CN105070283B - The method and apparatus dubbed in background music for singing voice - Google Patents
The method and apparatus dubbed in background music for singing voice Download PDFInfo
- Publication number
- CN105070283B CN105070283B CN201510535602.1A CN201510535602A CN105070283B CN 105070283 B CN105070283 B CN 105070283B CN 201510535602 A CN201510535602 A CN 201510535602A CN 105070283 B CN105070283 B CN 105070283B
- Authority
- CN
- China
- Prior art keywords
- song
- slice
- music
- singing voice
- melody
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of method and apparatus dubbed in background music for singing voice.This method comprises: receiving the singing voice of user's input；Speech recognition is carried out to the singing voice, obtains melody corresponding with the singing voice or lyric characters；According to the melody or lyric characters, a song is generated for the singing voice matching background music or determines corresponding accompaniment band and recommends user.The present invention compared with the existing technology in the background music that follows directly after sing, improve interest, and can sufficiently excavate the creativeness and property of participation of user.
Description
Technical field
The present embodiments relate to network technology more particularly to a kind of method and apparatus dubbed in background music for singing voice.
Background technique
As communication and the high speed development of information technology, music function have become one in the terminals such as computer or mobile phone
The indispensable application of item.
Music class product in the prior art is mostly that the corresponding song of user's selection plays out or user selects
It selects corresponding musical background and musical background and subtitle is followed to be sung, in social formal, the song that user can will sing
Song is shared onto social network sites.Have a drawback in that it is relatively simple with user interaction mode, lack interest, cannot sufficiently send out
Dig 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 dubbed in background music for singing voice, to improve interest.
In a first aspect, the embodiment of the invention provides a kind of methods dubbed in background music for singing voice, which comprises
Receive the singing voice of user's input；
Speech recognition is carried out to the singing voice, obtains melody corresponding with the singing voice or lyric characters；
According to the melody or lyric characters, a song is generated for the singing voice matching background music or determines phase
The accompaniment band answered simultaneously recommends user.
Second aspect, the embodiment of the invention also provides a kind of device dubbed in background music for singing voice, described device includes:
Song receiving module, for receiving the singing voice of user's input；
Speech recognition module obtains corresponding with the singing voice for carrying out speech recognition to the singing voice
Melody or lyric characters；
Song synthesis module, for being that the singing voice matching background music is raw according to the melody or lyric characters
At a song or determines corresponding accompaniment band and recommend user.
The method and apparatus provided in an embodiment of the present invention dubbed in background music for singing voice, by being according to the singing voice of user
The singing voice adds background music, or recommends corresponding accompaniment band to user.The embodiment of the present invention is relative to existing skill
The background music that follows directly after in art is sung, and interest is improved, and can sufficiently excavate the creativeness and ginseng of user
With property.
Detailed description of the invention
Fig. 1 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention one provides；
Fig. 2 is a kind of flow chart of method dubbed in background music for singing voice provided by Embodiment 2 of the present invention；
Fig. 3 is the extraction background music in the method provided in an embodiment of the present invention dubbed in background music for singing voice and by background sound
The happy flow chart that song is synthesized with singing voice；
Fig. 4 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention three provides；
Fig. 5 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention four provides；
Fig. 6 is a kind of structural schematic diagram for device dubbed in background music for singing voice that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
In description, only some but not all contents related to the present invention are shown in the drawings.
Embodiment one
Fig. 1 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention one provides, and the present embodiment can
The case where suitable for one section of singing voice being inputted according to user being user's matching background music, this method can by computer or
The terminals such as mobile phone execute, and specifically include as follows:
S110 receives the singing voice of user's input.
In order to sufficiently excavate the creativeness and property of participation of user, one section or song matching background being sung for user
Music makes one section or a first full songs with background music.In order to realize such function, first have to pass through words
Cylinder receives one section of user's input or the singing voice of a song.
S120 carries out speech recognition to the singing voice, obtains melody corresponding with the singing voice or lyrics text
Word.
Speech recognition is carried out to the singing voice using speech recognition system, to identify the rotation in the singing voice
Rule or the corresponding lyric characters of the singing voice.
Speech recognition technology is to allow machine that voice signal is changed into corresponding text or life by identification and understanding process
The high-tech of order, speech recognition technology mainly include three Feature Extraction Technology, pattern match criterion and model training technology sides
Face.
S130, according to the melody or lyric characters, for the singing voice matching background music generate a song or
It determines corresponding accompaniment band and recommends user.
According to the melody or lyric characters, song corresponding with the melody or lyric characters is searched in music libraries,
And background music corresponding with the melody or lyric characters is extracted in the song, according in the singing voice of user
The singing voice is synthesized a song with the background music by the corresponding relationship of melody or lyric characters and background music.
Singer's sound corresponding in the song can also be removed according to the song searched in music libraries, thus
Corresponding accompaniment band is obtained, which is recommended into user, for example, which first song can inform that user sings is, and recommends to use
It is sung using accompaniment band at family.
The present embodiment is by carrying out speech recognition to the singing voice, obtaining after receiving the singing voice of user
Melody corresponding with the singing voice or lyric characters are matched according to the melody or lyric characters for the singing voice
Background music generates a song or determines corresponding accompaniment band and recommend user, is the song according to the singing voice of user
Sound voice is added to background music.The embodiment of the present invention improves interest, and can sufficiently excavate user creativeness with
Property of participation gives full play to the property of participation of user, yields to user, rather than user removes cooperation background music；When user at will sings
After one section of song, background music can be added for user automatically, promote the satisfaction and sense of accomplishment of user；Like the use of practical joke
Family, each sentence may all be different song, through the embodiment of the present invention in method can be its synthesize a song, increase
Interest；For the singing voice according to user, after synthesizing song for user, user can share the works of oneself to society
It hands in website, browses comment for the friend of oneself.
Embodiment two
Fig. 2 is a kind of flow chart of method dubbed in background music for singing voice provided by Embodiment 2 of the present invention, the present embodiment pair
In embodiment one according to the melody, generate a song for the singing voice matching background music and be optimized, tool
Body includes the following:
S210 receives the singing voice of user's input.
S220 carries out speech recognition to the singing voice, obtains melody corresponding with the singing voice.
The present embodiment is according to melody search and the matched song of singing voice in singing voice, and therefore, this step is passed through
Speech recognition obtains melody corresponding with the singing voice.
S230, by big data engine, searches at least one with the melody matching according to the melody in music libraries
Song.
Wherein, big data engine refers to being collected big data, store, calculate, excavate and managing, and passes through depth
Learning art and data modeling technique make data have " intelligence ".Such as Baidu's big data engine, Baidu's big data engine is mainly wrapped
Containing three big components: open cloud, data factory and Baidu's brain.
The song files for largely having purchased copyright are contained in music libraries, the song files can be covered all substantially
The music of type is searched in music libraries by big data engine, in search, is gone in matching music libraries according to the melody
The melody of song, when matching degree reaches setting value, it is believed that this song song is the song with the melody matching.
Wherein, singing voice may be that one section in a certain song that user sings or one are whole, it is also possible to each
Word is respectively from different songs or other situations.Therefore, above-mentioned to be searched in music libraries and the melody matching
Song may search at least one song.
It is of course also possible to the mode of a song or number of songs is selected by user, thus when being searched in music libraries,
Corresponding song can be matched for user according to the mode that user selects.When user selects the mode of a song, in music
Search one and the highest song of singing voice matching degree in library；When user selects the mode of number of songs, Ke Yigen
The every a bit of of the song in music libraries is matched per a bit of according in singing voice.
S240, extracts background music corresponding with the melody at least one described song, and by the background music
A song is synthesized with the singing voice.
Background music corresponding with the melody at least one described song is extracted respectively, by the background sound
It is happy be added to and singer's voice in melody corresponding with the background music, thus by the background music and the song
One song of sound speech synthesis.
Specifically, Fig. 3 be extraction background music in the method provided in an embodiment of the present invention dubbed in background music for singing voice simultaneously
Background music is synthesized to the flow chart of song with singing voice, as shown in figure 3, extract at least one described song with the rotation
Restrain corresponding background music, and the background music synthesized with the singing voice song preferably include it is as follows:
S241, according in the singing voice pause or interval, to the singing voice carry out melody slice, sung
Sound slice；
S242 searches the singer's sound for reaching setting value with song slice matching degree at least one described song
Slice；
The singing voice of user is different surely completely the same with the melody of singer's sound in song, therefore, will with it is described
Singer's sound slice that the matching degree of song slice reaches setting value is considered to be sliced the singer's sound being consistent with the song of user
Sound slice.
S243 is sliced according to singer's sound, determines background music slice corresponding with singer's sound slice, institute
Background music slice is stated to be sliced as background music corresponding with song slice；
The song is sliced and background music corresponding with song slice slice synthesizes a song by S244.
Wherein, the background music slice preferably includes absolute music slice and is sliced with voice music；
The song is sliced and one song of background music corresponding with song slice slice synthesis preferably includes:
Absolute music slice is inserted between adjacent song slice；
According to sound size, speed and the tone in song slice, adjust corresponding adjoint with song slice
Sound size, speed and the tone of voice music slice, and the song is sliced and is sliced with the adjoint voice music after adjusting
It is synthesized together.
Wherein, absolute music slice refers to the background music in the pause between singer's sound, is with voice music slice
Refer to the background music with singer's sound.Tone (key) is exactly to rise in musical works (or some part in a works)
The a group that the keynote of central role mutually works under dominating has the sound of certain altitude, and tune is consistent with scale.
According to sound size, speed and the tone in song slice, adjusts the song and be sliced corresponding adjoint people
Sound size, speed and the tone of the happy slice of sound are allowed to adapt to the song slice, after the song is sliced and is adjusted
It is synthesized together with voice music slice, the adjoint voice music slice is made to be known as the background music of the song slice.
Matched singer's sound is sliced with the song by searching in the song to singing voice slice and in music libraries
Sound slice, can be improved matching precision, so that the singing voice for user adds more accurate background music.
The present embodiment by receive user input singing voice after, to the singing voice carry out speech recognition,
Obtain melody corresponding with the singing voice, according to the melody, by big data engine, in music libraries search with it is described
At least one song of melody matching, extracts background music corresponding with the melody at least one described song, and by institute
It states background music and synthesizes a song with the singing voice, be that the singing voice adds according to the melody of the singing voice of user
Background music is added, has improved interest, and can sufficiently excavate the creativeness and property of participation of user, with one phase of embodiment
Than the present embodiment searches for matched song by big data engine according to the melody of singing voice in music libraries, can be improved
Search speed and precision.
Based on the above technical solution, before the singing voice for receiving user's input, further preferably include:
Melody slice is carried out to every song in music libraries, determines singer's sound slice, absolute music in every song
Slice and adjoint voice music are sliced.
One song is made of singer's sound and background music, and background music be further divided into absolute music part (such as
Music etc. when pausing between head, tail or every singer's sound) and with voice musical portions.Wherein, singer's sound can be with table
It is shown as Voice, background music is expressed as Bgm (Backgroundmusic), and absolute music is partially shown as PureBgm, with voice
Musical portions are expressed as VoiceBgm.
Arrangement division is carried out to the melody in music libraries by big data engine, according in the music score of every song or song
Pause or interval song is sliced, determine every song singer's sound be sliced Voice1, Voice2 ..., VoiceN,
Absolute music is sliced PureBgm1, PuerBgm2 ..., PuerBgmN1 and adjoint voice music are sliced VoiceBgm1,
VoiceBgm2 ..., VoiceBgmN, wherein N indicates the quantity of singer's sound slice in a song or with voice music
The quantity of slice, N1 indicate the quantity of absolute music slice in a song.Generally, singer's sound slice is cut with voice music
Piece is one-to-one relationship, i.e., has a bit of adjoint voice background music per a bit of singer's sound, therefore, by singer's sound
The quantity of sound slice and the quantity of adjoint voice music slice are all indicated with N；In absolute music, and prelude and after play i.e. song
Head and tail part, more 1 of quantity than the quantity that song sound is sliced of absolute music slice.
As extension, after the above-mentioned song in music libraries is sliced, obtained slice can also be used for and user
Interactive game in, such as: play one of singer's sound slice and corresponding background music, user allowed to guess the song
Title etc.；One for can also being hummed according to user searches for matching singer's sound slice in music libraries, thus
To corresponding song, the ranking list of song is released according to similarity, or similarity judgement is carried out to any two songs works.
Embodiment three
Fig. 4 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention three provides, the present embodiment pair
In embodiment one according to the lyric characters, for the singing voice matching background music generate a song carried out it is excellent
Change, specifically include as follows:
S410 receives the singing voice of user's input.
S420 carries out speech recognition to the singing voice, obtains lyric characters corresponding with the singing voice.
The present embodiment is according to the lyric characters search and the matched song of singing voice, therefore, this step in singing voice
Lyric characters corresponding with the singing voice are obtained by speech recognition.
S430 is searched in music libraries and is matched with the lyric characters by big data engine according to the lyric characters
Music text.
It is searched in music libraries by big data engine, in search, is gone in matching music libraries according to the lyric characters
Song music text, when matching degree reaches setting value, it is believed that this song song is matched with the lyric characters
Song.
S440 determines at least one song corresponding with the music text according to the music text.
The music text may be the music text in a song, it is also possible to each music text respectively from
Different songs or other situations.Therefore, it according to the music text, can determine corresponding with the music text
At least one song.
S450, extracts background music corresponding with the music text at least one described song, and by the background
Music synthesizes a song with the singing voice.
It extracts background music or can mention background music according to corresponding in embodiment two with singing voice synthesis song
Mode or synthesis mode is taken to complete, which is not described herein again.
The present embodiment is by carrying out speech recognition to the singing voice and obtaining after the singing voice for receiving user's input
Lyric characters corresponding with the singing voice, according to the lyric characters, searched in music libraries by big data engine with
The matched music text of lyric characters determines at least one song corresponding with the music text according to the music text
Song, extracts background music corresponding with the music text at least one described song, and by Beijing music and described
Singing voice synthesizes a song, is that the singing voice is added to background sound according to the lyric characters in the singing voice of user
It is happy, interest is improved, and can sufficiently excavate the creativeness and property of participation of user, compared with embodiment one, the present embodiment
Matched song is searched in music libraries by big data engine according to the lyric characters in singing voice, search speed can be improved
Degree and precision.
Example IV
Fig. 5 is a kind of flow chart for method dubbed in background music for singing voice that the embodiment of the present invention four provides, the present embodiment pair
In embodiment one according to the melody, generate a song for the singing voice matching background music and be optimized, tool
Body includes the following:
S510 receives the singing voice of user's input.
S520 carries out speech recognition to the singing voice, obtains melody corresponding with the singing voice.
In the present embodiment, according to the melody in singing voice, analog instruments is driven to generate background music, therefore, this step
Melody corresponding with the singing voice is obtained by speech recognition.
S530 drives analog instruments to generate background music according to the melody.
In the present embodiment, the singing voice of user, it may be possible to which user has come what interest was at will sung, is not a certain first song
Segment in song, therefore corresponding song can not be found in music libraries, analog instruments at this moment can be driven to generate background music,
It is that segment in certain song can also drive analog instruments to generate background music even if the singing voice of user.It is simulated in driving
Musical instrument generate background music when, according to the melody, automatically generate with the matched music score of the singing voice, driven according to music score
Musical instrument generates background music.For example, analog instruments can be driven to generate piano version, violin version, whistling version, vertical bamboo flute sound version, mention greatly
Qin version, guitar version or Chinese lute version etc..Wherein, the analog instruments include simulation piano, simulation violin, simulation flute or simulation
It is desolate, it can also include simulation violoncello, simulation guitar or simulation Chinese lute etc..
Alternatively, it is also possible to generating the background music of different editions according to membership grade, such as: it, can be with for primary member
Only piano version；For advanced member, can have piano version, violin version, whistling version, vertical bamboo flute sound version, violoncello version, guitar version or
Chinese lute version etc..
The singing voice and the background music are synthesized a song, and save the song by S540.
It is generated when the background music according to singing voice, during generating background music, directly by song language
Sound is synthesized with background music, eventually becomes a complete song, and save to the song, in order to user's receipts
Listen the works of oneself.
The present embodiment receive user input singing voice after, to the singing voice carry out speech recognition obtain with
The corresponding melody of the singing voice drives analog instruments to generate background music according to the melody, by the singing voice and
The background music synthesizes a song, and saves the song, is the song language according to the melody of the singing voice of user
Sound generates background music, interest is improved, and can sufficiently excavate the creativeness and property of participation of user, with one phase of embodiment
Than it is that the singing voice generates background music that the present embodiment, which can drive analog instruments according to the melody of singing voice, more
The creativeness of user can be excited.
Based on the above technical solution, the singing voice and the background music are being synthesized into a song, and
After saving the song, further preferably include:
Play the song；
Receiving user is the tempo class audio and/or harmony that the song defines.
Play the song, during playing the song, receive user to the customized addition of the song, repair
Multiple to wait operation, user can add bass, bucket drum equal rhythm class audio for the song, while can also add harmony, may be used also
To add the information such as one section of voice self-introduction in song beginning, in information such as song ending addition voice descriptions.
Wherein, harmony refers to the combined acoustics that two or more different sounds are constituted by certain rule while sounding, includes:
Chord is the basic material of harmony, by 3 or 3 or more different sounds, is stacked according to three degree or other methods are in combination with structure
At this is the vertical structure of harmony；Harmony carries out, and refers to the successive connection of each chord, this is the transverse movement of harmony.
Embodiment five
Fig. 6 is a kind of structural schematic diagram for device dubbed in background music for singing voice that the embodiment of the present invention five provides, such as Fig. 6 institute
Show, it be the device that singing voice is dubbed in background music includes song receiving module 610, speech recognition module 620 and song that this implementation is described
Synthesis module 630.
Wherein, song receiving module 610 is used to receive the singing voice of user's input；
Speech recognition module 620 is used to carry out speech recognition to the singing voice, obtains corresponding with the singing voice
Melody or lyric characters；
Song synthesis module 630 is used for according to the melody or lyric characters, is the singing voice matching background music
It generates a song or determines corresponding accompaniment band and recommend user.
Preferably, the song synthesis module includes:
Song search unit, for according to the melody, by big data engine, search and the melody in music libraries
At least one matched song；
First song synthesis unit, for extracting background music corresponding with the melody at least one described song,
And the background music is synthesized into a song with the singing voice.
Preferably, the song synthesis unit includes:
Melody be sliced subelement, for according in the singing voice pause or interval, to the singing voice carry out
Melody slice obtains song slice；
Singer's sound searches subelement, reaches for searching at least one described song with song slice matching degree
Singer's sound to setting value is sliced；
Background music determines subelement, for being sliced according to singer's sound, determining and singer's sound slice pair
The background music slice answered, the background music slice are sliced as background music corresponding with song slice；
Song synthesizing subunit, for by the song be sliced and background music corresponding with the song slice slice close
At a song.
Preferably, the background music slice includes absolute music slice and is sliced with voice music；
The song synthesizing subunit is specifically used for:
Absolute music slice is inserted between adjacent song slice；
According to sound size, speed and the tone in song slice, adjust corresponding adjoint with song slice
Sound size, speed and the tone of voice music slice, and the song is sliced and is sliced with the adjoint voice music after adjusting
It is synthesized together.
Preferably, the song synthesis module includes:
Music text search unit, for according to the lyric characters, by big data engine, in music libraries search with
The matched music text of lyric characters；
Song determination unit, for determining at least one song corresponding with the music text according to the music text
It is bent；
Second song synthesis unit, for extracting background sound corresponding with the music text at least one described song
It is happy, and the background music is synthesized into a song with the singing voice.
Preferably, the song synthesis module includes:
Background music generation unit, for driving analog instruments to generate background music according to the melody；
Third song synthesis unit for the singing voice and the background music to be synthesized a song, and saves
The song.
Method provided by any embodiment of the invention can be performed in the said goods, has the corresponding functional module of execution method
And beneficial effect.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (11)
1. a kind of method dubbed in background music for singing voice, which is characterized in that the described method includes:
Receive the singing voice of user's input；
Speech recognition is carried out to the singing voice, obtains melody corresponding with the singing voice；
According to the melody, a song is generated for the singing voice matching background music；
Wherein, according to the melody, a song is generated for the singing voice matching background music, comprising:
According in the singing voice pause or interval, to the singing voice carry out melody slice, obtain song slice；Its
In, background music slice corresponding with song slice includes absolute music slice and is sliced with voice music；
According to the melody, determines absolute music slice corresponding with song slice and be sliced with voice music；
Absolute music slice is inserted between adjacent song slice；
According to sound size, speed and the tone in song slice, adjoint voice corresponding with song slice is adjusted
Sound size, speed and the tone of music slice, and the song is sliced and is synthesized with the adjoint voice music slice after adjusting
Together.
2. the method according to claim 1, wherein determination is corresponding with song slice according to the melody
Absolute music slice and with voice music be sliced, comprising:
According to the melody, by big data engine, at least one song with the melody matching is searched in music libraries；
From at least one described song, extracts absolute music slice corresponding with song slice and cut with voice music
Piece.
3. according to the method described in claim 2, it is characterized in that, being extracted and the song from least one described song
It is sliced corresponding absolute music slice and is sliced with voice music, comprising:
The singer's sound for reaching setting value with song slice matching degree is searched at least one described song to be sliced；
It is sliced according to singer's sound, determines background music slice corresponding with song slice.
4. the method according to claim 1, wherein before the singing voice for receiving user's input, further includes:
Melody slice is carried out to every song in music libraries, determines singer's sound slice, absolute music slice in every song
It is sliced with voice music.
5. the method according to claim 1, wherein matching background according to the melody for the singing voice
Music generates a song
According to the melody, analog instruments is driven to generate background music；
The singing voice and the background music are synthesized into a song, and save the song.
6. according to the method described in claim 5, it is characterized in that, the singing voice and the background music are synthesized one
Song, and after saving the song, further includes:
Play the song；
Receiving user is the tempo class audio and/or harmony that the song defines.
7. according to the method described in claim 5, it is characterized in that, the analog instruments include simulation piano, simulation violin,
Simulate flute or simulation vertical bamboo flute.
8. a kind of device dubbed in background music for singing voice, which is characterized in that described device includes:
Song receiving module, for receiving the singing voice of user's input；
Speech recognition module obtains melody corresponding with the singing voice for carrying out speech recognition to the singing voice；
Song synthesis module, for generating a song for the singing voice matching background music according to the melody；
Wherein, the song synthesis module is specifically used for:
According in the singing voice pause or interval, to the singing voice carry out melody slice, obtain song slice；Its
In, background music slice corresponding with song slice includes absolute music slice and is sliced with voice music；
According to the melody, determines absolute music slice corresponding with song slice and be sliced with voice music；
Absolute music slice is inserted between adjacent song slice；
According to sound size, speed and the tone in song slice, adjoint voice corresponding with song slice is adjusted
Sound size, speed and the tone of music slice, and the song is sliced and is synthesized with the adjoint voice music slice after adjusting
Together.
9. device according to claim 8, which is characterized in that the song synthesis module is specifically used for:
According to the melody, by big data engine, at least one song with the melody matching is searched in music libraries；
From at least one described song, extracts absolute music slice corresponding with song slice and cut with voice music
Piece.
10. device according to claim 9, which is characterized in that the song synthesis module is specifically used for:
The singer's sound for reaching setting value with song slice matching degree is searched at least one described song to be sliced；
It is sliced according to singer's sound, determines background music slice corresponding with song slice.
11. device according to claim 8, which is characterized in that the song synthesis module includes:
Background music generation unit, for driving analog instruments to generate background music according to the melody；
Third song synthesis unit, for the singing voice and the background music to be synthesized a song, and described in preservation
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 CN105070283A (en) | 2015-11-18 |
| CN105070283B true 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) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740394B (en) * | 2016-01-27 | 2019-02-26 | 广州酷狗计算机科技有限公司 | Song 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 |
| 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 |
| CN106652997B (en) * | 2016-12-29 | 2020-07-28 | 腾讯音乐娱乐（深圳）有限公司 | Audio synthesis method and terminal |
| 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 |
| CN107786427B (en) * | 2017-09-28 | 2021-07-16 | 努比亚技术有限公司 | Information interaction method, terminal 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 |
| CN109979497B (en) * | 2017-12-28 | 2021-02-26 | 阿里巴巴集团控股有限公司 | Song generation method, device and system and data processing and song playing method |
| 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 |
| 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 |
| JP6610715B1 (en) * | 2018-06-21 | 2019-11-27 | カシオ計算機株式会社 | Electronic musical instrument, electronic musical instrument control method, and program |
| 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 |
| CN111916039B (en) | 2019-05-08 | 2022-09-23 | 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 |
| 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 |
| 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 |
| 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 |
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1441401A (en) * | 2003-04-16 | 2003-09-10 | 陈汉翔 | Sound controlled electronic organ |
| 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 |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1010814B (en) * | 1988-06-16 | 1990-12-12 | 王贺新 | Microphone with automatic musical instrument and vocal accompaniment by intellectual faculties sound-controlled |
| JP3633335B2 (en) * | 1999-01-28 | 2005-03-30 | ヤマハ株式会社 | Music generation apparatus and computer-readable recording medium on which music generation program is recorded |
| JP2004287099A (en) * | 2003-03-20 | 2004-10-14 | Sony Corp | Method and apparatus for singing synthesis, program, recording medium, and robot device |
| KR100658869B1 (en) * | 2005-12-21 | 2006-12-15 | 엘지전자 주식회사 | Music generating device and operating method thereof |
| US9620092B2 (en) * | 2012-12-21 | 2017-04-11 | The Hong Kong University Of Science And Technology | Composition using correlation between melody and lyrics |
| CN104391980B (en) * | 2014-12-08 | 2019-03-08 | 百度在线网络技术（北京）有限公司 | The method and apparatus for generating song |
-
2015
- 2015-08-27 CN CN201510535602.1A patent/CN105070283B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1441401A (en) * | 2003-04-16 | 2003-09-10 | 陈汉翔 | Sound controlled electronic organ |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 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;李明;《应用声学》;20060730;第25卷(第4期);第245页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105070283A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105070283B (en) | The method and apparatus dubbed in background music for singing voice | |
| US10229669B2 (en) | Apparatus, process, and program for combining speech and audio data | |
| Dittmar et al. | Music information retrieval meets music education | |
| Humphrey et al. | An introduction to signal processing for singing-voice analysis: High notes in the effort to automate the understanding of vocals in music | |
| JP2018537727A (en) | Automated music composition and generation machines, systems and processes employing language and / or graphical icon based music experience descriptors | |
| Mawer | French Music and Jazz in Conversation | |
| CN103959372A (en) | System and method for providing audio for a requested note using a render cache | |
| CN104040618A (en) | System and method for producing a more harmonious musical accompaniment and for applying a chain of effects to a musical composition | |
| Osborn | Beyond verse and chorus:* Experimental formal structure in post-millennial rock music | |
| Hutchings | Talking Drums: Generating drum grooves with neural networks | |
| Harkins | Microsampling: From Akufen's Microhouse to Todd Edwards and the Sound of UK Garage | |
| Rideout | Keyboard presents the evolution of electronic dance music | |
| JP2012088402A (en) | Information processor, information processing method, and program | |
| JP2015060200A (en) | Musical performance data file adjustment device, method, and program | |
| JP6459162B2 (en) | Performance data and audio data synchronization apparatus, method, and program | |
| Heetderks | Hardcore R e‐visioned: Reading and Misreading in Sonic Youth, 1987–8 | |
| JP6439239B2 (en) | Performance data file search method, system, program, terminal device, and server device | |
| Santiaji | Learning Electric Bass Techniques in the Funk Genre Using Minus One | |
| Köküer et al. | Curating and annotating a collection of traditional Irish flute recordings to facilitate stylistic analysis | |
| Ptacin | An annotated bibliography of works for solo marimba and electronics published from 1978-2012 | |
| Musib | Sound print as an identification tool | |
| Hutchison | Hammond B3 Organ Trios and Soul Jazz 1955-1965 | |
| Sudirana | Bali Fusion Pop Music | |
| Estes | Solo and Chamber Percussion Works by Nigel Westlake: An Examination of" Fabian Theory"," The Hinchinbrook Riffs"," The Invisible Men"," Kalabash"," Malachite Glass"," Moving Air"," Omphalo Centric Lecture" and" Penguin Circus" | |
| Brodbeck | “You Don’t Just Stick It Together”: The Beach Boys and the Beatles in the Mid-1960s |
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 |