CN105070283A - Singing voice scoring method and apparatus - Google Patents
Singing voice scoring method and apparatus Download PDFInfo
- Publication number
- CN105070283A CN105070283A CN201510535602.1A CN201510535602A CN105070283A CN 105070283 A CN105070283 A CN 105070283A CN 201510535602 A CN201510535602 A CN 201510535602A CN 105070283 A CN105070283 A CN 105070283A
- Authority
- CN
- China
- Prior art keywords
- song
- music
- singing voice
- slices
- background music
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Auxiliary Devices For Music (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a singing voice scoring method and apparatus. The method comprises the following steps: receiving singing voice input by a user; performing voice identification on the singing voice to obtain melody or a lyric text corresponding to the singing voice; and according to the melody or the lyric text, matching the singing voice with background music to generate a song or determining a corresponding accompaniment tape for recommending to the user. Compared to a conventional singing mode of directly flowing the background music in the prior art, the fun is enhanced, and the creativity and the participation of the user can be fully tapped.
Description
Technical field
The embodiment of the present invention relates to network technology, particularly relates to a kind of method and apparatus of dubbing in background music for singing voice.
Background technology
Along with communication and the high speed development of infotech, music function has become an indispensable application in the terminal such as computing machine or mobile phone.
Music series products of the prior art, mostly that user selects corresponding song to play, or user selects corresponding musical background and follows musical background and captions are sung, formal in social activity, the song sung can be shared on social network sites by user.The defect existed is with user interaction Method compare single, lacks interesting, fully can not excavate creativeness, the property of participation of user.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method and apparatus of dubbing in background music for singing voice, to improve interest.
First aspect, embodiments provide a kind of method of dubbing in background music for singing voice, described method comprises:
Receive the singing voice of user's input;
Speech recognition is carried out to described singing voice, obtains the melody corresponding with described singing voice or lyric characters;
According to described melody or lyric characters, generate a song for described singing voice matching background music or determine that corresponding accompaniment is with and recommends user.
Second aspect, the embodiment of the present invention additionally provides a kind of device of dubbing in background music for singing voice, and described device comprises:
Song receiver module, for receiving the singing voice of user's input;
Sound identification module, for carrying out speech recognition to described singing voice, obtains the melody corresponding with described singing voice or lyric characters;
Song synthesis module, for according to described melody or lyric characters, generates a song for described singing voice matching background music or determines that corresponding accompaniment is with and recommends user.
The method and apparatus of dubbing in background music for singing voice that the embodiment of the present invention provides, by being that described singing voice adds background music according to the singing voice of user, or recommends to user band of accompanying accordingly.The embodiment of the present invention is sung relative to background music of directly following of the prior art, improves interest, and fully can excavate creativeness and the property of participation of user.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention one provides;
Fig. 2 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention two provides;
Fig. 3 is extraction background music in the method for dubbing in background music for singing voice that provides of the embodiment of the present invention and background music and singing voice is synthesized the process flow diagram of song;
Fig. 4 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention three provides;
Fig. 5 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention four provides;
Fig. 6 is the structural representation of a kind of device of dubbing in background music for singing voice that the embodiment of the present invention five provides.
Embodiment
Below in conjunction with drawings and Examples, the present invention is described in further detail.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not full content.
Embodiment one
Fig. 1 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention one provides, the present embodiment is applicable to the situation that the one section of singing voice inputted according to user is user's matching background music, the method can be performed by the terminal such as computing machine or mobile phone, specifically comprises as follows:
S110, receives the singing voice of user's input.
In order to fully excavate creativeness and the property of participation of user, one section that can sing for user or a song matching background music, make it to become the full songs that a section or a head have background music.In order to realize such function, first one section of user's input or the singing voice of a song to be received by microphone.
S120, carries out speech recognition to described singing voice, obtains the melody corresponding with described singing voice or lyric characters.
Speech recognition system is utilized to carry out speech recognition to described singing voice, to identify melody in described singing voice or lyric characters corresponding to described singing voice.
Speech recognition technology allows machine, by identification and understanding process, voice signal is changed into the hi-tech of corresponding text or order, and speech recognition technology mainly comprises Feature Extraction Technology, pattern match criterion and model training technology three aspects.
S130, according to described melody or lyric characters, generates a song for described singing voice matching background music or determines that corresponding accompaniment is with and recommends user.
According to described melody or lyric characters, the song that search is corresponding with described melody or lyric characters in music libraries, and in described song, extract the background music corresponding with described melody or lyric characters, according to the corresponding relation of the melody in the singing voice of user or lyric characters and background music, described singing voice and described background music are synthesized a song.
Also according to searching for the song obtained in music libraries, singer's sound corresponding in this song can be removed, thus band of being accompanied accordingly, this accompaniment band is recommended user, such as, which first song what can inform that user sings is, and recommends user to use accompaniment band to sing.
