal CPU processor performance is to influence an absolutely essential factor of computing capability, meter
Calculation ability can compare between different architecture instruction sets, be exactly briefly that execution how many times per second calculate, from several megahertzs of list
Piece machine can follow this index to huge super calculation, specifically, the described first itself calculation power is to execute the equipment for repairing sound
Residue computing capability in real time.
Step S104, if it is determined that described first estimates first itself calculation power of the calculation amount beyond the terminal, then to sound
Frequency corrects server and sends the request of the first Distributed Calculation；
Preferably, first Distributed Calculation request includes but not limited to：Recording computation requests, extraction phonetic feature meter
Calculation request, the matching primitives request of speech recognition computation requests, recognition result and masterplate, change of voice computation requests etc. can also be
The modified calculating step of other audios.
Step S105 receives the audio and corrects the first result of calculation of server return and continue with audio amendment.
Preferably, the audio corrects server and is used to repair sound according to first Distributed Calculation request progress is corresponding
It calculates, and result of calculation is returned into the terminal, so that sound processing is repaiied in terminal completion.
Specifically, first result of calculation includes but not limited to：Recording result of calculation, extraction phonetic feature calculate knot
Fruit, speech recognition result of calculation, the matching primitives result of recognition result and masterplate, change of voice result of calculation etc..
It can be seen from the above description that the present invention realizes following technique effect：
In the embodiment of the present application, by the way of judging whether estimate calculation amount exceeds itself calculation power of terminal, pass through
To audio correct server send Distributed Calculation request, reached receive audio correct server return result of calculation and after
The continuous processing modified purpose of audio, to realize the technique effect that operand is reasonably allocated to server end, and then solves
Correlation repaiies the problem of repairing sound inefficiency caused by sound calculating is all placed in terminal.
According to an embodiment of the present application, as preferred in embodiment, as shown in Fig. 2, further include following steps S201 extremely
Step S203：
According to first audio-frequency information, obtain first and estimate calculation amount include：
Step S201 obtains the first audio frequency characteristics and estimates calculation amount according to the audio frequency characteristics of first audio-frequency information；
Preferably, first audio-frequency information includes audio frequency characteristics, and extraction audio frequency characteristics are in audio makeover process
A wherein step obtains the first audio frequency characteristics and estimates calculation amount according to first audio-frequency information, that is, carries out audio feature extraction work
Make required operational capability.
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Step S202 judges that first audio frequency characteristics estimate whether calculation amount exceeds the terminal itself first itself
Calculate power；
Preferably, judge whether the real-time remaining computing capability of terminal used by a user meets carry out audio feature extraction
Work required operational capability.
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment
Server sends the request of the first Distributed Calculation：
Step S203, if it is determined that first audio frequency characteristics, which estimate calculation amount, exceeds the terminal itself first itself
Power is calculated, then correcting server to audio sends the first audio frequency characteristics computation requests.
Preferably, if it is determined that the real-time remaining computing capability of terminal used by a user cannot meet carry out audio frequency characteristics
The required operational capability of work is extracted, then correcting server to audio sends the first audio frequency characteristics computation requests.
According to an embodiment of the present application, as preferred in embodiment, as shown in figure 3, further include following steps S301 extremely
Step S303：
According to first audio-frequency information, obtain first and estimate calculation amount include：
Step S301 obtains the first speech recognition and estimates calculation amount according to the voice signal of first audio-frequency information；
Preferably, first audio-frequency information includes voice signal, and it is in audio makeover process to carry out speech recognition
A wherein step obtains the first voice signal and estimates calculation amount according to first audio-frequency information, that is, carries out speech recognition work institute
The operational capability needed.
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Step S302 judges that first speech recognition estimates whether calculation amount exceeds the terminal itself first itself
Calculate power；
Preferably, judge whether the real-time remaining computing capability of terminal used by a user meets and carry out speech recognition work
Required operational capability.
