CN108735224B - Audio correction method and device based on distributed structure - Google Patents
Audio correction method and device based on distributed structure Download PDFInfo
- Publication number
- CN108735224B CN108735224B CN201810322060.3A CN201810322060A CN108735224B CN 108735224 B CN108735224 B CN 108735224B CN 201810322060 A CN201810322060 A CN 201810322060A CN 108735224 B CN108735224 B CN 108735224B
- Authority
- CN
- China
- Prior art keywords
- calculation
- terminal
- audio
- request
- 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.)
- Active
Links
- 238000012937 correction Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000012986 modification Methods 0.000 claims description 87
- 230000004048 modification Effects 0.000 claims description 87
- 238000002715 modification method Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 10
- 238000000605 extraction Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 9
- 230000033764 rhythmic process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Images
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
The application discloses a terminal audio correction method and device based on a distributed structure. The method comprises the following steps: acquiring first audio information of a first user; obtaining a first estimated calculated quantity according to the first audio information; judging whether the first estimated calculation amount exceeds a first self calculation force of the terminal; if the first estimated calculation amount exceeds the first self calculation force of the terminal, sending a first distributed calculation request to an audio correction server; receiving a first calculation result returned by the audio correction server and continuously processing audio correction; by adopting a mode of judging whether the estimated calculation amount exceeds the self calculation power of the terminal and sending a distributed calculation request to the audio correction server, the purposes of receiving the calculation result returned by the audio correction server and continuously processing the audio correction are achieved, so that the technical effect of reasonably distributing the calculation amount to the server side is realized, and the problem of low calculation efficiency of related sound correction is solved.
Description
Technical Field
The application relates to the field of sound correction, in particular to an audio correction method and device based on a distributed structure.
Background
With the rapid development of communication and information technologies, music functions have become a necessary application in terminals such as computers or mobile phones, and singing on mobile phones is becoming more and more popular, but because of the different perception abilities of different people to music and melody, and the conditions of running or rhythm not following up occur, the mood of singing is seriously affected, and therefore, the sound modifying technology is generated.
All the calculation related to the sound modification in the related sound modification technology is processed at a client (a mobile phone); when implementing the sound modifying method, the inventor finds that the related sound modifying technology has at least the following problems: firstly, a client needs to process a large amount of calculation, and has high power consumption, power consumption and poor real-time performance; secondly, the mobile phone cannot adapt to all models, and cannot use one-key tone correction for a mobile phone with poor configuration; in view of the above problems in the related art, the inventors provide a solution.
Disclosure of Invention
The application mainly aims to provide an audio correction method and device based on a distributed structure so as to solve the problem of low sound correction effect rate caused by the fact that related sound correction calculation is placed on a terminal.
In order to achieve the above object, according to an aspect of the present application, there is provided a terminal audio modification method based on a distributed structure.
The terminal audio correction method based on the distributed structure comprises the following steps: acquiring first audio information of a first user; obtaining a first estimated calculated quantity according to the first audio information; judging whether the first estimated calculation amount exceeds a first self calculation force of the terminal; if the first estimated calculation amount exceeds the first self calculation force of the terminal, sending a first distributed calculation request to an audio correction server; and receiving a first calculation result returned by the audio correction server and continuously processing audio correction.
Further, obtaining a first pre-estimated calculated amount according to the first audio information includes: obtaining a first audio characteristic pre-estimation calculated quantity according to the audio characteristic of the first audio information; judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps: judging whether the first audio characteristic pre-estimated calculation amount exceeds a first self calculation force of the terminal; if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps: and if the first audio characteristic pre-estimated calculation amount exceeds the first self calculation force of the terminal, sending a first audio characteristic calculation request to an audio correction server.
Further, obtaining a first pre-estimated calculated amount according to the first audio information includes: obtaining a first speech recognition pre-estimation calculated quantity according to the speech signal of the first audio information; judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps: judging whether the first speech recognition estimated calculation amount exceeds a first self calculation power of the terminal; if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps: and if the first speech recognition estimated calculation amount exceeds the first self calculation force of the terminal, sending a first speech recognition calculation request to an audio correction server.
Further, obtaining a first pre-estimated calculated amount according to the first audio information includes: obtaining a first sound modifying parameter after the first audio information is compared with a preset standard audio template, and obtaining a first sound modifying estimated calculated amount through the first sound modifying parameter; judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps: judging whether the first sound modification estimated calculation amount exceeds a first self calculation force of the terminal; if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps: and if the first sound modification estimated calculation amount exceeds the first self calculation force of the terminal, sending a first sound modification calculation request to an audio modification server.
In order to achieve the above object, according to another aspect of the present application, there is provided a terminal audio correction apparatus based on a distributed structure.
The terminal audio correction device based on the distributed structure comprises: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first audio information of a first user; the calculation unit is used for obtaining a first pre-estimated calculated amount according to the first audio information; the judging unit is used for judging whether the first estimated calculation amount exceeds the first self calculation power of the terminal; a request sending unit, configured to send a first distributed computation request to an audio correction server if it is determined that the first estimated computation amount exceeds a first self computation power of the terminal itself; and the continuous sound correcting unit is used for receiving the first calculation result returned by the audio correcting server and continuously processing the audio correction.
In order to achieve the above object, according to one aspect of the present application, a server-side audio modification method based on a distributed structure is provided.
The server-side audio correction method based on the distributed structure comprises the following steps: receiving a first distributed computing request sent by a terminal; obtaining a first distributed computation result according to the first distributed computation request; and sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result.
Further, the first distributed computation request sent by the receiving terminal includes: receiving a first audio feature calculation request sent by a terminal; obtaining a first distributed computation result according to the first distributed computation request includes: calculating a request according to the first audio characteristic to obtain a first audio characteristic value; sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises: and sending the first audio characteristic value to the terminal so that the terminal performs preset sound modification processing according to the first audio characteristic value.
Further, the first distributed computation request sent by the receiving terminal includes: receiving a first voice recognition calculation request sent by a terminal; obtaining a first distributed computation result according to the first distributed computation request includes: obtaining a first voice recognition result according to the first voice recognition calculation request; comparing the first voice recognition result with a preset standard audio template to obtain a first voice modification parameter; sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises: and sending the first sound modification parameter to the terminal so that the terminal performs preset sound modification processing according to the first sound modification parameter.
Further, the first distributed computation request sent by the receiving terminal includes: receiving a first sound modification calculation request sent by a terminal; obtaining a first distributed computation result according to the first distributed computation request includes: obtaining modified first audio information according to the first sound modification calculation request; sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises: and sending the modified first audio information to the terminal so that the terminal can display and play the modified first audio information.
In order to achieve the above object, according to another aspect of the present application, a server-side audio modification apparatus based on a distributed structure is provided.
The server-side audio correction device based on the distributed structure comprises: the receiving unit is used for receiving a first distributed computing request sent by a terminal; the processing unit is used for obtaining a first distributed calculation result according to the first distributed calculation request; and the result returning unit is used for sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result.
In the embodiment of the application, by adopting a mode of judging whether the estimated calculation amount exceeds the self calculation power of the terminal and sending a distributed calculation request to the audio correction server, the purposes of receiving the calculation result returned by the audio correction server and continuously processing audio correction are achieved, so that the technical effect of reasonably distributing the calculation amount to the server side is realized, and the problem of low sound correction effect rate caused by the fact that related sound correction calculation is placed on the terminal is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
fig. 1 is a schematic diagram of a terminal audio modification method according to a first embodiment of the invention;
fig. 2 is a schematic diagram of a terminal audio modification method according to a second embodiment of the invention;
fig. 3 is a schematic diagram of a terminal audio modification method according to a third embodiment of the invention;
fig. 4 is a schematic diagram of a terminal audio modification method according to a fourth embodiment of the invention;
fig. 5 is a schematic diagram of a terminal audio modification apparatus according to a first embodiment of the present invention;
fig. 6 is a schematic diagram of a server-side audio modification method according to a fifth embodiment of the invention;
fig. 7 is a schematic diagram of a server-side audio modification method according to a sixth embodiment of the invention;
fig. 8 is a schematic diagram of a server-side audio modification method according to a seventh embodiment of the invention;
fig. 9 is a schematic diagram of a server-side audio modification method according to an eighth embodiment of the invention; and
fig. 10 is a schematic diagram of a server-side audio correction apparatus according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meanings of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific situations.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the method includes steps S101 to S105 as follows:
step S101, acquiring first audio information of a first user;
preferably, the first audio information is a song audio that the user can sing through a microphone of the mobile terminal, and the song audio is preferably an audio of a song that the user sing.
Specifically, the mobile terminal may be an electronic device with a recording function, such as a mobile phone and a tablet computer.
Step S102, obtaining a first pre-estimated calculated amount according to the first audio information;
preferably, the step of modifying the first audio information includes, but is not limited to: recording, extracting voice features, voice recognition, matching of a recognition result and a template, and changing voice, in particular, since data interfaces between modules are clearly defined, a computing capability evaluation can be performed on a device for performing voice modification, wherein the evaluation includes but is not limited to: recording evaluation, voice feature extraction evaluation, voice recognition evaluation, matching evaluation of a recognition result and a template, and sound change evaluation, wherein specifically, the first estimated calculation amount includes but is not limited to: recording estimation calculated quantity, extracting voice feature estimation calculated quantity, voice recognition estimation calculated quantity, matching estimation calculated quantity of recognition result and template and variable sound estimation calculated quantity.
Step S103, judging whether the first estimated calculated amount exceeds a first self calculated amount of the terminal;
preferably, the mobile terminals used by the users are different, so that the respective factory computing capacities of the terminals of different models are different, the performance of a CPU processor of the terminal is an absolutely important factor affecting the computing capacity, the computing capacity can be compared among different architecture instruction sets, that is, how many times of computation are performed per second, from a single chip microcomputer of several megahertz to huge super computation, the index can be followed, and specifically, the first self computing capacity is the real-time residual computing capacity of the device for performing sound modification.
Step S104, if the first estimated calculated amount is judged to exceed the first self calculation power of the terminal, a first distributed calculation request is sent to an audio correction server;
preferably, the first distributed computing request includes, but is not limited to: the method comprises the following steps of recording calculation request, voice feature extraction calculation request, voice recognition calculation request, matching calculation request of recognition result and template, voice change calculation request and the like, and can also be used for other audio correction calculation steps.
And step S105, receiving a first calculation result returned by the audio correction server and continuously processing audio correction.
Preferably, the audio correction server is configured to perform corresponding sound correction calculation according to the first distributed calculation request, and return a calculation result to the terminal, so that the terminal completes sound correction processing.
Specifically, the first calculation result includes, but is not limited to: recording calculation results, extracting voice feature calculation results, voice recognition calculation results, matching calculation results of recognition results and templates, sound change calculation results and the like.
From the above description, it can be seen that the present invention achieves the following technical effects:
in the embodiment of the application, by adopting a mode of judging whether the estimated calculation amount exceeds the self calculation power of the terminal and sending a distributed calculation request to the audio correction server, the purposes of receiving the calculation result returned by the audio correction server and continuously processing audio correction are achieved, so that the technical effect of reasonably distributing the calculation amount to the server side is realized, and the problem of low sound correction effect rate caused by the fact that related sound correction calculation is placed on the terminal is solved.
According to the embodiment of the present application, as a preferred embodiment, as shown in fig. 2, the following steps S201 to S203 are further included:
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
step S201, obtaining a first audio characteristic pre-estimated calculated quantity according to the audio characteristic of the first audio information;
preferably, the first audio information includes audio features, the audio feature is extracted as one step in an audio correction process, and a first audio feature pre-estimation calculation amount, that is, the calculation capacity required for the audio feature extraction work, is obtained according to the first audio information.
Judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
step S202, judging whether the first audio characteristic estimated calculation amount exceeds a first self calculation force of the terminal;
preferably, it is determined whether the real-time remaining computing power of the terminal used by the user satisfies the computing power required for performing the audio feature extraction.
If the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
step S203, if the first audio characteristic pre-estimated calculation amount is judged to exceed the first self calculation force of the terminal, a first audio characteristic calculation request is sent to an audio correction server.
Preferably, if it is determined that the real-time remaining computing power of the terminal used by the user cannot satisfy the computing power required for performing the audio feature extraction work, the first audio feature computing request is sent to the audio modification server.
According to the embodiment of the present application, as a preferable example of the embodiment, as shown in fig. 3, the method further includes the following steps S301 to S303:
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
step S301, obtaining a first speech recognition pre-estimation calculated quantity according to the speech signal of the first audio information;
preferably, the first audio information includes a speech signal, speech recognition is performed as one of the steps in the audio correction process, and according to the first audio information, an estimated calculation amount of the first speech signal, that is, an arithmetic capability required for the speech recognition work, is obtained.
Judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
step S302, judging whether the first speech recognition estimated calculation amount exceeds the first self calculation force of the terminal;
preferably, it is determined whether the real-time remaining computing power of the terminal used by the user satisfies the computing power required for performing the voice recognition work.
If the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
step S303, if the first speech recognition estimated calculation amount is judged to exceed the first self calculation power of the terminal, a first speech recognition calculation request is sent to an audio correction server.
Preferably, if it is determined that the real-time remaining computing power of the terminal used by the user cannot satisfy the computing power required for performing the voice recognition work, the first voice recognition computing request is sent to the audio correction server.
According to the embodiment of the present application, as a preferable embodiment, as shown in fig. 4, the following steps S401 to S403 are further included:
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
step S401, obtaining a first sound modifying estimated calculated quantity according to a first sound modifying parameter obtained after the first audio information is compared with a preset standard audio template and the first sound modifying parameter;
preferably, the first audio information is compared with a preset standard audio template to obtain a first sound modification parameter, a first sound modification estimated calculated amount is obtained through the first sound modification parameter, and sound modification is performed according to the first sound modification parameter to form one step in the audio modification process.
Specifically, the first modifying parameter is a difference value between the first audio information and the preset standard audio template in terms of pitch, rhythm and the like.
Judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
step S402, judging whether the first sound modification estimated calculation amount exceeds the first self calculation force of the terminal;
preferably, it is determined whether the real-time remaining computing power of the terminal used by the user satisfies the computing power required for the sound correction work.
If the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
step S403, if it is determined that the first sound modification estimated calculated amount exceeds the first self calculated amount of the terminal itself, sending a first sound modification calculation request to an audio modification server.
Preferably, if it is determined that the real-time remaining computing power of the terminal used by the user cannot satisfy the computing power required for the sound correction work, a first sound correction computing request is sent to the audio correction server.
According to an embodiment of the present invention, a server-side audio correction method based on a distributed structure is provided, as shown in fig. 6, the method includes the following steps S601 to S603:
step S601, receiving a first distributed computation request sent by a terminal;
preferably, the audio correction server receives a first distributed computation request sent by a terminal, where the first distributed computation request includes but is not limited to: the method comprises the following steps of recording calculation request, voice feature extraction calculation request, voice recognition calculation request, matching calculation request of recognition result and template, voice change calculation request and the like, and can also be used for other audio correction calculation steps.
Step S602, obtaining a first distributed computation result according to the first distributed computation request;
preferably, the first calculation result includes, but is not limited to: recording calculation results, extracting voice feature calculation results, voice recognition calculation results, matching calculation results of recognition results and templates, sound change calculation results and the like.
Step S603, sending the first distributed computation result to the terminal, so that the terminal performs preset sound modification processing according to the first distributed computation result.
Preferably, the first distributed computation result is returned to the terminal, so that the terminal can perform subsequent sound modification processing operations according to the first distributed computation result.
According to the embodiment of the present application, as a preferable example in the embodiment, as shown in fig. 7, the method further includes the following steps S701 to S703:
the first distributed computation request sent by the receiving terminal comprises:
step S701, receiving a first audio feature calculation request sent by a terminal;
preferably, the first audio information includes audio features, and the audio features are extracted as one step in the audio correction process.
Obtaining a first distributed computation result according to the first distributed computation request includes:
step S702, calculating a request according to the first audio characteristic to obtain a first audio characteristic value;
preferably, according to the first audio information, a first audio feature pre-estimation calculation amount is obtained, that is, the calculation capability required for the audio feature extraction work is performed.
Sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
step S703 of sending the first audio characteristic value to the terminal, so that the terminal performs preset sound modification processing according to the first audio characteristic value.
Preferably, the first audio characteristic value is returned to the terminal, so that the terminal can perform subsequent sound modification processing operation according to the first audio characteristic value.
According to the embodiment of the present application, as a preferred embodiment, as shown in fig. 8, the method further includes the following steps S801 to S804:
the first distributed computation request sent by the receiving terminal comprises:
step S801, receiving a first voice recognition calculation request sent by a terminal;
preferably, the first audio information includes a voice signal, and the voice recognition is performed according to the voice signal as one of the audio correction processes.
Obtaining a first distributed computation result according to the first distributed computation request includes:
step S802, obtaining a first voice recognition result according to the first voice recognition calculation request;
preferably, the first audio information is subjected to speech recognition to obtain a speech recognition result, where the speech recognition result includes, but is not limited to: text information, pitch information, rhythm information, etc.
Step S803, comparing the first voice recognition result with a preset standard audio template to obtain a first voice modification parameter;
preferably, the first audio information corresponds to a preset standard audio template, for example, the first audio information of the user is dry sound information of a song "nunchaku", and the preset standard audio template is audio information of a recording studio version "nunchaku" recorded by an original singer, which is zhou jieren, and after comparison, a first sound modification parameter is obtained, where the first sound modification parameter is a difference value between the first audio information and the preset standard audio template in terms of pitch, rhythm, and the like.
Sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
step S804, the first sound modification parameter is sent to the terminal, so that the terminal performs preset sound modification processing according to the first sound modification parameter.
Preferably, the first sound modification parameter is returned to the terminal, so that the terminal can perform subsequent sound modification processing operation according to the first sound modification parameter.
According to the embodiment of the present application, as a preferred embodiment, as shown in fig. 9, the method further includes the following steps S901 to S903:
the first distributed computation request sent by the receiving terminal comprises:
step S901, receiving a first sound modification calculation request sent by a terminal;
preferably, the first audio information is compared with a preset standard audio template to obtain a first sound modification parameter, a first sound modification estimated calculated amount is obtained through the first sound modification parameter, and sound modification is performed according to the first sound modification parameter to form one step in the audio modification process.
Obtaining a first distributed computation result according to the first distributed computation request includes:
step S902, obtaining modified first audio information according to the first sound modification calculation request;
preferably, the first audio information is modified to obtain the modified first audio information with accurate pitch and rhythm.
Sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
step S903, sending the corrected first audio information to the terminal, so that the terminal can display and play the corrected first audio information.
Preferably, the corrected user voice with accurate pitch and rhythm is returned to the terminal, so that the terminal displays and plays the user voice according to the corrected user voice.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the terminal audio modification method based on the distributed structure, as shown in fig. 5, the apparatus includes: the acquiring unit 10 is configured to acquire first audio information of a first user, preferably, the first audio information is a song audio that can be acquired by a microphone of the mobile terminal, and the song audio is preferably an audio of a song that is sung by the user; the calculating unit 20 is configured to obtain a first estimated calculated amount according to the first audio information, and preferably, the step of performing sound modification on the first audio information includes but is not limited to: recording, extracting voice features, voice recognition, matching of a recognition result and a template, and changing voice, in particular, since data interfaces between modules are clearly defined, a computing capability evaluation can be performed on a device for performing voice modification, wherein the evaluation includes but is not limited to: recording evaluation, voice feature extraction evaluation, voice recognition evaluation, matching evaluation of a recognition result and a template, and sound change evaluation, wherein specifically, the first estimated calculation amount includes but is not limited to: recording estimation calculated quantity, extracting voice feature estimation calculated quantity, voice recognition estimation calculated quantity, matching estimation calculated quantity of a recognition result and a template, and variable sound estimation calculated quantity; a determining unit 30, configured to determine whether the first estimated computation amount exceeds a first self-computation amount of the terminal itself, preferably, mobile terminals used by users are different, so that respective factory computation capacities of terminals of different models are also different, the strength of the CPU processor performance of the terminal is an absolutely important factor affecting the computation capacity, the computation capacity can be compared between different architecture instruction sets, that is, how many times of computation are performed per second, and the index can be followed from a several mhz single chip to a huge super-computation, specifically, the first self-computation amount is a real-time remaining computation capacity of a device that performs sound modification; a request sending unit 40, configured to send a first distributed computation request to an audio correction server if it is determined that the first pre-estimated computation amount exceeds a first self-computation power of the terminal itself, where preferably, the first distributed computation request includes but is not limited to: recording calculation request, extraction voice feature calculation request, voice recognition calculation request, matching calculation request of recognition result and template, voice change calculation request, etc., or other audio correction calculation steps; and a continuous sound modification unit 50, configured to receive the first calculation result returned by the audio modification server and continuously process audio modification, preferably, the audio modification server is configured to perform corresponding sound modification calculation according to the first distributed calculation request, and return the calculation result to the terminal, so that the terminal completes sound modification processing.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the server-side audio modification method based on the distributed structure, as shown in fig. 10, the apparatus includes: a receiving unit 60, configured to receive a first distributed computation request sent by a terminal, and preferably, the audio correction server receives the first distributed computation request sent by the terminal, where the first distributed computation request includes but is not limited to: recording calculation request, extraction voice feature calculation request, voice recognition calculation request, matching calculation request of recognition result and template, voice change calculation request, etc., or other audio correction calculation steps; the processing unit 70 is configured to obtain a first distributed computation result according to the first distributed computation request, and preferably, the first computation result includes, but is not limited to: recording calculation results, extracting voice feature calculation results, voice recognition calculation results, matching calculation results of recognition results and templates, sound change calculation results and the like; a result returning unit 80, configured to send the first distributed computation result to the terminal, so that the terminal performs preset sound modification processing according to the first distributed computation result, and preferably, return the first distributed computation result to the terminal, so that the terminal can perform subsequent sound modification processing operations according to the first distributed computation result.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A terminal audio correction method based on a distributed structure is characterized by comprising the following steps:
acquiring first audio information of a first user;
obtaining a first pre-estimated calculated amount according to the first audio information, wherein the first pre-estimated calculated amount comprises:
recording estimation calculated quantity, extracting voice feature estimation calculated quantity, voice recognition estimation calculated quantity and variable voice estimation calculated quantity;
judging whether the first estimated calculation amount exceeds a first self calculation force of the terminal;
if the first estimated calculation amount exceeds the first self calculation force of the terminal, sending a first distributed calculation request to an audio correction server, wherein the first distributed calculation request consists of a recording calculation request, a calculation request for extracting voice features, a voice recognition calculation request, a matching calculation request of a recognition result and a template, and a variable sound calculation request; and
receiving a first calculation result returned by the audio correction server and continuously processing audio correction;
the method further comprises the following steps:
and determining the first self computing power of the terminal according to the model of the client used by the user, the factory computing power, the performance of a CPU (Central processing Unit) and the computing power of instruction sets with different architectures.
2. The terminal audio correction method according to claim 1,
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
obtaining a first audio characteristic pre-estimation calculated quantity according to the audio characteristic of the first audio information;
judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
judging whether the first audio characteristic pre-estimated calculation amount exceeds a first self calculation force of the terminal;
if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
and if the first audio characteristic pre-estimated calculation amount exceeds the first self calculation force of the terminal, sending a first audio characteristic calculation request to an audio correction server.
3. The terminal audio correction method according to claim 1,
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
obtaining a first speech recognition pre-estimation calculated quantity according to the speech signal of the first audio information;
judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
judging whether the first speech recognition estimated calculation amount exceeds a first self calculation power of the terminal;
if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
and if the first speech recognition estimated calculation amount exceeds the first self calculation force of the terminal, sending a first speech recognition calculation request to an audio correction server.
4. The terminal audio correction method according to claim 1,
obtaining a first pre-estimated calculated quantity according to the first audio information comprises:
obtaining a first sound modifying parameter after the first audio information is compared with a preset standard audio template, and obtaining a first sound modifying estimated calculated amount through the first sound modifying parameter;
judging whether the first pre-estimated calculation amount exceeds the first self calculation power of the terminal comprises the following steps:
judging whether the first sound modification estimated calculation amount exceeds a first self calculation force of the terminal;
if the first estimated calculation amount is judged to exceed the first self calculation power of the terminal, sending a first distributed calculation request to an audio correction server comprises the following steps:
and if the first sound modification estimated calculation amount exceeds the first self calculation force of the terminal, sending a first sound modification calculation request to an audio modification server.
5. A terminal audio frequency correction device based on a distributed structure is characterized by comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first audio information of a first user;
the calculation unit is used for obtaining a first pre-estimated calculated amount according to the first audio information;
the judging unit is used for judging whether the first estimated calculation amount exceeds the first self calculation power of the terminal;
a request sending unit, configured to send a first distributed computation request to an audio correction server if it is determined that the first estimated computation amount exceeds a first self computation power of the terminal itself;
the continuous sound correcting unit is used for receiving a first calculation result returned by the audio correcting server and continuously processing audio correction;
the first distributed calculation request consists of a recording calculation request, a calculation request for extracting voice features, a voice recognition calculation request, a matching calculation request of a recognition result and a template, and a variable sound calculation request;
the first self computing power of the terminal is determined according to the model of a client used by a user, the factory computing power, the performance of a CPU (Central processing Unit) processor and the computing power of instruction sets of different architectures.
6. A server-side audio correction method based on a distributed structure is used for processing a terminal audio correction request, and the method comprises the following steps:
receiving a first distributed computing request sent by a terminal, wherein the first distributed computing request is a first estimated computing quantity obtained by the terminal according to acquired first audio information of a first user; judging whether the first estimated calculation amount exceeds a first self calculation force of the terminal; if the first estimated calculated amount exceeds the first self-calculated amount of the terminal, the first estimated calculated amount comprises: recording estimation calculated quantity, extracting voice feature estimation calculated quantity, voice recognition estimation calculated quantity and variable voice estimation calculated quantity;
obtaining a first distributed computation result according to the first distributed computation request;
sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result;
the first distributed calculation request consists of a recording calculation request, a calculation request for extracting voice features, a voice recognition calculation request, a matching calculation request of a recognition result and a template, and a variable sound calculation request;
the first self computing power of the terminal is determined according to the model of a client used by a user, the factory computing power, the performance of a CPU (Central processing Unit) processor and the computing power of instruction sets of different architectures.
7. The server-side audio modification method according to claim 6,
the first distributed computation request sent by the receiving terminal comprises:
receiving a first audio feature calculation request sent by a terminal;
obtaining a first distributed computation result according to the first distributed computation request includes:
calculating a request according to the first audio characteristic to obtain a first audio characteristic value;
sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
and sending the first audio characteristic value to the terminal so that the terminal performs preset sound modification processing according to the first audio characteristic value.
8. The server-side audio modification method according to claim 6,
the first distributed computation request sent by the receiving terminal comprises:
receiving a first voice recognition calculation request sent by a terminal;
obtaining a first distributed computation result according to the first distributed computation request includes:
obtaining a first voice recognition result according to the first voice recognition calculation request;
comparing the first voice recognition result with a preset standard audio template to obtain a first voice modification parameter;
sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
and sending the first sound modification parameter to the terminal so that the terminal performs preset sound modification processing according to the first sound modification parameter.
9. The server-side audio modification method according to claim 6,
the first distributed computation request sent by the receiving terminal comprises:
receiving a first sound modification calculation request sent by a terminal;
obtaining a first distributed computation result according to the first distributed computation request includes:
obtaining modified first audio information according to the first sound modification calculation request;
sending the first distributed calculation result to the terminal so that the terminal performs preset sound modification processing according to the first distributed calculation result comprises:
and sending the modified first audio information to the terminal so that the terminal can display and play the modified first audio information.
10. A server-side audio modification apparatus based on a distributed architecture, comprising:
the receiving unit is used for receiving a first distributed computing request sent by a terminal;
the processing unit is used for obtaining a first distributed calculation result according to the first distributed calculation request;
a result returning unit, configured to send the first distributed computation result to the terminal, so that the terminal performs preset sound modification processing according to the first distributed computation result;
the first distributed calculation request consists of a recording calculation request, a calculation request for extracting voice features, a voice recognition calculation request, a matching calculation request of a recognition result and a template, and a variable sound calculation request;
the first self computing power of the terminal is determined according to the model of a client used by a user, the factory computing power, the performance of a CPU (Central processing Unit) processor and the computing power of instruction sets of different architectures.
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 CN108735224A (en) | 2018-11-02 |
| CN108735224B true 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) |
Families Citing this family (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 (6)
| 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 |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN106024007B (en) * | 2016-06-21 | 2019-10-15 | 维沃移动通信有限公司 | A kind of sound processing method and mobile terminal |
| CN107070987B (en) * | 2017-03-01 | 2020-02-14 | 网宿科技股份有限公司 | Data acquisition method and system for distributed object storage system |
| CN107230483B (en) * | 2017-07-28 | 2020-08-11 | Tcl移动通信科技（宁波）有限公司 | Voice volume processing method based on mobile terminal, storage medium and mobile terminal |
-
2018
- 2018-04-11 CN CN201810322060.3A patent/CN108735224B/en active Active
Patent Citations (6)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108735224A (en) | 2018-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108255653B (en) | Product testing method and terminal thereof | |
| CN104133851A (en) | Audio similarity detecting method, audio similarity detecting device and electronic equipment | |
| CN109903773B (en) | Audio processing method, device and storage medium | |
| CN109147818A (en) | Acoustic feature extracting method, device, storage medium and terminal device | |
| CN110992963B (en) | Network communication method, device, computer equipment and storage medium | |
| CN109388367A (en) | Audio method of adjustment, device, electronic equipment and storage medium | |
| CN109271128A (en) | Audio setting method, device, electronic equipment and storage medium | |
| CN109379678A (en) | Non-linear compensation method, device, storage medium and terminal device | |
| CN111787461B (en) | Intelligent sound equipment, control method and device thereof and computer readable storage medium | |
| CN114073854A (en) | Game method and system based on multimedia file | |
| CN113242361A (en) | Video processing method and device and computer readable storage medium | |
| CN105243066A (en) | Audio recommendation apparatus and audio play method | |
| CN108735224B (en) | Audio correction method and device based on distributed structure | |
| CN108810075B (en) | Audio correction system realized based on server side | |
| CN109961804B (en) | Intelligent equipment satisfaction evaluation method and device and storage medium | |
| CN109089190A (en) | Impedance curve determines method, apparatus, storage medium and terminal device | |
| CN112435641A (en) | Audio processing method and device, computer equipment and storage medium | |
| CN111429949B (en) | Pitch line generation method, device, equipment and storage medium | |
| CN112948763A (en) | Method and device for predicting quantity of component, electronic equipment and storage medium | |
| CN114422814B (en) | Method and device for processing direct broadcast audio and video, server and readable storage medium | |
| CN111739493B (en) | Audio processing method, device and storage medium | |
| CN114333905A (en) | Earphone wearing detection method and device, electronic equipment and storage medium | |
| CN115116472A (en) | Audio recognition method, device, equipment and storage medium | |
| WO2019109786A1 (en) | User gender recognition method and device | |
| CN112843729A (en) | Operation parameter determination method and device, computer 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 |