The present embodiment is by after receiving the singing voice of user, speech recognition is carried out to described singing voice, obtain the melody corresponding with described singing voice or lyric characters, according to described melody or lyric characters, generating a song for described singing voice matching background music or determine that corresponding accompaniment is with and recommends user, is that described singing voice with the addition of background music according to the singing voice of user.The embodiment of the present invention improves interest, and fully can excavate creativeness and the property of participation of user, gives full play to the property of participation of user, yields to user, instead of user's deallocation closes background music; After user has at will sung one section of song, automatically for user adds background music, satisfaction and the sense of accomplishment of user can be promoted; The user of hobby practical joke, each may be all different song, can synthesize a song, add interest by the method in the embodiment of the present invention for it; For the singing voice according to user, after user synthesizes song, the works of oneself can be shared in social network sites by user, and the friend for oneself browses comment.
Embodiment two
Fig. 2 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention two provides, the present embodiment in embodiment one according to described melody, be optimized for described singing voice matching background music generates a song, specifically comprise as follows:
S210, receives the singing voice of user's input.
S220, carries out speech recognition to described singing voice, obtains the melody corresponding with described singing voice.
The song that the present embodiment mates with singing voice according to the melody in singing voice search, therefore, this step obtains the melody corresponding with described singing voice through speech recognition.
S230, according to described melody, by large data engine, at least one song of search and described melody matching in music libraries.
Wherein, large data engine refers to be collected large data, store, calculates, excavates and manages, and by degree of depth learning art and data modeling technology, data is had " intelligence ".Data engine as large in Baidu, the large data engine of Baidu mainly comprises three large assemblies: open cloud, data factory and Baidu's brain.
A large amount of song files that have purchased copyright is contained in music libraries, described song files can contain the music of all kinds substantially, searched in music libraries by large data engine, when searching for, the melody of the song of mating in music libraries is removed according to described melody, when matching degree reaches setting value, can think that this song is the song with described melody matching.
Wherein, singing voice may be in a certain song sung of user one section or one whole, also may be every in short respectively from different songs, or other situations.Therefore, the song of above-mentioned search and described melody matching in music libraries can search at least one song.
Certainly, the pattern of a song or how first song also can be selected by user, thus when searching in music libraries, can according to the pattern of user's selection for user mates corresponding song.When user selects the pattern of a song, in music libraries, search for a song the highest with described singing voice matching degree; When user selects the pattern of how first song, can often a bit of according to the song in the every a bit of coupling music libraries in singing voice.
S240, extracts background music corresponding with described melody at least one song described, and described background music and described singing voice is synthesized a song.
The background music corresponding with described melody at least one song described is extracted respectively, described background music is added to melody corresponding with described background music in described singer's voice, thus described background music and described singing voice are synthesized a song.
Concrete, Fig. 3 is extraction background music in the method for dubbing in background music for singing voice that provides of the embodiment of the present invention and background music and singing voice is synthesized the process flow diagram of song, as shown in Figure 3, extract background music corresponding with described melody at least one song described, and described background music and described singing voice are synthesized a song preferably include as follows:
S241, according to the pause in described singing voice or interval, carries out melody section to described singing voice, obtains song section;
S242, searches singer's sound that matching degree of cutting into slices with described song reaches setting value and cuts into slices at least one song described;
The singing voice of user differs completely the same with the melody of the singer's sound in song surely, therefore, cuts into slices with the cut into slices singer's sound be consistent of thinking to cut into slices with the song of user of singer's sound that the matching degree that described song is cut into slices reaches setting value.
S243, according to the section of described singer's sound, corresponding background music of determining cut into slices with described singer's sound is cut into slices, and described background music is cut into slices and to be cut into slices as with described song corresponding background music of cutting into slices;
S244, to cut into slices synthesis one song by the section of described song and with described song corresponding background music of cutting into slices.
Wherein, described background music section preferably includes absolute music section and cuts into slices with voice music;
Preferably include by the section of described song and with described song corresponding background music synthesis one song of cutting into slices of cutting into slices:
Described absolute music section is inserted between adjacent song section;
According to sound size, speed and tone in the section of described song, regulate sound size, speed and tone that corresponding adjoint voice music of cut into slices with described song is cut into slices, and described song to be cut into slices and adjoint voice music after adjustment is cut into slices and is synthesized together.
Wherein, absolute music section refers to the background music in the pause between singer's sound, refers to the background music with singer's sound with the section of voice music.Tone (key), be exactly the sound that under the keynote domination played the role of a nucleus in musical works (or the some parts in works), a group that works mutually has certain altitude, tune is consistent with scale.
According to sound size, speed and tone in described song section, sound size, speed and tone that the adjoint voice music regulating described song to cut into slices correspondence is cut into slices, make it to adapt to the section of described song, described song section and the adjoint voice music after regulating are cut into slices and is synthesized together, make described section with voice music be called the background music that described song is cut into slices.
By searching the singer's sound mated of cut into slices with described song in song in music libraries cut into slices to singing voice section, can matching precision be improved, thus be the singing voice interpolation background music more accurately of user.
The present embodiment is by after the singing voice receiving user's input, speech recognition is carried out to described singing voice, obtain the melody corresponding with described singing voice, according to described melody, by large data engine, at least one song of search and described melody matching in music libraries, extract background music corresponding with described melody at least one song described, and described background music and described singing voice are synthesized a song, be that described singing voice with the addition of background music according to the melody of the singing voice of user, improve interest, and fully can excavate creativeness and the property of participation of user, compared with embodiment one, the present embodiment searches for the song of coupling in music libraries by large data engine according to the melody of singing voice, search speed and precision can be improved.