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment
Server sends the request of the first Distributed Calculation：
Step S303, if it is determined that calculation amount is estimated in first speech recognition exceeds the terminal itself first itself
Power is calculated, then correcting server to audio sends the first speech recognition computation requests.
Preferably, if it is determined that the real-time remaining computing capability of terminal used by a user cannot meet carry out speech recognition
Work required operational capability, then correcting server to audio sends the first speech recognition computation requests.
According to an embodiment of the present application, as preferred in embodiment, as shown in figure 4, further include following steps S401 extremely
Step S403：
According to first audio-frequency information, obtain first and estimate calculation amount include：
Step S401, first obtained after being compared according to first audio-frequency information and preset standard audio template repair sound ginseng
Number, and repaiies sound parameter by described first, obtains first and repair sound estimating calculation amount；
Preferably, first audio-frequency information is compared with preset standard audio template, obtains first and repaiies sound parameter,
And sound parameter is repaiied by described first, it obtains first and repaiies sound estimating calculation amount, repair sound parameter according to described first and carry out repairing sound and be
A wherein step in audio makeover process.
Specifically, described first repair sound parameter be first audio-frequency information pitch, rhythm etc. with it is described default
The difference of standard audio template.
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Step S402, judge described first repair sound estimate calculation amount whether beyond the terminal itself first itself calculate
Power；
Preferably, judge whether the real-time remaining computing capability of terminal used by a user meets repair needed for sound work
The operational capability wanted.
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment
Server sends the request of the first Distributed Calculation：
Step S403, if it is determined that described first repair sound estimate calculation amount beyond the terminal itself first itself calculate
Power then corrects server transmission first to audio and repaiies sound computation requests.
Preferably, if it is determined that the real-time remaining computing capability of terminal used by a user, which cannot meet, repair sound work
Required operational capability then corrects server transmission first to audio and repaiies sound computation requests.
According to embodiments of the present invention, a kind of server end audio modification method method based on distributed frame is provided,
As shown in fig. 6, this method includes following step S601 to step S603：
Step S601 receives the first Distributed Calculation request that terminal is sent；
Preferably, the audio is corrected the first Distributed Calculation that server receiving terminal is sent and is asked, and described first
Distributed Calculation is asked：Recording computation requests, extraction phonetic feature computation requests, speech recognition calculating are asked
Ask, the matching primitives request of recognition result and masterplate, change of voice computation requests etc., can also be the modified calculating step of other audios
Suddenly.
Step S602 asks according to first Distributed Calculation, obtains the first Distributed Calculation result；
Preferably, first result of calculation includes but not limited to：Recording result of calculation, extraction phonetic feature calculate knot
Fruit, speech recognition result of calculation, the matching primitives result of recognition result and masterplate, change of voice result of calculation etc..
The first Distributed Calculation result is sent to the terminal, so that the terminal is according to by step S603
First Distributed Calculation result carries out default sound of repairing and handles.
Preferably, the first Distributed Calculation result is returned into the terminal, to enable the terminal to according to
The progress of first Distributed Calculation result is subsequent to repair sound processing operation.
According to an embodiment of the present application, as preferred in embodiment, as shown in fig. 7, further include following steps S701 extremely
Step S703：
Receiving the first Distributed Calculation request that terminal is sent includes：
Step S701 receives the first audio frequency characteristics computation requests that terminal is sent；
Preferably, first audio-frequency information includes audio frequency characteristics, and extraction audio frequency characteristics are in audio makeover process
A wherein step.
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
Step S702 obtains the first audio frequency characteristics value according to the first audio frequency characteristics computation requests；
Preferably, according to first audio-frequency information, the first audio frequency characteristics is obtained and estimate calculation amount, that is, carry out audio frequency characteristics
Extract the required operational capability of work.
The first Distributed Calculation result is sent to the terminal, so that the terminal is distributed according to described first
Result of calculation preset repairing sound and handling：
The first audio frequency characteristics value is sent to the terminal, so that the terminal is according to described first by step S703
Audio frequency characteristics value carries out default sound of repairing and handles.
Preferably, the first audio frequency characteristics value is returned into the terminal, to enable the terminal to according to described first
The progress of audio frequency characteristics value is subsequent to repair sound processing operation.
According to an embodiment of the present application, as preferred in embodiment, as shown in figure 8, further include following steps S801 extremely
Step S804：
Receiving the first Distributed Calculation request that terminal is sent includes：
Step S801 receives the first speech recognition computation requests that terminal is sent；
Preferably, first audio-frequency information includes voice signal, and it is audio to carry out speech recognition according to voice signal
A wherein step in makeover process.
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
Step S802 obtains the first voice recognition result according to the first speech recognition computation requests；
Preferably, speech recognition is carried out to the first audio-frequency information, obtains voice recognition result, institute's speech recognition result packet
It includes but unlimited：Text information, pitch information, cadence information etc..
First voice recognition result is compared step S803 with preset standard audio template, obtains first and repaiies
Sound parameter；
Preferably, first audio-frequency information is all corresponding with preset standard audio template, for example, the first audio letter of user
Breath is song《Double-cut stick》Dry acoustic intelligence, then the preset standard audio template is the recording recorded by original singer Zhou Jielun
Canopy version《Double-cut stick》Audio-frequency information after being compared, obtains first and repaiies sound parameter, described first repaiies sound parameter as first sound
Difference of the frequency information in pitch, rhythm etc. and the preset standard audio template.
The first Distributed Calculation result is sent to the terminal, so that the terminal is distributed according to described first
Result of calculation preset repairing sound and handling：
Step S804 repaiies sound parameter by described first and is sent to the terminal, so that the terminal is repaiied according to described first
Sound parameter carries out default sound of repairing and handles.
Preferably, it repaiies sound parameter by described first and returns to the terminal, to enable the terminal to repair according to described first
The progress of sound parameter is subsequent to repair sound processing operation.
According to an embodiment of the present application, as preferred in embodiment, as shown in figure 9, further include following steps S901 extremely
Step S903：
Receiving the first Distributed Calculation request that terminal is sent includes：
Step S901 receives terminal is sent first and repaiies sound computation requests；
Preferably, first audio-frequency information is compared with preset standard audio template, obtains first and repaiies sound parameter,
And sound parameter is repaiied by described first, it obtains first and repaiies sound estimating calculation amount, repair sound parameter according to described first and carry out repairing sound and be
A wherein step in audio makeover process.
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
Step S902 repaiies sound computation requests according to described first, obtains revised first audio-frequency information；
Preferably, processing is modified to first audio-frequency information, obtains all accurate revised institute of pitch, rhythm
State the first audio-frequency information.
The first Distributed Calculation result is sent to the terminal, so that the terminal is distributed according to described first
Result of calculation preset repairing sound and handling：
Revised first audio-frequency information is sent to the terminal by step S903, so that the terminal is according to repairing
The first audio-frequency information after just is shown broadcasting.
Preferably, by pitch, rhythm, all accurately the dry sound of revised user returns to the terminal, so that the terminal root
It is shown broadcasting according to the dry sound of revised user.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
According to embodiments of the present invention, it additionally provides a kind of for implementing the above-mentioned terminal audio frequency amendment based on distributed frame
The device of method, as shown in figure 5, the device includes：Acquiring unit 10, the first audio-frequency information for obtaining the first user are excellent
Choosing, first audio-frequency information is that can obtain the song audio that user sings, the song by the microphone of mobile terminal
Audio is preferably the dry sound audio for the song that user sings；Computing unit 20, for according to first audio-frequency information, obtaining the
One estimates calculation amount, it is preferred that carrying out the step of repairing sound to first audio-frequency information includes but not limited to：Recording, extraction language
Sound feature, speech recognition, matching, the change of voice of recognition result and masterplate, specifically, since the data-interface between each module is
Through what is be clearly defined, therefore the equipment that sound can be repaiied to execution carries out computing capability assessment, and the assessment includes but unlimited
In：Recording assessment, the assessment of extraction phonetic feature, speech recognition assessment, matching assessment, the change acoustic evaluation of recognition result and masterplate,
Specifically, described first estimates calculation amount and includes but not limited to：Calculation amount is estimated in recording, extraction phonetic feature estimates calculation amount,
Calculation amount is estimated in the matching that calculation amount, recognition result and masterplate are estimated in speech recognition, calculation amount is estimated in the change of voice；Judging unit 30,
For judging that whether described first estimate calculation amount beyond the terminal itself first itself calculation power, it is preferred that user is made
Mobile terminal is had nothing in common with each other, thus the respective manufacture operational capability of terminal of every different model is also not quite similar, terminal
The power of CPU processor performance is to influence an absolutely essential factor of computing capability, and computing capability can refer in different frameworks
It enables and comparing between collecting, be exactly briefly that execution how many times per second calculate, it, can from several megahertzs of microcontrollers to huge super calculation
This index is followed, specifically, described first itself calculates the real-time remaining computing capability that power is the equipment that sound is repaiied in execution；Request hair
Unit 40 is sent, for if it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to sound
Frequency corrects server and sends the request of the first Distributed Calculation, it is preferred that first Distributed Calculation request includes but not limited to：
Recording computation requests, the matching primitives for extracting phonetic feature computation requests, speech recognition computation requests, recognition result and masterplate are asked
It asks, change of voice computation requests etc., can also be the modified calculating step of other audios；Continue to repair sound unit 50, it is described for receiving
Audio corrects the first result of calculation that server returns and continues with audio amendment, it is preferred that the audio corrects server
It is calculated for carrying out corresponding sound of repairing according to first Distributed Calculation request, and result of calculation is returned into the terminal, with
The terminal completion is set to repair sound processing.
According to embodiments of the present invention, it additionally provides a kind of for implementing the above-mentioned server end audio based on distributed frame
The device of modification method, as shown in Figure 10, which includes：Receiving unit 60, the first distribution sent for receiving terminal
Formula computation requests, it is preferred that the audio corrects the first Distributed Calculation request that server receiving terminal is sent, and described the
One Distributed Calculation is asked：Recording computation requests, extraction phonetic feature computation requests, speech recognition calculating are asked
Ask, the matching primitives request of recognition result and masterplate, change of voice computation requests etc., can also be the modified calculating step of other audios
Suddenly；Processing unit 70 obtains the first Distributed Calculation result for being asked according to first Distributed Calculation, it is preferred that
First result of calculation includes but not limited to：Recording result of calculation, extraction phonetic feature result of calculation, speech recognition calculate knot
The matching primitives result of fruit, recognition result and masterplate, change of voice result of calculation etc.；Unit 80 is returned the result, is used for described first
Distributed Calculation result is sent to the terminal, so that the terminal carries out default repair according to the first Distributed Calculation result
Sound processing, it is preferred that will the first Distributed Calculation result return terminal, to enable the terminal to according to described the
The progress of one Distributed Calculation result is subsequent to repair sound processing operation.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, either they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific
Hardware and software combines.
The foregoing is merely the preferred embodiments of the application, are not intended to limit this application, for the skill of this field
For art personnel, the application can have various modifications and variations.Within the spirit and principles of this application, any made by repair
Change, equivalent replacement, improvement etc., should be included within the protection domain of the application.
Claims (10)
1. a kind of terminal audio frequency modification method based on distributed frame, which is characterized in that the method includes：
Obtain the first audio-frequency information of the first user；
First, which is obtained, according to first audio-frequency information estimates calculation amount；
Judge that described first estimates whether calculation amount exceeds the first of the terminal the itself calculation power；
If it is determined that described first estimates first itself calculation power of the calculation amount beyond the terminal, then server hair is corrected to audio
The first Distributed Calculation is sent to ask；And
The audio is received to correct the first result of calculation of server return and continue with audio amendment.
2. terminal audio frequency modification method according to claim 1, which is characterized in that
According to first audio-frequency information, obtain first and estimate calculation amount include：
According to the audio frequency characteristics of first audio-frequency information, obtains the first audio frequency characteristics and estimate calculation amount；
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Judge that whether first audio frequency characteristics estimate calculation amount beyond the terminal itself first itself calculation power；
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment service
Device sends the request of the first Distributed Calculation：
If it is determined that first audio frequency characteristics estimate calculation amount calculates power beyond the terminal itself first itself, then to audio
It corrects server and sends the first audio frequency characteristics computation requests.
3. terminal audio frequency modification method according to claim 1, which is characterized in that
According to first audio-frequency information, obtain first and estimate calculation amount include：
According to the voice signal of first audio-frequency information, obtains the first speech recognition and estimate calculation amount；
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Judge that whether first speech recognition estimates calculation amount beyond the terminal itself first itself calculation power；
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment service
Device sends the request of the first Distributed Calculation：
If it is determined that calculation amount is estimated in first speech recognition calculates power beyond the terminal itself first itself, then to audio
It corrects server and sends the first speech recognition computation requests.
4. terminal audio frequency modification method according to claim 1, which is characterized in that
According to first audio-frequency information, obtain first and estimate calculation amount include：
First obtained after being compared according to first audio-frequency information and preset standard audio template repaiies sound parameter, and by described
First repaiies sound parameter, obtains first and repair sound estimating calculation amount；
Judge described first estimate calculation amount whether beyond the terminal itself first itself calculate power include：
Judge described first repair sound estimate calculation amount whether beyond the terminal itself first itself calculate power；
If it is determined that described first estimates calculation amount beyond the terminal itself first itself calculation power, then to audio amendment service
Device sends the request of the first Distributed Calculation：
If it is determined that described first repair sound estimate calculation amount beyond the terminal itself first itself calculate power, then to audio amendment
Server sends first and repaiies sound computation requests.
5. a kind of terminal audio frequency correcting device based on distributed frame, which is characterized in that including：
Acquiring unit, the first audio-frequency information for obtaining the first user；
Computing unit, for according to first audio-frequency information, obtaining first and estimating calculation amount；
Judging unit, for judging that whether described first estimate calculation amount beyond the terminal itself first itself calculation power；
Request transmitting unit, for if it is determined that described first estimates calculation amount beyond the calculation of the terminal itself first itself
Power then corrects server to audio and sends the request of the first Distributed Calculation；
Continue to repair sound unit, corrects the first result of calculation that server returns and continue with audio for receiving the audio and repair
Just.
6. a kind of server end audio modification method based on distributed frame, which is characterized in that repaiied for processing terminal audio
Positive request, the method includes：
Receive the first Distributed Calculation request that terminal is sent；
It is asked according to first Distributed Calculation, obtains the first Distributed Calculation result；
The first Distributed Calculation result is sent to the terminal, so that the terminal is according to first Distributed Calculation
As a result default sound of repairing is carried out to handle.
7. server end audio modification method according to claim 6, which is characterized in that
Receiving the first Distributed Calculation request that terminal is sent includes：
Receive the first audio frequency characteristics computation requests that terminal is sent；
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
According to the first audio frequency characteristics computation requests, the first audio frequency characteristics value is obtained；
The first Distributed Calculation result is sent to the terminal, so that the terminal is according to first Distributed Calculation
As a result it carries out presetting repairing sound and handling and includes：
The first audio frequency characteristics value is sent to the terminal, so that the terminal is carried out according to the first audio frequency characteristics value
It is default to repair sound processing.
8. server end audio modification method according to claim 6, which is characterized in that
Receiving the first Distributed Calculation request that terminal is sent includes：
Receive the first speech recognition computation requests that terminal is sent；
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
According to the first speech recognition computation requests, the first voice recognition result is obtained；
First voice recognition result is compared with preset standard audio template, first is obtained and repaiies sound parameter；
The first Distributed Calculation result is sent to the terminal, so that the terminal is according to first Distributed Calculation
As a result it carries out presetting repairing sound and handling and includes：
Sound parameter is repaiied by described first and is sent to the terminal, is preset so that the terminal repaiies sound parameter according to described first
Repair sound processing.
9. server end audio modification method according to claim 6, which is characterized in that
Receiving the first Distributed Calculation request that terminal is sent includes：
It receives terminal is sent first and repaiies sound computation requests；
It is asked according to first Distributed Calculation, obtaining the first Distributed Calculation result includes：
Sound computation requests are repaiied according to described first, obtain revised first audio-frequency information；
The first Distributed Calculation result is sent to the terminal, so that the terminal is according to first Distributed Calculation
As a result it carries out presetting repairing sound and handling and includes：
Revised first audio-frequency information is sent to the terminal, so that the terminal is according to revised first audio
Information is shown broadcasting.
10. a kind of server end audio correcting device based on distributed frame, which is characterized in that including：
Receiving unit, the first Distributed Calculation request sent for receiving terminal；
Processing unit obtains the first Distributed Calculation result for being asked according to first Distributed Calculation；
Return the result unit, for the first Distributed Calculation result to be sent to the terminal so that the terminal according to
The first Distributed Calculation result carries out default sound of repairing and handles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810322060.3A CN108735224B (en) | 2018-04-11 | 2018-04-11 | Audio correction method and device based on distributed structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810322060.3A CN108735224B (en) | 2018-04-11 | 2018-04-11 | Audio correction method and device based on distributed structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108735224A true CN108735224A (en) | 2018-11-02 |
| CN108735224B CN108735224B (en) | 2021-04-30 |
Family
ID=63941381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810322060.3A Active CN108735224B (en) | 2018-04-11 | 2018-04-11 | Audio correction method and device based on distributed structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108735224B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002127A (en) * | 2022-06-09 | 2022-09-02 | 方图智能(深圳)科技集团股份有限公司 | Distributed audio system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1217311C (en) * | 2002-04-22 | 2005-08-31 | 安徽中科大讯飞信息科技有限公司 | Distributed voice synthesizing system |
| CN103179167A (en) * | 2011-12-26 | 2013-06-26 | 深圳光启高等理工研究院 | Method and system for cloud computing and load balancing server |
| CN103944994A (en) * | 2014-04-25 | 2014-07-23 | 中国联合网络通信集团有限公司 | Distributed resource obtaining method and device |
| CN104184533A (en) * | 2014-07-29 | 2014-12-03 | 上海本脉信息科技有限公司 | Digital sound console based on cloud technology |
| US9159310B2 (en) * | 2012-10-19 | 2015-10-13 | The Tc Group A/S | Musical modification effects |
| CN105825844A (en) * | 2015-07-30 | 2016-08-03 | 维沃移动通信有限公司 | Sound repairing method and device |
| CN105945943A (en) * | 2016-05-12 | 2016-09-21 | 东北大学 | Cloud robot distributed control system and method based on dynamic Agent |
| CN106024007A (en) * | 2016-06-21 | 2016-10-12 | 维沃移动通信有限公司 | Sound processing method and mobile terminal |
| CN107070987A (en) * | 2017-03-01 | 2017-08-18 | 网宿科技股份有限公司 | Data capture method and system for distributed objects storage system |
| CN107230483A (en) * | 2017-07-28 | 2017-10-03 | Tcl移动通信科技（宁波）有限公司 | Speech volume processing method, storage medium and mobile terminal based on mobile terminal |
-
2018
- 2018-04-11 CN CN201810322060.3A patent/CN108735224B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1217311C (en) * | 2002-04-22 | 2005-08-31 | 安徽中科大讯飞信息科技有限公司 | Distributed voice synthesizing system |
| CN103179167A (en) * | 2011-12-26 | 2013-06-26 | 深圳光启高等理工研究院 | Method and system for cloud computing and load balancing server |
| US9159310B2 (en) * | 2012-10-19 | 2015-10-13 | The Tc Group A/S | Musical modification effects |
| CN103944994A (en) * | 2014-04-25 | 2014-07-23 | 中国联合网络通信集团有限公司 | Distributed resource obtaining method and device |
| CN104184533A (en) * | 2014-07-29 | 2014-12-03 | 上海本脉信息科技有限公司 | Digital sound console based on cloud technology |
| CN105825844A (en) * | 2015-07-30 | 2016-08-03 | 维沃移动通信有限公司 | Sound repairing method and device |
| CN105945943A (en) * | 2016-05-12 | 2016-09-21 | 东北大学 | Cloud robot distributed control system and method based on dynamic Agent |
| CN106024007A (en) * | 2016-06-21 | 2016-10-12 | 维沃移动通信有限公司 | Sound processing method and mobile terminal |
| CN107070987A (en) * | 2017-03-01 | 2017-08-18 | 网宿科技股份有限公司 | Data capture method and system for distributed objects storage system |
| CN107230483A (en) * | 2017-07-28 | 2017-10-03 | Tcl移动通信科技（宁波）有限公司 | Speech volume processing method, storage medium and mobile terminal based on mobile terminal |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002127A (en) * | 2022-06-09 | 2022-09-02 | 方图智能(深圳)科技集团股份有限公司 | Distributed audio system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108735224B (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110795528B (en) | Data query method and device, electronic equipment and storage medium | |
| CN102768659B (en) | Method and system for identifying repeated account | |
| US20170164049A1 (en) | Recommending method and device thereof | |
| CN107666638B (en) | A kind of method and terminal device for estimating tape-delayed | |
| WO2021115176A1 (en) | Speech recognition method and related device | |
| CN107146631B (en) | Music identification method, note identification model establishment method, device and electronic equipment | |
| CN110209809B (en) | Text clustering method and device, storage medium and electronic device | |
| CN109460461A (en) | Text matching technique and system based on text similarity model | |
| CN101454826A (en) | Speech recognition word dictionary/language model making system, method, and program, and speech recognition system | |
| CN110335596A (en) | Products Show method, apparatus, equipment and storage medium based on speech recognition | |
| CN103325371A (en) | Voice recognition system and method based on cloud | |
| CN108847222A (en) | Speech recognition modeling generation method, device, storage medium and electronic equipment | |
| CN112994980B (en) | Time delay test method, device, electronic equipment and storage medium | |
| CN108922520B (en) | Voice recognition method, voice recognition device, storage medium and electronic equipment | |
| CN109003607B (en) | Voice recognition method, voice recognition device, storage medium and electronic equipment | |
| CN104750667B (en) | A kind of processing method of picture material, mobile terminal and storage medium | |
| CN109376362A (en) | A kind of the determination method and relevant device of corrected text | |
| CN111858865B (en) | Semantic recognition method, semantic recognition device, electronic equipment and computer readable storage medium | |
| CN114242047B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN108735224A (en) | Audio modification method based on distributed frame and device | |
| CN113555007B (en) | Voice splicing point detection method and storage medium | |
| CN110708619B (en) | Word vector training method and device for intelligent equipment | |
| CN112541069A (en) | Text matching method, system, terminal and storage medium combined with keywords | |
| CN108206020A (en) | A kind of audio recognition method, device and terminal device | |
| CN117332068A (en) | Man-machine interaction method and device, electronic equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |