CN110349559A

CN110349559A - Carry out audio synthetic method, device, system, equipment and storage medium

Info

Publication number: CN110349559A
Application number: CN201910629749.5A
Authority: CN
Inventors: 邓一雷; 苏裕贤; 江倩雯; 黄湘宇; 阮陈贵; 刘梓谦; 陈志明
Original assignee: Guangzhou Kugou Computer Technology Co Ltd
Current assignee: Guangzhou Kugou Computer Technology Co Ltd
Priority date: 2019-07-12
Filing date: 2019-07-12
Publication date: 2019-10-18

Abstract

This application discloses a kind of progress audio synthetic method, device, system, equipment and storage mediums, belong to internet area.The described method includes: singing request to the connecing for the first audio that server sends corresponding target song；Receive first audio that the server is sent, wherein first audio includes the first sound audio of the first segment of the target song；Record the second voice audio of the second segment of the target song；Based on the second voice audio and first audio, generate the second audio, wherein, second audio includes the second voice audio of the first sound audio of the first segment of the target song and the second segment of the target song, first segment the end time in the target song with second segment in the target song at the beginning of it is identical；Second audio is sent to the server.Using the application, the mode of audio recording is enriched, improves the flexibility of audio recording.

Description

Carry out audio synthetic method, device, system, equipment and storage medium

Technical field

This application involves internet area, in particular to a kind of progress audio synthetic method, device, system, equipment and Storage medium.

Background technique

With the prosperity of mobile network, the selectable entertainment way of people is more and more, is carried out by singing application program Singing songs have become a kind of common entertainment way of people.

Be in the technology for singing application program progress singing songs at present: user can select song in singing application program Song, the audio accompaniment of operation downloading song, then, user, which can operate, sings application program broadcasting audio accompaniment, and is drilled It sings, the voice audio that terminal acquisition user sings simultaneously is synthesized with audio accompaniment, is generated and is sung audio.

During realizing the application, the inventor finds that the existing technology has at least the following problems: above by singing Application program progress audio recording mode is more single, and flexibility is poor.

Summary of the invention

The embodiment of the present application provides a kind of progress audio synthetic method, device, system, equipment and storage medium, energy The mode to give song recitals on singing application program enough is enriched, improves the flexibility to give song recitals.The technical solution is as follows:

On the one hand, a kind of progress audio synthetic method is provided, the method is used for terminal, which comprises

The connecing for the first audio for sending corresponding target song to server sings request；

Receive first audio that the server is sent, wherein first audio includes the target song The first sound audio of first segment；

Record the second voice audio of the second segment of the target song；

Based on the second voice audio and first audio, the second audio is generated, wherein second audio includes Second voice audio of the second segment of the first sound audio and target song of the first segment of the target song, institute State the first segment in the target song end time and second segment in the target song at the beginning of It is identical；

Second audio is sent to the server.

Optionally, first audio further includes the audio accompaniment of the target song, and second audio further includes institute State the audio accompaniment of target song.

Optionally, which is characterized in that the connecing for the first audio for sending corresponding target song to server sings request Before, further includes:

Connecing art of singing to server transmission can request that；

It receives the connecing for server transmission and sings function pages, wherein described connect is sung in function pages including described first Corresponding connect of audio sings option；

It is connect described in display and sings function pages；

The connecing for the first audio for sending corresponding target song to server sings request, comprising:

When receiving that first audio is corresponding to connect the triggering command for singing option, corresponding target song is sent to server Bent connecing for the first audio sings request.

Optionally, first audio that corresponding target song is sent to server connects before singing request, further includes:

The account dynamic page request of the first account is sent to server, wherein first account is to upload described the The account of one audio；

Receive the account dynamic page for the first account that the server is sent, wherein the account of first account is dynamic It include that corresponding connect of the first audio sings option in the state page；

Show the account dynamic page of first account；

Optionally, the second voice audio of second segment for recording the target song, further includes:

When receiving starting record command, start audio recording；

When receiving end record command, or the sum of duration for recording duration and the first sound audio is equal to the mesh When marking the duration of song, terminate audio recording；

Obtain the second voice audio of the second segment of the target song recorded.

On the other hand, a kind of progress audio synthetic method is provided, the method is used for server, the method packet It includes:

Receive leading singer's notice that first terminal is sent, wherein the first sound of target song is carried in leading singer's notice Frequently, first audio includes the first sound audio of the first segment of the target song；

Store first audio；

When receive second terminal transmission correspondence first audio connect sing request when, Xiang Suoshu second terminal send First audio；

Receive the second audio of the target song that the second terminal is sent, wherein second audio includes institute The second voice audio of the first sound audio of the first segment of target song and the second segment of the target song is stated, it is described First segment the end time in the target song with second segment in the target song at the beginning of phase Together.

Optionally, first audio further includes the audio accompaniment of the target song, and second audio further includes institute State the audio accompaniment of target song, comprising:

Optionally, after the leading singer's notice for receiving first terminal transmission, further includes:

Connecing to sing corresponding connect of the first audio is added in function pages sing option.

In the account dynamic page for the first account that the first terminal currently logs in, it is corresponding to add first audio Connect and sing option.

Optionally, after second audio for receiving the target song that the second terminal is sent, further includes:

In the account dynamic page for the first account that the first terminal currently logs in, it is corresponding to add second audio Play options add second sound and in the account dynamic page for the second account that the second terminal currently logs in Frequently corresponding play options.

Optionally, if the sum of duration of the first sound audio and the second voice audio is equal to the target and sings Bent duration adds second audio then in the account dynamic page for the first account that the first terminal currently logs in Corresponding play options, and in the account dynamic page for the second account that the second terminal currently logs in add described the The corresponding play options of two audios；

If the sum of duration of the first sound audio and the second voice audio be less than the target song when It is long, then in the account dynamic page for the second account that the second terminal currently logs in, it is corresponding to add second audio It connects and sings option, alternatively, adding corresponding connect of the second audio in function pages connecing to sing and singing option.

On the other hand, a kind of device for carrying out audio synthesis is provided, described device is applied to terminal, and described device includes:

Sending module, the connecing for the first audio for being configured as sending corresponding target song to server sing request；

Receiving module is configured as receiving first audio that the server is sent, wherein first audio pack Include the first sound audio of the first segment of the target song；

Module is recorded, is configured as recording the second voice audio of the second segment of the target song；

Generation module is configured as generating the second audio based on the second voice audio and first audio, In, second audio include the first segment of the target song the first sound audio and second of the target song Second voice audio of section, end time of first segment in the target song and second segment are in the mesh It is identical at the beginning of marking in song；

Sending module is additionally configured to send second audio to the server.

Optionally, the sending module, is also configured to send to server and connects art of singing and can request that；

The receiving module, is also configured to receive that the server sends connects and sing function pages, wherein described to connect Sing in function pages includes that corresponding connect of the first audio sings option；

Described device further includes display module, is configured as: connecing described in display and sings function pages；

The sending module, is configured as: when receiving that first audio is corresponding to connect the triggering command for singing option, The connecing for the first audio for sending corresponding target song to server sings request.

Optionally, the sending module, the account dynamic page for being also configured to send the first account to server are asked It asks, wherein first account is to upload the account of first audio；

The receiving module is also configured to receive the account dynamic page for the first account that the server is sent, In, it include that corresponding connect of the first audio sings option in the account dynamic page of first account；

Described device further includes display module, is configured as: the account dynamic page of display first account；

Optionally, the recording module, is configured as:

When receiving starting record command, start audio recording, when receiving end record command, or record duration with When the sum of duration of the first sound audio is equal to the duration of the target song, terminate audio recording；

Described device further includes obtaining module, is configured as: obtaining the of the second segment of the target song of recording Two voice audios.

In another aspect, providing a kind of device for carrying out audio synthesis, described device is applied to server, comprising:

Receiving module is configured as receiving leading singer's notice that first terminal is sent, wherein carry in leading singer's notice First audio of target song, first audio include the first sound audio of the first segment of the target song；

Memory module is configured as storing first audio；

Sending module, be configured as when receive second terminal transmission correspondence first audio connect sing request when, First audio is sent to the second terminal；

Receiving module is configured as receiving the second audio of the target song that the second terminal is sent, wherein institute State the first sound audio for the first segment that the second audio includes the target song and the second segment of the target song Second voice audio, end time of first segment in the target song and second segment are sung in the target It is identical at the beginning of in song.

Optionally, described device further includes adding module, is configured as: the leading singer's notice for receiving first terminal and sending Later corresponding connect of the first audio is added in function pages sing option connecing to sing.

Optionally, the adding module is also configured to the account of the first account currently logged in the first terminal In dynamic page, adds corresponding connect of the first audio and sing option.

Optionally, the adding module is also configured to the account of the first account currently logged in the first terminal In dynamic page, the corresponding play options of second audio, and the second account currently logged in the second terminal are added Account dynamic page in, add the corresponding play options of second audio.

Optionally, the adding module, if being also configured to the first sound audio and the second voice audio The sum of duration be equal to the duration of the target song, then the account dynamic of the first account currently logged in the first terminal In the page, the corresponding play options of second audio, and the account of the second account currently logged in the second terminal are added In the dynamic page of family, the corresponding play options of second audio are added, if the first sound audio and second people The sum of duration of sound audio is less than the duration of the target song, the then account of the second account currently logged in the second terminal In the dynamic page of family, adds corresponding connect of the second audio and sing option, alternatively, adding described second in function pages connecing to sing Corresponding connect of audio sings option.

In another aspect, providing a kind of system for carrying out audio, the system comprises first terminal, second terminal and services Device, in which:

The server receives leading singer's notice that first terminal is sent, wherein carries target song in leading singer's notice The first bent audio, first audio includes the first sound audio of the first segment of the target song；Store described One audio；When receive second terminal transmission correspondence first audio connect sing request when, Xiang Suoshu second terminal send First audio；Receive the second audio of the target song that the second terminal is sent, wherein second audio pack The second voice audio of the first sound audio of the first segment of the target song and the second segment of the target song is included, First segment in the target song end time and second segment in the target song at the beginning of Between it is identical；

The second terminal, the connecing for the first audio for sending corresponding target song to server sing request；Receive the clothes First audio that business device is sent；Record the second voice audio of the second segment of the target song；Based on described second Voice audio and first audio generate the second audio；Second audio is sent to the server.

In another aspect, providing a kind of computer equipment, the computer equipment includes processor and memory, the storage At least one instruction is stored in device, described instruction is loaded by the processor and executed to realize progress audio as described above Operation performed by synthetic method.

In another aspect, providing a kind of computer readable storage medium, at least one instruction is stored in the storage medium, Described instruction is loaded as processor and is executed to realize operation performed by progress audio synthetic method as described above.

Technical solution provided by the embodiments of the present application has the benefit that

The embodiment of the present application, in singing application program in such a way that leading singer connects and sings, by the voice of different user recording Audio carries out sequential concatenation, is combined into an audio.As it can be seen that the embodiment of the present application enriches the mode of audio recording, improve The flexibility of audio recording.

Detailed description of the invention

In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other Attached drawing.

Fig. 1 is a kind of schematic diagram of implementation environment provided by the embodiments of the present application；

Fig. 2 is progress audio synthetic method flow chart provided by the embodiments of the present application；

Fig. 3 is progress audio synthetic method flow chart provided by the embodiments of the present application；

Fig. 4 is progress audio synthetic method flow chart provided by the embodiments of the present application；

Fig. 5 a is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 b is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 c is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 d is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 e is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 f is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 5 g is the interface schematic diagram of application program provided by the embodiments of the present application；

Fig. 6 a is audio duration schematic diagram provided by the embodiments of the present application；

Fig. 6 b is audio duration schematic diagram provided by the embodiments of the present application；

Fig. 7 is progress audio synthetic method flow chart provided by the embodiments of the present application；

Fig. 8 is the apparatus structure schematic diagram provided by the embodiments of the present application for carrying out audio synthesis；

Fig. 9 is the apparatus structure schematic diagram provided by the embodiments of the present application for carrying out audio synthesis；

Figure 10 is terminal structure schematic diagram provided by the embodiments of the present application；

Figure 11 is server architecture schematic diagram provided by the embodiments of the present application.

Specific embodiment

To keep the purposes, technical schemes and advantages of the application clearer, below in conjunction with attached drawing to the application embodiment party Formula is described in further detail.

Fig. 1 is a kind of schematic diagram of implementation environment provided by the embodiments of the present application.Referring to Fig. 1, audio provided by the present application Synthetic method can be realized jointly by terminal and server.Terminal can be run with the application program for singing function, such as Application program is sung, terminal can have the components such as microphone, earphone, loudspeaker, and terminal has communication function, can access mutually Networking, terminal can be mobile phone, tablet computer, intelligent wearable device, desktop computer, laptop etc..Server can be with It is the background server of above-mentioned application program, server can be established with terminal and be communicated.The server can be one individually Server is also possible to a server group, and if it is individual server, which can be responsible for the institute in following proposal There is processing, if it is server group, the different server in server group can be responsible for the different disposal in following proposal respectively, Specific processing distribution condition can be arbitrarily arranged according to actual needs by technical staff, and details are not described herein again.

The audio synthetic method provided in the embodiment of the present application, different voice audios can be carried out splicing and with song Bent audio accompaniment data are synthesized, which is properly termed as connecing art of singing energy.It is to sing application program in the embodiment of the present application Example carries out the detailed description of scheme, and other situations are similar therewith, repeat no more.It is equipped in terminal and sings application program.It sings Application program can play the audio accompaniment of song and show the lyrics of song, obtain the song that the user that terminal is recorded sings Voice audio, then the voice audio of the song of the performance of user is synthesized with the audio accompaniment of the song, generate sing Audio.

When application program is sung in user's use, an account, the account created can be registered in singing application program Other accounts can be paid close attention to, can also be of interest by other accounts, each account has the account dynamic page of oneself, wherein can Browsing account dynamic page can be accessed mutually with the performance audio etc. for showing the account, between different accounts.User passes through The performance audio for singing application program recording can be stored in terminal and play for oneself, can also share the account dynamic at oneself It is played on the page for other accounts.User can also pass through the dynamic page browsing broadcasting receipts of other accounts of the account access of oneself The performance audio for listening other accounts to record.However, being sung in singing application program using the above method, lack between user mutually Dynamic, in the form of a single, flexibility is poor.By audio synthetic method provided by the embodiments of the present application, can allow different users it Between choral song, the mode sung on the net is increased, to improve the flexibility that user sings on the net.

Fig. 2 is the flow chart of server side in a kind of audio synthetic method provided by the embodiments of the present application.Referring to fig. 2, The embodiment includes:

Step 201, leading singer's notice that first terminal is sent is received, wherein carry the of target song in leading singer's notice One audio, the first audio include the first sound audio of the first segment of target song.

Step 202, the first audio is stored.

Step 203, when receive second terminal transmission the first audio of correspondence connect sing request when, to second terminal send First audio.

Step 204, the second audio of the target song that second terminal is sent is received, wherein the second audio includes target song Second voice audio of the second segment of the first sound audio and target song of the first bent segment, the first segment are sung in target End time in song with the second segment in target song at the beginning of it is identical.

Fig. 3 is the flow chart of terminal side in a kind of audio synthetic method provided by the embodiments of the present application.It, should referring to Fig. 3 Embodiment includes:

Step 301, request is sung to the connecing for the first audio that server sends corresponding target song.

Step 302, the first audio that server is sent is received, wherein the first audio includes the first segment of target song The first sound audio.

Step 303, the second voice audio of the second segment of target song is recorded.

Step 304, it is based on the second voice audio and the first audio, generates the second audio, wherein the second audio includes target Second voice audio of the second segment of the first sound audio and target song of the first segment of song, the first segment is in target End time in song with the second segment in target song at the beginning of it is identical.

Step 305, the second audio is sent to server.

Fig. 4 is the process interacted between server and terminal in a kind of audio synthetic method provided by the embodiments of the present application Figure.Referring to fig. 4, which includes:

Step 401, server receives leading singer's notice that first terminal is sent.

Wherein, the first audio of target song is carried in leading singer's notice, first audio includes the target The first sound audio of first segment of song.Target song can be a first full songs, be also possible in full songs One snatch of song.It may include the audio accompaniment of target song in first audio, can not also include the accompaniment of target song Audio (is sung opera arias).

In an implementation, the starting of certain user's operation first terminal sings application program and logs in the first account.It sings using journey Be provided in sequence connect art of singing can label, user, which can click the label and enter, to be connect and sings function interface.As shown in Figure 5 a, it sings connecing It is provided with triggering leading singer's function in function interface and connects the option of art of singing energy, user can play oneself connecing to sing in function pages The song offerings that concern account and server recommend the song offerings of account publication that can sing by connecing art of singing, can also click and connect It sings and leads a chorus function choosing-item in function pages, triggering leading singer's function, the song offerings for issuing the performance of oneself are carried out for other users It plays and connects and sing.After user issues song offerings success, the first account is defined as accentor, issued song in this section Works are defined as leading singer's audio, i.e. the first audio.If user's use connect art of singing can connect sing other leading singer audios and issue at After function, then the first account is defined as meeting the person of singing in this section of song offerings, and song offerings, which are defined as connecing, sings audio, i.e., Second audio.

The present embodiment carries out scheme explanation in case where first terminal is led a chorus, and the user of first terminal is clicking leading singer Enter leading singer's function pages after function choosing-item, while sending leading singer's request to server, server can be logged according to user The hobby song of first account or current hit song it is random be pushed to first terminal.As shown in Figure 5 b, it sings using journey Sequence can show the corresponding lyrics while playing accompanying song audio in leading singer's function pages.It is additionally provided in the page Search column sings the mode option, replacement song choices and replacement snatch of song option, if user is not desired to sing what server was recommended Song, then can send the instruction of replacement song, such as can click the replacement song choices replacement song in leading singer's function pages Song, or the instruction of replacement snatch of song can be sent, such as click other segments of replacement snatch of song option replacement song, also The song for oneself wanting leading singer can be searched in the search column in leading singer's function pages.Finally selected song is above-mentioned mesh Song is marked, after selected target song, clicks to record option and can start recording function and records voice audio.

User can choose the mode of singing before performance, wherein singing mode is divided into accompaniment mode and mode of singing opera arias.? Under accompaniment mode, user can carry out singing songs with accompanying and looking at lyrics prompt.In performance circle for singing application program Stopping option being provided in face, as shown in Figure 5 c.In this mode, user's performance duration is fixed, can be by technical staff Setting, and user can be set and need that set duration performance is finished and could be terminated, it cannot be clicked during performance Stop option.After performance, the voice audio and audio accompaniment for singing the user that application program will acquire synthesize the first sound Frequently, that is, audio is led a chorus.At this point, the duration of audio accompaniment is the duration of target song, and voice audio is the one of target song Part, so the duration of voice audio is likely less than the duration equal to audio accompaniment, the duration of the first audio is equal to audio accompaniment Duration.Terminal can also show that performance terminates the page, be provided with re-recording options and next step option as fig 5d, in the page, User can play the leading singer's audio of oneself, click re-recording options, can record leading singer's audio again.

Under the mode of singing opera arias, user only carries out singing songs under lyrics prompt, there was only user in leading singer's audio of generation Voice audio.Stopping option being provided in the performance interface for singing application program, as shown in Figure 5 c.In this mode, it uses Family is clicked during singing songs and stops option, then sings application program and stop audio recording.Singing application program will acquire User voice audio as the first audio, i.e. leading singer's audio.At this point, voice audio duration is equal to the first audio duration.Eventually End can also show that performance terminates the page, be provided with re-recording options and next step option as fig 5d, in the page, user can broadcast The leading singer's audio of oneself is put, re-recording options is clicked, leading singer's audio can be recorded again.

After obtaining leading singer's audio, next step option is clicked, first terminal can send leading singer's notice to server, wherein leading a chorus Leading singer's audio (i.e. the first audio) is carried in notice.

Step 402, server stores the first audio.

In an implementation, server obtains leading singer's audio therein after receiving leading singer's notice of first terminal transmission, will Leading singer's audio storage corresponding with the first account.

Optionally, be provided with to connect in singing application program and sing functional label, click connect sing functional label can enter connect Function pages are sung, the information for singing the first audio for adding the first account publication in function pages, including leading singer's song are being connect Cover, leading singer's lyrics and corresponding connect sing option, play options, the functions such as thumb up, comment on, giving gifts wherein can also add. As shown in Figure 5 a, the leading singer's sound sung and have the entitled account fed of account to issue a song entitled " ham " in function pages is connect Frequently, server can sing leading singer's audio-frequency information that addition is fed on function pages feeding connecing for account in concern, in leading singer's sound The cover of leading singer's song and the lyrics of leading singer's audio are shown in the information of frequency, have different functions below the cover of leading singer's audio Option is to thumb up, give gifts, commenting on, forwarding, connecing and the function choosing-items such as sing respectively, wherein connecing, to sing option be to sing function pages connecing Middle addition corresponding connect of the first audio sings option.Click, which connects, sings option, can enter to connect accordingly and sing the page, to hello hello publication Leading singer's audio connect singing.

Optionally, server can add first in the account dynamic page for the first account that first terminal currently logs in The information of audio is provided with the song of play options and target song wherein may include the cover of target song on cover The information such as word also are added with to connect and sing option.In addition, can also show the first audio meets the person of singing in account dynamic page Number and connect the information etc. of the person of singing.As depicted in fig. 5e, the account of the small mew of the entitled mew of user has issued the entitled " fire of a song Leg " leading singer's audio, the dynamic of addition leading singer audio, has play options on cover and shows in its corresponding account dynamic page The lyrics of " ham " are shown with, have different function choosing-items in account dynamic page bottom, are to thumb up, give gifts, commenting on, turning respectively It sends out, connect and sing.Wherein connecing and singing option is to add corresponding connect of the first audio in function pages and sing option connecing to sing.Click, which connects, sings choosing , the leading singer's audio for feeding publication connect singing.

Step 403, second terminal sings request to the connecing for the first audio that server sends corresponding target song.

In an implementation, the user's operation second terminal starting of second terminal sings application program and logs in the second account.Song It sings application program and will connect and sing function pages and be shown to second terminal user, second terminal user can broadcast connecing to sing in function pages It puts oneself concern account and server recommends the song offerings of account publication, can also click and connect in the corresponding position of these works Sing button, triggering connects art of singing energy, choruses same section of song with other people.

First audio is corresponding to meet the case where singing option, Yong Hutong is added connecing to sing for server in function pages It crosses second terminal starting and sings application program, the label for connecing art of singing energy is clicked in singing application program, second can be triggered eventually It holds to server transmission and connects art of singing and can request that, server can send connect to second terminal sings function pages.Second terminal docking is sung Function pages are shown, user's browsing connects when singing function pages, may browse through each leading singer's audio for connecing and singing in function pages, In include above-mentioned first terminal upload the first audio.The user can click corresponding connect of the first audio and sing option, at this time may be used Request is sung to trigger second terminal to the connecing for the first audio that server sends corresponding target song.Meanwhile second terminal can be with Display, which connects, sings the recording page.

The first sound can be added in the account dynamic page for the first account that first terminal currently logs in for server Frequently corresponding to connect the case where singing option, user can search first account of its concern in concern account list, and click the The icon of one account can trigger the account dynamic page request that second terminal sends the first account to server, server meeting The account dynamic page that the first account is sent to second terminal, each neck including the publication of the first account in account dynamic page Sing audio.Second terminal shows that user may browse through to the publication of the first account to the account dynamic page of the first account Each leading singer's audio clicks corresponding connect of the first audio and sings option, can trigger second terminal at this time including the first audio The connecing for the first audio for sending corresponding target song to server sings request.Meanwhile second terminal can show to connect and sing recording page Face.

Sing that have a head to sing audio in function pages be " flower field wrong " led a chorus by account A, second terminal user for example, connecing This corresponding connects of leading singer's audio can be clicked to sing function choosing-item and connect singing.After second terminal detects that connecing art of singing can trigger, It can be sent to server and request is sung by the connecing for " flower field being wrong " that account A is led a chorus.Second terminal user can also be directly in concern account The first account of its concern is searched in the list of family, and clicks the icon of the first account, and the account dynamic of A account is sent to server The request of the page after server receives above-mentioned request, can send second terminal for the account dynamic page of A account.Second Terminal user can browse to leading singer's audio of " flower field wrong " in the account dynamic page of A account, and second terminal user can be with " flower field is wrong " corresponding connect for clicking account A leading singer sings option, and second terminal can send to server and lead a chorus " flower by account A Field is wrong " connect and sing request.

Step 404, when server receive second terminal transmission correspondence first audio connect sing request when, service Device sends first audio to second terminal.

In an implementation, second terminal user connect performance mode when singing and connects the performance mode for the leading singer's audio sung It is identical.For example, accentor has selected accompaniment mode in leading singer " flower field is wrong ", then meets the person of singing and receive leading singer's sound that server is sent The voice audio of audio accompaniment and accentor in frequency including target song, then second terminal user can sing with accompaniment.Such as Fruit accentor has selected the mode of singing opera arias in leading singer " flower field is wrong ", then meets the person of singing and receive in leading singer's audio that server is sent only The voice audio of accentor, then second terminal user can only sing opera arias.

Step 405, second terminal records the second voice audio of the second segment of target song.

In an implementation, recording target song can be there are two types of mode, the first: second terminal receives meeting after leading singer's audio Display connects and sings the page, connects to sing and is provided with recording option in the page, as shown in figure 5f.Second terminal starts to play leading singer's sound simultaneously Frequently, leading a chorus in audio may include audio accompaniment, can not also include audio accompaniment, as the people of the accentor in leading singer's audio It after sound audio plays, clicks and records option, second terminal opens sound-recording function, starts to record the voice audio for meeting the person of singing (i.e. Second voice audio).Second terminal user, which also can choose to click directly on, records the voice audio-frequency unit that option skips accentor, The sound-recording function for directly opening second terminal starts to connect singing song, connects second terminal after singing and end automatically sound-recording function.The Two kinds: second terminal plays leading singer's audio after receiving leading singer's audio, and leading a chorus in audio may include audio accompaniment, can also not Including audio accompaniment, after the voice audio (i.e. the first sound audio) for leading a chorus the accentor in audio plays, second eventually Sound-recording function is opened at end, starts to record the voice audio for meeting the person of singing.

Step 406, second terminal is based on the second voice audio and the first audio, generates the second audio.

Wherein, the second audio includes the first sound audio of the first segment of target song and the second segment of target song The second voice audio, at the beginning of end time of first segment in target song and the second segment are in target song It is identical.It can also include the audio accompaniment of target song in second audio.

In an implementation, second terminal can record the voice audio of the second account and close with the voice audio in leading singer's audio At generation, which connects, sings audio, i.e. the second audio.If leading a chorus audio is sung under the mode of singing opera arias, the voice of the second account Audio meeting direct splicing is behind leading singer's audio.If leading a chorus audio is sung under accompaniment mode, the second account Voice audio can connect in leading singer's audio behind the first voice, and such as Fig. 6 a, for leading singer's audio under accompaniment mode, Fig. 6 b is companion It plays connecing of generating under mode and sings audio.

Step 407, second terminal sends the second audio to server.

Step 408, server receives the second audio of the target song that second terminal is sent.

In an implementation, when server receive second terminal transmission connect sing audio after, the first account account dynamic The corresponding position of leading singer's audio in the page adds the play options of the second account.Simultaneously in the account dynamic page of the second account Middle addition, which connects, sings the corresponding play options of audio.Sing application program be additionally provided with account concern the page be used to as shown in fig. 5g Browsing user, which pays close attention to the leading singer of account publication or connects, sings audio.For example, account B connects leading singer's audio " the flower field for having sung account A publication It is wrong ", it generates to connect and sings audio.Server, which can add account B in the account dynamic page of account A and connect, sings the corresponding broadcasting of audio Option, while can add to connect in the account dynamic page of account B and sing corresponding connect of audio and sing option.Server can also be related in institute Addition account B, which connects, in the account concern page of note B account sings the corresponding play options of audio.

Fig. 7 is the process interacted between server and terminal in a kind of audio synthetic method provided by the embodiments of the present application Figure.In the process, it can participate in connecing there are two the above user singing processing.Referring to Fig. 7, which includes:

Step 701, server receives leading singer's notice that first terminal is sent.

Step 702, server stores the first audio.

Step 703, second terminal sings request to the connecing for the first audio that server sends corresponding target song.

Step 704, when receive second terminal transmission the first audio of correspondence connect sing request when, server to second eventually End sends first audio.

Step 705, the second voice audio of the second segment of the target song is recorded.

Wherein step 701-705 repeats to repeat no more with above-mentioned steps 401-405 content.

Step 706, when second terminal, which receives, terminates record command, terminate audio recording, alternatively, when recording it is long with When the sum of duration of the first sound audio is equal to the duration of the target song, terminate audio recording.

In an implementation, second terminal, which can show to connect, sings the recording page, connects to sing and record in the page including terminating option.Second Terminal can play leading singer's audio after receiving leading singer's audio, and leading a chorus in audio may include audio accompaniment, can not also include Audio accompaniment, after the voice audio for leading a chorus the accentor in audio plays, second terminal opens sound-recording function, starts to record System connects the voice audio for the person of singing.Second terminal user also can choose the voice audio-frequency unit for skipping accentor, directly open the The sound-recording function of two terminals starts to connect singing song.In connecing and singing, connects connecing for the person of singing and sing the time and can be equipped with minimum duration, in sound The duration that frequency is recorded is when being less than minimum duration, terminate option be in can not selected state, be more than to terminate choosing after minimum duration Enter can click end option with selected state, user, before target song terminates terminate sing, also can choose by Song connects to sing and finish.For example, set the minimum time to 10 seconds, meets the person of singing at least and then to lead a chorus audio and sing 10 seconds songs.10 It after second, meets the person of singing and can choose to terminate to connect at any point in time and sing, song can also be connect to sing and finish, connect second after singing Terminal ends automatically sound-recording function.

Step 707, the second voice audio and the first audio of the second segment of target song of the second terminal based on recording, Generate the second audio, wherein the second audio include the first segment of target song the first sound audio and target song Second voice audio of two segments, end time of first segment in target song opening in target song with the second segment Time beginning is identical.

Step 708, second terminal sends the second audio to server.

Step 709, if the sum of duration of the first sound audio and the second voice audio is less than the duration of target song, For server in the account dynamic page for the second account that second terminal currently logs in, addition corresponding connect of the second audio sings choosing , alternatively, adding corresponding connect of the second audio in function pages connecing to sing and singing option, if the first sound audio and the second voice The sum of duration of audio is equal to the duration of target song, then the account dynamic page of the second account currently logged in second terminal The corresponding play options of the second audio of middle addition, and/or, the corresponding broadcasting choosing of the second audio is added in function pages connecing to sing ?.

In an implementation, if the user of second terminal has not sung target song, just form over two people's Sing building sequence.Server can be judged based on duration at this time, if connect, to sing the sum of duration of each one sound audio in audio small In the duration of target song, then server can participate in connecing the account dynamic page for each account sung or connecing to sing in function pages adding The correspondence that audio is sung in adjunction, which connects, sings option, if connect sing the sum of duration of each one sound audio in audio be equal to target song when Long, then addition connects and sings the corresponding play options of audio in the account dynamic page for the second account that second terminal currently logs in, The user for accessing the account dynamic page of the second account may browse through this and connect the displaying content for singing audio, and by playing choosing Playing this connects and sings audio, in addition can also sing the corresponding play options of audio connecing to sing to add this in function pages and connect, each Browsing, which connects, to be sung the users of function pages and can sing the displaying content of audio connecing to sing to browse to this in function pages and connect, and by broadcasting Putting option plays, this connects and sings audio.

It sings application program for example, user can operate first terminal starting and logs in A account, concurrent cloth leads a chorus audio A. Leading singer's audio A that the B account that second terminal logs in can issue A account connect singing, and generation, which connects, sings audio A B.If A account The sum of voice audio time of family and B account is equal in the duration of target song accompaniment time, then account of the server in B account Addition, which connects, in dynamic page sings the corresponding broadcasting choosing of audio A B, and server can also pay close attention to the page in the account of all concern B accounts Middle addition, which connects, sings the corresponding play options of audio A B.If the sum of voice audio time of A account and B account is less than target song The duration of accompaniment time, server can connect connecing to sing function pages and add in the accounts concern pages of all concern B accounts It sings connecing for audio A B and sings option.And the corresponding position addition of leading singer's audio A that can be issued in the account dynamic page of A account Option is sung in connecing for AB, meanwhile, server can also add to connect in the account dynamic page of B account and sing connecing for audio A B and sing option. Later when the account dynamic page of C account browsing A account, it both can choose to connect and sung leading singer's audio A, generation, which connects, sings audio A C, Also it can choose to connect and sing connecing for B and sing audio A B, when the account dynamic page of C account browsing B account, can connect and sing connecing for B and sing Audio A B is generated to connect and is sung audio A BC.According to the above rule, it can also generate to connect and sing audio A CD, connect and sing audio A BCD etc.. If C account continues to sing audio A B and be followed by singing connecing, and the sum of A account, B account and the voice audio duration of C account are equal to The duration of the audio accompaniment of target song, then account concern of the server in all concern C accounts of account dynamic page of C account The play options of middle addition ABC audio in the page.

The embodiment of the present application provides a kind of device for carrying out audio synthesis, which can be the service in above-described embodiment Device, as shown in figure 8, described device includes:

Receiving module 810 is configured as receiving leading singer's notice that first terminal is sent, wherein take in leading singer's notice The first audio with target song, first audio include the first sound audio of the first segment of the target song；

Memory module 820 is configured as storing first audio；

Sending module 830 is configured as singing request when the connecing for correspondence first audio for receiving second terminal transmission When, Xiang Suoshu second terminal sends first audio；

Receiving module 840 is configured as receiving the second audio of the target song that the second terminal is sent, In, second audio include the first segment of the target song the first sound audio and second of the target song Second voice audio of section, end time of first segment in the target song and second segment are in the mesh It is identical at the beginning of marking in song.

The embodiment of the present application provides a kind of device for carrying out audio synthesis, which can be the end in above-described embodiment End, as shown in figure 9, described device includes:

Sending module 910, the connecing for the first audio for being configured as sending corresponding target song to server sing request；

Receiving module 920 is configured as receiving first audio that the server is sent, wherein first sound Frequency includes the first sound audio of the first segment of the target song；

Module 930 is recorded, is configured as recording the second voice audio of the second segment of the target song；

Generation module 940 is configured as generating the second audio based on the second voice audio and first audio, Wherein, second audio include the first segment of the target song the first sound audio and the target song second Second voice audio of segment, end time of first segment in the target song is with second segment described It is identical at the beginning of in target song；

Sending module 950 is configured as sending second audio to the server.

Optionally, the sending module 910, is also configured to send to server and connects art of singing and can request that；

The receiving module 920, is also configured to receive that the server sends connects and sing function pages, wherein described It connects to sing in function pages and sings option including corresponding connect of the first audio；

The sending module 910, is configured as: singing the triggering command of option when receiving corresponding connect of first audio When, the connecing for the first audio for sending corresponding target song to server sings request.

Optionally, the sending module 910 is also configured to send the account dynamic page of the first account to server Request, wherein first account is to upload the account of first audio；

The receiving module 920 is also configured to receive the account dynamic page for the first account that the server is sent Face, wherein include that corresponding connect of the first audio sings option in the account dynamic page of first account；

Optionally, the recording module 930, is configured as: when receiving starting record command, start audio recording, When receiving end record command, or the sum of duration for recording duration and the first sound audio is equal to the target song When duration, terminate audio recording；

The embodiment of the present application also provides a kind of system for carrying out audio synthesis, it is characterised in that eventually the system comprises first End, second terminal and server, in which:

It should be understood that it is provided by the above embodiment carry out audio synthesis device when carrying out audio synthesis, only with The division progress of above-mentioned each functional module can according to need and for example, in practical application by above-mentioned function distribution by not Same functional module is completed, i.e., the internal structure of device is divided into different functional modules, to complete whole described above Or partial function.In addition, progress audio synthetic method embodiment provided by the above embodiment belongs to same design, it is specific Realization process is detailed in embodiment of the method, and which is not described herein again.

Figure 10 shows the structural block diagram of the terminal 1000 of one exemplary embodiment of the application offer.The terminal can be First terminal or second terminal in above-described embodiment.The terminal 1000 may is that smart phone, tablet computer, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) player, laptop or desktop computer.Terminal 1000 is also possible to referred to as user equipment, portable terminal, on knee Other titles such as terminal, terminal console.

In general, terminal 1000 includes: processor 1001 and memory 1002.

Processor 1001 may include one or more processing cores, such as 4 core processors, 8 core processors etc..Place Reason device 1001 can use DSP (Digital Signal Processing, Digital Signal Processing), FPGA (Field- Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array, may be programmed Logic array) at least one of example, in hardware realize.Processor 1001 also may include primary processor and coprocessor, master Processor is the processor for being handled data in the awake state, also referred to as CPU (Central Processing Unit, central processing unit)；Coprocessor is the low power processor for being handled data in the standby state.? In some embodiments, processor 1001 can be integrated with GPU (Graphics Processing Unit, image processor), GPU is used to be responsible for the rendering and drafting of content to be shown needed for display screen.In some embodiments, processor 1001 can also be wrapped AI (Artificial Intelligence, artificial intelligence) processor is included, the AI processor is for handling related machine learning Calculating operation.

Memory 1002 may include one or more computer readable storage mediums, which can To be non-transient.Memory 1002 may also include high-speed random access memory and nonvolatile memory, such as one Or multiple disk storage equipments, flash memory device.In some embodiments, the non-transient computer in memory 1002 can Storage medium is read for storing at least one instruction, at least one instruction performed by processor 1001 for realizing this Shen Please in embodiment of the method provide carry out audio synthetic method.

In some embodiments, terminal 1000 is also optional includes: peripheral device interface 1003 and at least one periphery are set It is standby.It can be connected by bus or signal wire between processor 1001, memory 1002 and peripheral device interface 1003.It is each outer Peripheral equipment can be connected by bus, signal wire or circuit board with peripheral device interface 1003.Specifically, peripheral equipment includes: In radio circuit 1004, touch display screen 1005, camera 1006, voicefrequency circuit 1007, positioning component 1008 and power supply 1009 At least one.

Peripheral device interface 1003 can be used for I/O (Input/Output, input/output) is relevant outside at least one Peripheral equipment is connected to processor 1001 and memory 1002.In some embodiments, processor 1001, memory 1002 and periphery Equipment interface 1003 is integrated on same chip or circuit board；In some other embodiments, processor 1001, memory 1002 and peripheral device interface 1003 in any one or two can be realized on individual chip or circuit board, this implementation Example is not limited this.

Radio circuit 1004 is for receiving and emitting RF (Radio Frequency, radio frequency) signal, also referred to as electromagnetic signal. Radio circuit 1004 is communicated by electromagnetic signal with communication network and other communication equipments.Radio circuit 1004 is by telecommunications Number being converted to electromagnetic signal is sent, alternatively, the electromagnetic signal received is converted to electric signal.Optionally, radio circuit 1004 include: antenna system, RF transceiver, one or more amplifiers, tuner, oscillator, digital signal processor, volume solution Code chipset, user identity module card etc..Radio circuit 1004 can by least one wireless communication protocol come with it is other Terminal is communicated.The wireless communication protocol includes but is not limited to: Metropolitan Area Network (MAN), each third generation mobile communication network (2G, 3G, 4G and 5G), WLAN and/or WiFi (Wireless Fidelity, Wireless Fidelity) network.In some embodiments, radio frequency electrical Road 1004 can also include NFC (Near Field Communication, wireless near field communication) related circuit, the application This is not limited.

Display screen 1005 is for showing UI (User Interface, user interface).The UI may include figure, text, Icon, video and its their any combination.When display screen 1005 is touch display screen, display screen 1005 also there is acquisition to exist The ability of the touch signal on the surface or surface of display screen 1005.The touch signal can be used as control signal and be input to place Reason device 1001 is handled.At this point, display screen 1005 can be also used for providing virtual push button and/or dummy keyboard, it is also referred to as soft to press Button and/or soft keyboard.In some embodiments, display screen 1005 can be one, and the front panel of terminal 1000 is arranged；Another In a little embodiments, display screen 1005 can be at least two, be separately positioned on the different surfaces of terminal 1000 or in foldover design； In still other embodiments, display screen 1005 can be flexible display screen, is arranged on the curved surface of terminal 1000 or folds On face.Even, display screen 1005 can also be arranged to non-rectangle irregular figure, namely abnormity screen.Display screen 1005 can be with Using LCD (Liquid Crystal Display, liquid crystal display), OLED (Organic Light-Emitting Diode, Organic Light Emitting Diode) etc. materials preparation.

CCD camera assembly 1006 is for acquiring image or video.Optionally, CCD camera assembly 1006 includes front camera And rear camera.In general, the front panel of terminal is arranged in front camera, the back side of terminal is arranged in rear camera.? In some embodiments, rear camera at least two is that main camera, depth of field camera, wide-angle camera, focal length are taken the photograph respectively As any one in head, to realize that main camera and the fusion of depth of field camera realize background blurring function, main camera and wide Pan-shot and VR (Virtual Reality, virtual reality) shooting function or other fusions are realized in camera fusion in angle Shooting function.In some embodiments, CCD camera assembly 1006 can also include flash lamp.Flash lamp can be monochromatic temperature flash of light Lamp is also possible to double-colored temperature flash lamp.Double-colored temperature flash lamp refers to the combination of warm light flash lamp and cold light flash lamp, can be used for Light compensation under different-colour.

Voicefrequency circuit 1007 may include microphone and loudspeaker.Microphone is used to acquire the sound wave of user and environment, and It converts sound waves into electric signal and is input to processor 1001 and handled, or be input to radio circuit 1004 to realize that voice is logical Letter.For stereo acquisition or the purpose of noise reduction, microphone can be separately positioned on the different parts of terminal 1000 to be multiple. Microphone can also be array microphone or omnidirectional's acquisition type microphone.Loudspeaker is then used to that processor 1001 or radio frequency will to be come from The electric signal of circuit 1004 is converted to sound wave.Loudspeaker can be traditional wafer speaker, be also possible to piezoelectric ceramics loudspeaking Device.When loudspeaker is piezoelectric ceramic loudspeaker, the audible sound wave of the mankind can be not only converted electrical signals to, can also be incited somebody to action Electric signal is converted to the sound wave that the mankind do not hear to carry out the purposes such as ranging.In some embodiments, voicefrequency circuit 1007 may be used also To include earphone jack.

Positioning component 1008 is used for the current geographic position of positioning terminal 1000, to realize navigation or LBS (Location Based Service, location based service).Positioning component 1008 can be the GPS (Global based on the U.S. Positioning System, global positioning system), the dipper system of China, Russia Gray receive this system or European Union The positioning component of Galileo system.

Power supply 1009 is used to be powered for the various components in terminal 1000.Power supply 1009 can be alternating current, direct current Electricity, disposable battery or rechargeable battery.When power supply 1009 includes rechargeable battery, which can support wired Charging or wireless charging.The rechargeable battery can be also used for supporting fast charge technology.

In some embodiments, terminal 1000 further includes having one or more sensors 1010.One or more sensing Device 1010 includes but is not limited to: acceleration transducer 1011, gyro sensor 1012, pressure sensor 1013, fingerprint sensing Device 1014, optical sensor 1015 and proximity sensor 1016.

Acceleration transducer 1011 can detecte the acceleration in three reference axis of the coordinate system established with terminal 1000 Size.For example, acceleration transducer 1011 can be used for detecting component of the acceleration of gravity in three reference axis.Processor The 1001 acceleration of gravity signals that can be acquired according to acceleration transducer 1011, control touch display screen 1005 with transverse views Or longitudinal view carries out the display of user interface.Acceleration transducer 1011 can be also used for game or the exercise data of user Acquisition.

Gyro sensor 1012 can detecte body direction and the rotational angle of terminal 1000, gyro sensor 1012 Acquisition user can be cooperateed with to act the 3D of terminal 1000 with acceleration transducer 1011.Processor 1001 is according to gyro sensors The data that device 1012 acquires, following function may be implemented: action induction (for example changing UI according to the tilt operation of user) is clapped Image stabilization, game control and inertial navigation when taking the photograph.

The lower layer of side frame and/or touch display screen 1005 in terminal 1000 can be set in pressure sensor 1013.When When the side frame of terminal 1000 is arranged in pressure sensor 1013, user can detecte to the gripping signal of terminal 1000, by Reason device 1001 carries out right-hand man's identification or prompt operation according to the gripping signal that pressure sensor 1013 acquires.Work as pressure sensor 1013 when being arranged in the lower layer of touch display screen 1005, is grasped by processor 1001 according to pressure of the user to touch display screen 1005 Make, realization controls the operability control on the interface UI.Operability control include button control, scroll bar control, At least one of icon control, menu control.

Fingerprint sensor 1014 is used to acquire the fingerprint of user, is collected by processor 1001 according to fingerprint sensor 1014 Fingerprint recognition user identity, alternatively, by fingerprint sensor 1014 according to the identity of collected fingerprint recognition user.Knowing Not Chu the identity of user when being trusted identity, authorize the user to execute relevant sensitive operation by processor 1001, which grasps Make to include solving lock screen, checking encryption information, downloading software, payment and change setting etc..Fingerprint sensor 1014 can be set Set the front, the back side or side of terminal 1000.When being provided with physical button or manufacturer Logo in terminal 1000, fingerprint sensor 1014 can integrate with physical button or manufacturer Logo.

Optical sensor 1015 is for acquiring ambient light intensity.In one embodiment, processor 1001 can be according to light The ambient light intensity that sensor 1015 acquires is learned, the display brightness of touch display screen 1005 is controlled.Specifically, work as ambient light intensity When higher, the display brightness of touch display screen 1005 is turned up；When ambient light intensity is lower, the aobvious of touch display screen 1005 is turned down Show brightness.In another embodiment, the ambient light intensity that processor 1001 can also be acquired according to optical sensor 1015, is moved The acquisition parameters of state adjustment CCD camera assembly 1006.

Proximity sensor 1016, also referred to as range sensor are generally arranged at the front panel of terminal 1000.Proximity sensor 1016 for acquiring the distance between the front of user Yu terminal 1000.In one embodiment, when proximity sensor 1016 is examined When measuring the distance between the front of user and terminal 1000 and gradually becoming smaller, by processor 1001 control touch display screen 1005 from Bright screen state is switched to breath screen state；When proximity sensor 1016 detect the distance between front of user and terminal 1000 by When gradual change is big, touch display screen 1005 is controlled by processor 1001 and is switched to bright screen state from breath screen state.

It, can be with it will be understood by those skilled in the art that the restriction of the not structure paired terminal 1000 of structure shown in Figure 10 Including than illustrating more or fewer components, perhaps combining certain components or being arranged using different components.

Figure 11 is a kind of structural schematic diagram of server provided by the embodiments of the present application, the server 1100 can because of configuration or Performance is different and generates bigger difference, may include one or more processors (central processing Units, CPU) 1001 and one or more memory 1102, wherein at least one is stored in the memory 1102 Item instruction, at least one instruction are loaded by the processor 1101 and are executed to realize that above-mentioned each embodiment of the method provides Method.Certainly, which can also have the components such as wired or wireless network interface, keyboard and input/output interface, To carry out input and output, which can also include other for realizing the component of functions of the equipments, and this will not be repeated here.

In the exemplary embodiment, a kind of computer readable storage medium is additionally provided, the memory for example including instruction, Above-metioned instruction can be executed by the processor in terminal to complete to carry out audio synthetic method in following embodiments.For example, described Computer readable storage medium can be read-only memory (Read-only Memory, ROM), random access memory (Random Access Memory, RAM), CD-ROM, tape, floppy disk and optical data storage devices etc..

Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..

The foregoing is merely the preferred embodiments of the application, not to limit the application, it is all in spirit herein and Within principle, any modification, equivalent replacement, improvement and so on be should be included within the scope of protection of this application.

Claims

1. a kind of progress audio synthetic method, which is characterized in that the method is used for terminal, comprising:

Receive first audio that the server is sent, wherein first audio includes the first of the target song The first sound audio of segment；

Record the second voice audio of the second segment of the target song；

Based on the second voice audio and first audio, the second audio is generated, wherein second audio includes described Second voice audio of the second segment of the first sound audio and target song of the first segment of target song, described One segment the end time in the target song with second segment in the target song at the beginning of it is identical；

Second audio is sent to the server.

2. the method according to claim 1, wherein first audio further includes the accompaniment of the target song Audio, second audio further include the audio accompaniment of the target song.

3. method according to claim 1 or 2, which is characterized in that described to send the of corresponding target song to server One audio connects before singing request, further includes:

Connecing art of singing to server transmission can request that；

It receives the connecing for server transmission and sings function pages, wherein described connect is sung in function pages including first audio Corresponding connect sings option；

It is connect described in display and sings function pages；

When receiving that first audio is corresponding to connect the triggering command for singing option, corresponding target song is sent to server Request is sung in connecing for first audio.

4. method according to claim 1 or 2, which is characterized in that described to send the of corresponding target song to server One audio connects before singing request, further includes:

The account dynamic page request of the first account is sent to server, wherein first account is to upload first sound The account of frequency；

Receive the account dynamic page for the first account that the server is sent, wherein the account dynamic page of first account It include that corresponding connect of the first audio sings option in face；

Show the account dynamic page of first account；

5. method according to claim 1 or 2, which is characterized in that second segment for recording the target song Second voice audio, comprising:

When receiving starting record command, start audio recording；

When receiving end record command, or the sum of duration for recording duration and the first sound audio is equal to the target and sings When the duration of song, terminate audio recording；

6. a kind of progress audio synthetic method, which is characterized in that the method is used for server, comprising:

Receive leading singer's notice that first terminal is sent, wherein the first audio of target song, institute are carried in leading singer's notice State the first sound audio that the first audio includes the first segment of the target song；

Store first audio；

When receive second terminal transmission correspondence first audio connect sing request when, Xiang Suoshu second terminal send described in First audio；

Receive the second audio of the target song that the second terminal is sent, wherein second audio includes the mesh Second voice audio of the second segment of the first sound audio and target song of the first segment of mark song, described first Segment the end time in the target song with second segment in the target song at the beginning of it is identical.

7. according to the method described in claim 6, it is characterized in that, first audio further includes the accompaniment of the target song Audio, second audio further include the audio accompaniment of the target song.

8. method according to claim 6 or 7, which is characterized in that the leading singer for receiving first terminal transmission notifies it Afterwards, further includes:

9. method according to claim 6 or 7, which is characterized in that the leading singer for receiving first terminal transmission notifies it Afterwards, further includes:

In the account dynamic page for the first account that the first terminal currently logs in, addition first audio is corresponding to be connect Sing option.

10. method according to claim 6 or 7, which is characterized in that the mesh for receiving the second terminal and sending After the second audio for marking song, further includes:

In the account dynamic page for the first account that the first terminal currently logs in, addition second audio is corresponding to be broadcast Option is put, and in the account dynamic page for the second account that the second terminal currently logs in, adds second audio pair The play options answered.

11. method according to claim 6 or 7, which is characterized in that the mesh for receiving the second terminal and sending After the second audio for marking song, further includes:

If the sum of duration of the first sound audio and the second voice audio is equal to the duration of the target song, In the account dynamic page for the first account that the first terminal currently logs in, the corresponding broadcasting choosing of second audio is added , and in the account dynamic page for the second account that the second terminal currently logs in, it is corresponding to add second audio Play options；

If the sum of duration of the first sound audio and the second voice audio is less than the duration of the target song, In the account dynamic page for the second account that the second terminal currently logs in, adds corresponding connect of the second audio and sing choosing , and/or, connecing to sing corresponding connect of the second audio is added in function pages sing option.

12. a kind of device for carrying out audio synthesis, which is characterized in that described device is used for terminal, comprising:

Receiving module is configured as receiving first audio that the server is sent, wherein first audio includes institute State the first sound audio of the first segment of target song；

Generation module is configured as generating the second audio, wherein institute based on the second voice audio and first audio State the first sound audio for the first segment that the second audio includes the target song and the second segment of the target song Second voice audio, end time of first segment in the target song and second segment are sung in the target It is identical at the beginning of in song；

Sending module is additionally configured to send second audio to the server.

13. a kind of device for carrying out audio synthesis, which is characterized in that described device includes:

Receiving module is configured as receiving leading singer's notice that first terminal is sent, wherein carry target in leading singer's notice First audio of song, first audio include the first sound audio of the first segment of the target song；

Memory module is configured as storing first audio；

Sending module, be configured as when receive second terminal transmission correspondence first audio connect sing request when, to institute It states second terminal and sends first audio；

Receiving module is additionally configured to receive the second audio of the target song that the second terminal is sent, wherein described Second audio includes the of the first sound audio of the first segment of the target song and the second segment of the target song Two voice audios, end time of first segment in the target song and second segment are in the target song In at the beginning of it is identical.

14. a kind of system for carrying out audio synthesis, which is characterized in that the system comprises first terminal, second terminal and services Device, in which:

The server receives leading singer's notice that first terminal is sent, wherein carries target song in leading singer's notice First audio, first audio include the first sound audio of the first segment of the target song；Store first sound Frequently；When receive second terminal transmission correspondence first audio connect sing request when, Xiang Suoshu second terminal send described in First audio；Receive the second audio of the target song that the second terminal is sent, wherein second audio includes institute The second voice audio of the first sound audio of the first segment of target song and the second segment of the target song is stated, it is described First segment the end time in the target song with second segment in the target song at the beginning of phase Together；

The second terminal, the connecing for the first audio that Xiang Suoshu server sends corresponding target song sing request；Receive the clothes First audio that business device is sent；Record the second voice audio of the second segment of the target song；Based on described second Voice audio and first audio generate second audio；Second audio is sent to the server.

15. a kind of computer equipment, which is characterized in that the computer equipment includes processor and memory, the memory In be stored at least one instruction, described instruction is loaded by the processor and is executed to realize as claim 1 to right is wanted Ask operation performed by 11 described in any item progress audio synthetic methods.

16. a kind of computer readable storage medium, which is characterized in that be stored at least one instruction, institute in the storage medium Instruction is stated to be loaded by processor and executed to realize as claim 1 to the described in any item progress audios of claim 11 synthesize Operation performed by method.