On the basis of technique scheme, before the singing voice receiving user's input, also preferably include:
Melody section is carried out to the every song in music libraries, determines the singer's sound section in every song, absolute music section and cut into slices with voice music.
One song is made up of singer's sound and background music, and background music can also be divided into absolute music part (music etc. when such as pausing between head, tail or every singer's sound) and adjoint voice musical portions.Wherein, singer's sound can be expressed as Voice, and background music is expressed as Bgm (Backgroundmusic), and absolute music part is expressed as PureBgm, is expressed as VoiceBgm with voice musical portions.
Carry out arrangement by large data engine to the melody in music libraries to divide, according to the pause in the music score of every song or song or interval, song is cut into slices, determine singer's sound section Voice1 of every song, Voice2, VoiceN, absolute music section PureBgm1, PuerBgm2 ..., PuerBgmN1 and adjoint voice music section VoiceBgm1, VoiceBgm2,, VoiceBgmN, wherein, the quantity that N represents the singer's sound section in a song or the quantity of cutting into slices with voice music, N1 represents the quantity of absolute music section in a song.Generally, the section of singer's sound is relation one to one with cut into slices with voice music, and namely every a bit of singer's sound has a bit of with voice background music, therefore, and the quantity that singer's sound is cut into slices and all representing with N with the quantity that voice music is cut into slices; In absolute music, add prelude and after play the head and tail part of i.e. song, many 1 of the quantity of the number ratio song sound section of absolute music section.
As expansion, above-mentioned song in music libraries is cut into slices after, also can the section obtained be used in the interactive game with user, such as: play the section of one of them singer's sound and the background music of correspondence, allow user guess the title etc. of this song; Also according to of user's humming, the singer's sound section matched can be searched in music libraries, thus obtains corresponding song, release the ranking list of song according to similarity, or similarity judgement is carried out to any two song works.
Embodiment three
Fig. 4 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention three provides, the present embodiment in embodiment one according to described lyric characters, be optimized for described singing voice matching background music generates a song, specifically comprise as follows:
S410, receives the singing voice of user's input.
S420, carries out speech recognition to described singing voice, obtains the lyric characters corresponding with described singing voice.
The song that the present embodiment mates with singing voice according to the lyric characters in singing voice search, therefore, this step obtains the lyric characters corresponding with described singing voice through speech recognition.
S430, according to described lyric characters, by large data engine, searches for the music word mated with described lyric characters in music libraries.
Searched in music libraries by large data engine, when searching for, removing the music word of the song of mating in music libraries according to described lyric characters, when matching degree reaches setting value, can think that this song is the song of mating with described lyric characters.
S440, according to described music word, determines at least one song corresponding with described music word.
Described music word may be the music word in a song, also may be each music word respectively from different songs, or other situations.Therefore, according to described music word, at least one song corresponding with described music word can be determined.
S450, extracts background music corresponding with described music word at least one song described, and described background music and described singing voice is synthesized a song.
Extract background music or background music and singing voice are synthesized song and can complete according to extracting mode corresponding in embodiment two or synthesis mode, repeat no more here.
The present embodiment is by after the singing voice receiving user's input, speech recognition is carried out to described singing voice and obtains the lyric characters corresponding with described singing voice, according to described lyric characters, in music libraries, the music word mated with described lyric characters is searched for by large data engine, at least one song corresponding with described music word is determined according to described music word, extract background music corresponding with described music word at least one song described, and described Beijing music and described singing voice are synthesized a song, be that described singing voice with the addition of background music according to the lyric characters in the singing voice of user, improve interest, and fully can excavate creativeness and the property of participation of user, compared with embodiment one, the present embodiment searches for the song of coupling in music libraries by large data engine according to the lyric characters in singing voice, search speed and precision can be improved.
Embodiment four
Fig. 5 is the process flow diagram of a kind of method of dubbing in background music for singing voice that the embodiment of the present invention four provides, the present embodiment in embodiment one according to described melody, be optimized for described singing voice matching background music generates a song, specifically comprise as follows:
S510, receives the singing voice of user's input.
S520, carries out speech recognition to described singing voice, obtains the melody corresponding with described singing voice.
In the present embodiment, according to the melody in singing voice, drive analog instruments generation background music, therefore, this step obtains the melody corresponding with described singing voice through speech recognition.
S530, according to described melody, drives analog instruments generation background music.
In the present embodiment, the singing voice of user, likely that user has carried out interest and at will sings, it is not the fragment in a certain song, therefore corresponding song cannot be found in music libraries, at this moment analog instruments generation background music can be driven, even if the singing voice of user is fragment in certain song also can drive analog instruments generation background music.When driving analog instruments generation background music, according to described melody, automatically generating the music score mated with described singing voice, driving musical instrument generation background music according to music score.Such as, analog instruments can be driven to generate piano version, violin version, whistling version, vertical bamboo flute sound version, violoncello version, guitar version or Chinese lute version etc.Wherein, described analog instruments comprises simulation piano, simulates violin, simulates flute or simulate desolate, can also comprise simulation violoncello, simulation guitar or simulation Chinese lute etc.
In addition, also according to member's grade, the background music of different editions can be generated, such as: for elementary member, piano version can be only had; For senior member, piano version, violin version, whistling version, vertical bamboo flute sound version, violoncello version, guitar version or Chinese lute version etc. can be had.
S540, synthesizes a song by described singing voice and described background music, and preserves described song.
Generate according to singing voice during described background music, in the process of generation background music, directly singing voice and background music are synthesized, finally become a complete song, and described song is preserved, so that user listens to the works of oneself.
The present embodiment is after the singing voice receiving user's input, speech recognition is carried out to described singing voice and obtains the melody corresponding with described singing voice, analog instruments generation background music is driven according to described melody, described singing voice and described background music are synthesized a song, and preserve described song, be described singing voice generation background music according to the melody of the singing voice of user, improve interest, and fully can excavate creativeness and the property of participation of user, compared with embodiment one, the present embodiment can drive analog instruments to be described singing voice generation background music according to the melody of singing voice, more can excite the creativeness of user.
On the basis of technique scheme, described singing voice and described background music are being synthesized a song, and after preserving described song, are also preferably including:
Play described song;
Receive tempo class audio and/or harmony that user is the definition of described song.
Play described song, in the process playing described song, receive user to the operation such as self-defined interpolation, reparation of described song, user can be that described song adds bass, bucket drum equal rhythm class audio, also harmony can be added simultaneously, the information such as one section of voice self-introduction can also be added in song beginning, add the information such as voice description in song ending.Wherein, harmony refers to and comprises the combined acoustics that two or more different sounds are formed by sounding while of certain rule: chord, it is the basic material of harmony, by more than 3 or 3 different sounds, according to three degree, stacked or additive method is bonded simultaneously, and this is the vertical structure of harmony; Harmony carries out, and refer to that the priority of each chord connects, this is the transverse movement of harmony.
Embodiment five
Fig. 6 is the structural representation of a kind of device of dubbing in background music for singing voice that the embodiment of the present invention five provides, and as shown in Figure 6, the device of dubbing in background music for singing voice described in this enforcement comprises song receiver module 610, sound identification module 620 and song synthesis module 630.
Wherein, song receiver module 610 is for receiving the singing voice of user's input;
Sound identification module 620, for carrying out speech recognition to described singing voice, obtains the melody corresponding with described singing voice or lyric characters;
Song synthesis module 630, for according to described melody or lyric characters, generates a song for described singing voice matching background music or determines that corresponding accompaniment is with and recommends user.
Preferably, described song synthesis module comprises:
Song search unit, for according to described melody, by large data engine, at least one song of search and described melody matching in music libraries;
First song synthesis unit, for extracting background music corresponding with described melody at least one song described, and synthesizes a song by described background music and described singing voice.
Preferably, described song synthesis unit comprises:
Melody section subelement, for according to the pause in described singing voice or interval, carries out melody section to described singing voice, obtains song section;
Singer's sound searches subelement, and the singer's sound reaching setting value for searching matching degree of cutting into slices with described song at least one song described is cut into slices;
Background music determination subelement, for according to the section of described singer's sound, corresponding background music of determining cut into slices with described singer's sound is cut into slices, and described background music is cut into slices and to be cut into slices as with described song corresponding background music of cutting into slices;
Song synthon unit, for cutting into slices synthesis one song by the section of described song and with described song corresponding background music of cutting into slices.
Preferably, described background music section comprises absolute music section and cuts into slices with voice music;
Described song synthon unit specifically for:
Described absolute music section is inserted between adjacent song section;
According to sound size, speed and tone in the section of described song, regulate sound size, speed and tone that corresponding adjoint voice music of cut into slices with described song is cut into slices, and described song to be cut into slices and adjoint voice music after adjustment is cut into slices and is synthesized together.
Preferably, described song synthesis module comprises:
Music text search unit, for according to described lyric characters, by large data engine, searches for the music word mated with described lyric characters in music libraries;
Song determining unit, for according to described music word, determines at least one song corresponding with described music word;
Second song synthesis unit, for extracting background music corresponding with described music word at least one song described, and synthesizes a song by described background music and described singing voice.
Preferably, described song synthesis module comprises:
Background music generation unit, for according to described melody, drives analog instruments generation background music;
3rd song synthesis unit, for described singing voice and described background music are synthesized a song, and preserves described song.
The said goods can perform the method that any embodiment of the present invention provides, and possesses the corresponding functional module of manner of execution and beneficial effect.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (15)
1. be the method that singing voice is dubbed in background music, it is characterized in that, described method comprises:
Receive the singing voice of user's input;
Speech recognition is carried out to described singing voice, obtains the melody corresponding with described singing voice or lyric characters;
According to described melody or lyric characters, generate a song for described singing voice matching background music or determine that corresponding accompaniment is with and recommends user.
2. method according to claim 1, is characterized in that, according to described melody, comprises for described singing voice matching background music generates a song:
According to described melody, by large data engine, at least one song of search and described melody matching in music libraries;
Extract background music corresponding with described melody at least one song described, and described background music and described singing voice are synthesized a song.
3. method according to claim 2, is characterized in that, extracts background music corresponding with described melody at least one song described, and described background music and described singing voice are synthesized a song comprises:
According to the pause in described singing voice or interval, melody section is carried out to described singing voice, obtain song section;
In at least one song described, search singer's sound that matching degree of cutting into slices with described song reaches setting value cut into slices;
According to the section of described singer's sound, corresponding background music of determining cut into slices with described singer's sound is cut into slices, and described background music is cut into slices and to be cut into slices as with described song corresponding background music of cutting into slices;
To cut into slices synthesis one song by the section of described song and with described song corresponding background music of cutting into slices.
4. method according to claim 3, is characterized in that, described background music section comprises absolute music section and cuts into slices with voice music;
Comprise by the section of described song and with described song corresponding background music synthesis one song of cutting into slices of cutting into slices:
Described absolute music section is inserted between adjacent song section;
According to sound size, speed and tone in the section of described song, regulate sound size, speed and tone that corresponding adjoint voice music of cut into slices with described song is cut into slices, and described song to be cut into slices and adjoint voice music after adjustment is cut into slices and is synthesized together.
5. method according to claim 4, is characterized in that, before the singing voice receiving user's input, also comprises:
Melody section is carried out to the every song in music libraries, determines the singer's sound section in every song, absolute music section and cut into slices with voice music.
6. method according to claim 1, is characterized in that, according to described lyric characters, comprises for described singing voice matching background music generates a song:
According to described lyric characters, by large data engine, in music libraries, search for the music word mated with described lyric characters;
According to described music word, determine at least one song corresponding with described music word;
Extract background music corresponding with described music word at least one song described, and described background music and described singing voice are synthesized a song.
7. method according to claim 1, is characterized in that, according to described melody, comprises for described singing voice matching background music generates a song:
According to described melody, drive analog instruments generation background music;
Described singing voice and described background music are synthesized a song, and preserves described song.
8. method according to claim 7, is characterized in that, described singing voice and described background music is being synthesized a song, and after preserving described song, is also comprising:
Play described song;
Receive tempo class audio and/or harmony that user is the definition of described song.
9. method according to claim 7, is characterized in that, described analog instruments comprises simulation piano, simulation violin, simulation flute or simulation vertical bamboo flute.
10. be the device that singing voice is dubbed in background music, it is characterized in that, described device comprises:
Song receiver module, for receiving the singing voice of user's input;
Sound identification module, for carrying out speech recognition to described singing voice, obtains the melody corresponding with described singing voice or lyric characters;
Song synthesis module, for according to described melody or lyric characters, generates a song for described singing voice matching background music or determines that corresponding accompaniment is with and recommends user.
11. devices according to claim 10, is characterized in that, described song synthesis module comprises:
Song search unit, for according to described melody, by large data engine, at least one song of search and described melody matching in music libraries;
First song synthesis unit, for extracting background music corresponding with described melody at least one song described, and synthesizes a song by described background music and described singing voice.
12. devices according to claim 11, is characterized in that, described song synthesis unit comprises:
Melody section subelement, for according to the pause in described singing voice or interval, carries out melody section to described singing voice, obtains song section;
Singer's sound searches subelement, and the singer's sound reaching setting value for searching matching degree of cutting into slices with described song at least one song described is cut into slices;
Background music determination subelement, for according to the section of described singer's sound, corresponding background music of determining cut into slices with described singer's sound is cut into slices, and described background music is cut into slices and to be cut into slices as with described song corresponding background music of cutting into slices;
Song synthon unit, for cutting into slices synthesis one song by the section of described song and with described song corresponding background music of cutting into slices.
13. devices according to claim 12, is characterized in that, described background music section comprises absolute music section and cuts into slices with voice music;
Described song synthon unit specifically for:
Described absolute music section is inserted between adjacent song section;
According to sound size, speed and tone in the section of described song, regulate sound size, speed and tone that corresponding adjoint voice music of cut into slices with described song is cut into slices, and described song to be cut into slices and adjoint voice music after adjustment is cut into slices and is synthesized together.
14. devices according to claim 10, is characterized in that, described song synthesis module comprises:
Music text search unit, for according to described lyric characters, by large data engine, searches for the music word mated with described lyric characters in music libraries;
Song determining unit, for according to described music word, determines at least one song corresponding with described music word;
Second song synthesis unit, for extracting background music corresponding with described music word at least one song described, and synthesizes a song by described background music and described singing voice.
15. devices according to claim 10, is characterized in that, described song synthesis module comprises:
Background music generation unit, for according to described melody, drives analog instruments generation background music;
3rd song synthesis unit, for described singing voice and described background music are synthesized a song, and preserves described song.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510535602.1A CN105070283B (en) | 2015-08-27 | 2015-08-27 | The method and apparatus dubbed in background music for singing voice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510535602.1A CN105070283B (en) | 2015-08-27 | 2015-08-27 | The method and apparatus dubbed in background music for singing voice |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105070283A true CN105070283A (en) | 2015-11-18 |
| CN105070283B CN105070283B (en) | 2019-07-09 |
Family
ID=54499636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510535602.1A Active CN105070283B (en) | 2015-08-27 | 2015-08-27 | The method and apparatus dubbed in background music for singing voice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105070283B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740394A (en) * | 2016-01-27 | 2016-07-06 | 广州酷狗计算机科技有限公司 | Music generation method, terminal, and server |
| CN106652997A (en) * | 2016-12-29 | 2017-05-10 | 腾讯音乐娱乐（深圳）有限公司 | Audio synthesis method and terminal |
| CN106652984A (en) * | 2016-10-11 | 2017-05-10 | 张文铂 | Automatic song creation method via computer |
| CN107786427A (en) * | 2017-09-28 | 2018-03-09 | 努比亚技术有限公司 | A kind of information interacting method, terminal and computer-readable recording medium |
| CN107799119A (en) * | 2016-09-07 | 2018-03-13 | 中兴通讯股份有限公司 | Audio preparation method, apparatus and system |
| CN108090081A (en) * | 2016-11-22 | 2018-05-29 | 百度在线网络技术（北京）有限公司 | A kind of content recommendation method and device |
| CN108172210A (en) * | 2018-02-01 | 2018-06-15 | 福州大学 | A kind of performance harmony generation method based on song rhythm |
| CN108182227A (en) * | 2017-12-27 | 2018-06-19 | 广州酷狗计算机科技有限公司 | Audio accompaniment recommends method, apparatus and computer readable storage medium |
| CN108242238A (en) * | 2018-01-11 | 2018-07-03 | 广东小天才科技有限公司 | A kind of audio file generation method and device, terminal device |
| WO2018121368A1 (en) * | 2016-12-30 | 2018-07-05 | 阿里巴巴集团控股有限公司 | Method for generating music to accompany lyrics and related apparatus |
| CN108428441A (en) * | 2018-02-09 | 2018-08-21 | 咪咕音乐有限公司 | Multimedia file producting method, electronic equipment and storage medium |
| CN108766409A (en) * | 2018-05-25 | 2018-11-06 | 中国传媒大学 | A kind of opera synthetic method, device and computer readable storage medium |
| CN109979497A (en) * | 2017-12-28 | 2019-07-05 | 阿里巴巴集团控股有限公司 | Generation method, device and system and the data processing and playback of songs method of song |
| CN110634465A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Music matching method, mobile terminal, data processing method and music matching system |
| CN110634464A (en) * | 2018-06-21 | 2019-12-31 | 卡西欧计算机株式会社 | Electronic musical instrument, control method for electronic musical instrument, and storage medium |
| CN110706679A (en) * | 2019-09-30 | 2020-01-17 | 维沃移动通信有限公司 | Audio processing method and electronic equipment |
| CN110910861A (en) * | 2019-11-20 | 2020-03-24 | 西安音乐学院 | Automatic accompaniment system for carrying out accurate matching by utilizing internet big data |
| CN111276115A (en) * | 2020-01-14 | 2020-06-12 | 孙志鹏 | Cloud beat |
| CN111491211A (en) * | 2020-04-17 | 2020-08-04 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
| CN111554267A (en) * | 2020-04-23 | 2020-08-18 | 北京字节跳动网络技术有限公司 | Audio synthesis method and device, electronic equipment and computer readable medium |
| CN111916039A (en) * | 2019-05-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Music file processing method, device, terminal and storage medium |
| CN112185321A (en) * | 2019-06-14 | 2021-01-05 | 微软技术许可有限责任公司 | Song generation |
| CN112420003A (en) * | 2019-08-22 | 2021-02-26 | 北京峰趣互联网信息服务有限公司 | Method and device for generating accompaniment, electronic equipment and computer-readable storage medium |
| CN112489607A (en) * | 2019-08-22 | 2021-03-12 | 北京峰趣互联网信息服务有限公司 | Method and device for recording songs, electronic equipment and readable storage medium |
| CN112712783A (en) * | 2020-12-21 | 2021-04-27 | 北京百度网讯科技有限公司 | Method and apparatus for generating music, computer device and medium |
| CN113593505A (en) * | 2020-04-30 | 2021-11-02 | 北京破壁者科技有限公司 | Voice processing method and device and electronic equipment |
| CN112185321B (en) * | 2019-06-14 | 2024-05-31 | 微软技术许可有限责任公司 | Song generation |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1031290A (en) * | 1988-06-16 | 1989-02-22 | 王贺新 | Intelligence is accompaniment vocal accompaniment microphone (acoustic control musical instrument) automatically |
| JP2000221969A (en) * | 1999-01-28 | 2000-08-11 | Yamaha Corp | Musical composition generating device and recording medium for recording musical composition generating program |
| CN1441401A (en) * | 2003-04-16 | 2003-09-10 | 陈汉翔 | Sound controlled electronic organ |
| US20060185504A1 (en) * | 2003-03-20 | 2006-08-24 | Sony Corporation | Singing voice synthesizing method, singing voice synthesizing device, program, recording medium, and robot |
| CN1940926A (en) * | 2006-03-15 | 2007-04-04 | 中国人民大学 | Efficient musical database query method based on humming |
| CN101313477A (en) * | 2005-12-21 | 2008-11-26 | Lg电子株式会社 | Music generating device and operating method thereof |
| CN103885949A (en) * | 2012-12-19 | 2014-06-25 | 中国科学院声学研究所 | Song searching system and method based on lyrics |
| CN103902642A (en) * | 2012-12-21 | 2014-07-02 | 香港科技大学 | Music composition system using correlation between melody and lyrics |
| CN104391980A (en) * | 2014-12-08 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Song generating method and device |
-
2015
- 2015-08-27 CN CN201510535602.1A patent/CN105070283B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1031290A (en) * | 1988-06-16 | 1989-02-22 | 王贺新 | Intelligence is accompaniment vocal accompaniment microphone (acoustic control musical instrument) automatically |
| JP2000221969A (en) * | 1999-01-28 | 2000-08-11 | Yamaha Corp | Musical composition generating device and recording medium for recording musical composition generating program |
| US20060185504A1 (en) * | 2003-03-20 | 2006-08-24 | Sony Corporation | Singing voice synthesizing method, singing voice synthesizing device, program, recording medium, and robot |
| CN1441401A (en) * | 2003-04-16 | 2003-09-10 | 陈汉翔 | Sound controlled electronic organ |
| CN101313477A (en) * | 2005-12-21 | 2008-11-26 | Lg电子株式会社 | Music generating device and operating method thereof |
| CN1940926A (en) * | 2006-03-15 | 2007-04-04 | 中国人民大学 | Efficient musical database query method based on humming |
| CN103885949A (en) * | 2012-12-19 | 2014-06-25 | 中国科学院声学研究所 | Song searching system and method based on lyrics |
| CN103902642A (en) * | 2012-12-21 | 2014-07-02 | 香港科技大学 | Music composition system using correlation between melody and lyrics |
| CN104391980A (en) * | 2014-12-08 | 2015-03-04 | 百度在线网络技术（北京）有限公司 | Song generating method and device |
Non-Patent Citations (2)
| Title |
|---|
| 李明: "中科院声学所推出基于哼唱旋律或口说歌词的歌曲检索系统", 《应用声学》 * |
| 梁越: "《多媒体技术应用教程 第2版》", 30 September 2012 * |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740394A (en) * | 2016-01-27 | 2016-07-06 | 广州酷狗计算机科技有限公司 | Music generation method, terminal, and server |
| CN107799119A (en) * | 2016-09-07 | 2018-03-13 | 中兴通讯股份有限公司 | Audio preparation method, apparatus and system |
| CN106652984B (en) * | 2016-10-11 | 2020-06-02 | 张文铂 | Method for automatically composing songs by using computer |
| CN106652984A (en) * | 2016-10-11 | 2017-05-10 | 张文铂 | Automatic song creation method via computer |
| CN108090081A (en) * | 2016-11-22 | 2018-05-29 | 百度在线网络技术（北京）有限公司 | A kind of content recommendation method and device |
| CN106652997A (en) * | 2016-12-29 | 2017-05-10 | 腾讯音乐娱乐（深圳）有限公司 | Audio synthesis method and terminal |
| WO2018121368A1 (en) * | 2016-12-30 | 2018-07-05 | 阿里巴巴集团控股有限公司 | Method for generating music to accompany lyrics and related apparatus |
| CN108268530B (en) * | 2016-12-30 | 2022-04-29 | 阿里巴巴集团控股有限公司 | Lyric score generation method and related device |
| CN108268530A (en) * | 2016-12-30 | 2018-07-10 | 阿里巴巴集团控股有限公司 | Dub in background music generation method and the relevant apparatus of a kind of lyrics |
| CN107786427A (en) * | 2017-09-28 | 2018-03-09 | 努比亚技术有限公司 | A kind of information interacting method, terminal and computer-readable recording medium |
| CN108182227A (en) * | 2017-12-27 | 2018-06-19 | 广州酷狗计算机科技有限公司 | Audio accompaniment recommends method, apparatus and computer readable storage medium |
| CN108182227B (en) * | 2017-12-27 | 2020-11-03 | 广州酷狗计算机科技有限公司 | Accompanying audio recommendation method and device and computer-readable storage medium |
| CN109979497A (en) * | 2017-12-28 | 2019-07-05 | 阿里巴巴集团控股有限公司 | Generation method, device and system and the data processing and playback of songs method of song |
| CN108242238A (en) * | 2018-01-11 | 2018-07-03 | 广东小天才科技有限公司 | A kind of audio file generation method and device, terminal device |
| CN108242238B (en) * | 2018-01-11 | 2019-12-31 | 广东小天才科技有限公司 | Audio file generation method and device and terminal equipment |
| CN108172210B (en) * | 2018-02-01 | 2021-03-02 | 福州大学 | Singing harmony generation method based on singing voice rhythm |
| CN108172210A (en) * | 2018-02-01 | 2018-06-15 | 福州大学 | A kind of performance harmony generation method based on song rhythm |
| CN108428441A (en) * | 2018-02-09 | 2018-08-21 | 咪咕音乐有限公司 | Multimedia file producting method, electronic equipment and storage medium |
| CN108428441B (en) * | 2018-02-09 | 2021-08-06 | 咪咕音乐有限公司 | Multimedia file generation method, electronic device and storage medium |
| CN108766409A (en) * | 2018-05-25 | 2018-11-06 | 中国传媒大学 | A kind of opera synthetic method, device and computer readable storage medium |
| CN110634464A (en) * | 2018-06-21 | 2019-12-31 | 卡西欧计算机株式会社 | Electronic musical instrument, control method for electronic musical instrument, and storage medium |
| CN110634465A (en) * | 2018-06-25 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Music matching method, mobile terminal, data processing method and music matching system |
| US11514923B2 (en) | 2019-05-08 | 2022-11-29 | Beijing Bytedance Network Technology Co., Ltd. | Method and device for processing music file, terminal and storage medium |
| CN111916039A (en) * | 2019-05-08 | 2020-11-10 | 北京字节跳动网络技术有限公司 | Music file processing method, device, terminal and storage medium |
| CN112185321B (en) * | 2019-06-14 | 2024-05-31 | 微软技术许可有限责任公司 | Song generation |
| CN112185321A (en) * | 2019-06-14 | 2021-01-05 | 微软技术许可有限责任公司 | Song generation |
| CN112489607A (en) * | 2019-08-22 | 2021-03-12 | 北京峰趣互联网信息服务有限公司 | Method and device for recording songs, electronic equipment and readable storage medium |
| CN112420003A (en) * | 2019-08-22 | 2021-02-26 | 北京峰趣互联网信息服务有限公司 | Method and device for generating accompaniment, electronic equipment and computer-readable storage medium |
| CN110706679B (en) * | 2019-09-30 | 2022-03-29 | 维沃移动通信有限公司 | Audio processing method and electronic equipment |
| CN110706679A (en) * | 2019-09-30 | 2020-01-17 | 维沃移动通信有限公司 | Audio processing method and electronic equipment |
| CN110910861A (en) * | 2019-11-20 | 2020-03-24 | 西安音乐学院 | Automatic accompaniment system for carrying out accurate matching by utilizing internet big data |
| CN111276115A (en) * | 2020-01-14 | 2020-06-12 | 孙志鹏 | Cloud beat |
| CN111491211A (en) * | 2020-04-17 | 2020-08-04 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
| CN111491211B (en) * | 2020-04-17 | 2022-01-28 | 维沃移动通信有限公司 | Video processing method, video processing device and electronic equipment |
| CN111554267A (en) * | 2020-04-23 | 2020-08-18 | 北京字节跳动网络技术有限公司 | Audio synthesis method and device, electronic equipment and computer readable medium |
| CN113593505A (en) * | 2020-04-30 | 2021-11-02 | 北京破壁者科技有限公司 | Voice processing method and device and electronic equipment |
| CN112712783A (en) * | 2020-12-21 | 2021-04-27 | 北京百度网讯科技有限公司 | Method and apparatus for generating music, computer device and medium |
| CN112712783B (en) * | 2020-12-21 | 2023-09-29 | 北京百度网讯科技有限公司 | Method and device for generating music, computer equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105070283B (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105070283B (en) | The method and apparatus dubbed in background music for singing voice | |
| US9659572B2 (en) | Apparatus, process, and program for combining speech and audio data | |
| CN101901595B (en) | Method and system for generating animation according to audio music | |
| CN106023969B (en) | Method for applying audio effects to one or more tracks of a music compilation | |
| CN104170006B (en) | Performance evaluation device, karaoke device, and server device | |
| Dittmar et al. | Music information retrieval meets music education | |
| CN103959372A (en) | System and method for providing audio for a requested note using a render cache | |
| Sewell | A typology of sampling in hip-hop | |
| CN102576524A (en) | System and method of receiving, analyzing, and editing audio to create musical compositions | |
| CN108268530B (en) | Lyric score generation method and related device | |
| US20060112812A1 (en) | Method and apparatus for adapting original musical tracks for karaoke use | |
| CN109326280B (en) | Singing synthesis method and device and electronic equipment | |
| Harkins | Microsampling: From Akufen's Microhouse to Todd Edwards and the Sound of UK Garage | |
| Rideout | Keyboard presents the evolution of electronic dance music | |
| Hutchings | Talking Drums: Generating drum grooves with neural networks | |
| JP4479701B2 (en) | Music practice support device, dynamic time alignment module and program | |
| JP2012088402A (en) | Information processor, information processing method, and program | |
| CN113178182A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| JP5311069B2 (en) | Singing evaluation device and singing evaluation program | |
| CN101488128B (en) | Music search method and system based on rhythm mark | |
| JP2015060200A (en) | Musical performance data file adjustment device, method, and program | |
| JP2008040260A (en) | Musical piece practice assisting device, dynamic time warping module, and program | |
| JP6459162B2 (en) | Performance data and audio data synchronization apparatus, method, and program | |
| JP6219750B2 (en) | Singing battle karaoke system | |
| Santiaji | Learning Electric Bass Techniques in the Funk Genre Using Minus One |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |