[go: up one dir, main page]

CN105740394A - Music generation method, terminal, and server - Google Patents

Music generation method, terminal, and server Download PDF

Info

Publication number
CN105740394A
CN105740394A CN201610057485.7A CN201610057485A CN105740394A CN 105740394 A CN105740394 A CN 105740394A CN 201610057485 A CN201610057485 A CN 201610057485A CN 105740394 A CN105740394 A CN 105740394A
Authority
CN
China
Prior art keywords
information
musical instrument
music
lyrics
chinese operas
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
Application number
CN201610057485.7A
Other languages
Chinese (zh)
Other versions
CN105740394B (en
Inventor
姚俊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Kugou Computer Technology Co Ltd
Original Assignee
Guangzhou Kugou Computer Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Kugou Computer Technology Co Ltd filed Critical Guangzhou Kugou Computer Technology Co Ltd
Priority to CN201610057485.7A priority Critical patent/CN105740394B/en
Publication of CN105740394A publication Critical patent/CN105740394A/en
Application granted granted Critical
Publication of CN105740394B publication Critical patent/CN105740394B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/685—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using automatically derived transcript of audio data, e.g. lyrics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Electrophonic Musical Instruments (AREA)

Abstract

The present invention discloses a music generation method, a terminal, and a server, and belongs to the technical field of audio processing. The method comprises: receiving lyric information of a to-be-generated target song; carrying out feature extraction on the lyric information to obtain feature words; sending a song information obtaining request to the server, wherein the feature words are carried in the song information obtaining request, so as to make the server based on the feature words return a score and background music of the target song; and when receiving the score and background music sent by the server, generating the target song based on a specified tone, the lyric, the score and the background music. The method, the terminal and the server disclosed by the present invention reduce user involvement, simplify song generation operations, and improve song generation efficiency.

Description

Song generates method, terminal and server
Technical field
The present invention relates to audio signal processing technique field, generate method, terminal and server particularly to a kind of song.
Background technology
In the modern life, for the job morale of keeping tensions down, a lot of users like when the leisure listening to some songs.Wherein, the song that user listens to is typically all what composer issued on the internet, and composer issues before song on the internet, generally requires the music score of Chinese operas based on this song and the lyrics generate this song.
At present, the music score of Chinese operas of song and the lyrics are substantially composer and are performed manually by creation, afterwards, some singers sing based on this music score of Chinese operas and the lyrics, and record in the process sung, thus generating this song.
But, owing to the music score of Chinese operas of song is to be performed manually by creation by composer, and also it is carried out performance by some singers based on the music score of Chinese operas and the lyrics to obtain when generating this song, what artificially participate in is more, complicated operation, reduces the efficiency generating song.
Summary of the invention
In order to solve problem of the prior art, embodiments provide a kind of song and generate method, terminal and server.Described technical scheme is as follows:
First aspect, it is provided that a kind of song generates method, and described method includes:
Receive the lyrics information of target song to be generated；
Described lyrics information is carried out feature extraction, obtains Feature Words；
Sending song information to server and obtain request, described song information obtains in request and carries described Feature Words, makes described server return the music score of Chinese operas and the background music of described target song based on described Feature Words；
When receiving the music score of Chinese operas and the background music that described server sends, based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, generate described target song.
Alternatively, described described lyrics information is carried out feature extraction, obtain Feature Words, including:
Judge whether described lyrics information is text message；
When described lyrics information is text message, described lyrics information is carried out feature extraction, obtain described Feature Words；
When described lyrics information is not text message, described lyrics information is carried out text conversion, obtain lyrics text message；
Described lyrics text message is carried out feature extraction, obtains described Feature Words.
Alternatively, described generate described target song based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, including:
Based on the music score of Chinese operas described in described designated tone normal complexion, described lyrics information is converted to lyrics audio-frequency information；
Described lyrics audio-frequency information and described background music are combined, obtain described target song.
Alternatively, described based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, before generating described target song, also include:
When receiving tone color and determining instruction, show that multiple tone color identifies；
When receiving the first selection instruction based on the plurality of tone color mark, the tone color selecting tone color mark that instruction is carried corresponding by described first is defined as described appointment tone color, and described first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
Alternatively, described after server transmission song information acquisition request, also include:
When receiving the musical instrument selection information that described server sends, showing that described musical instrument selects information, described musical instrument selects information to include multiple musical instrument mark；
When receiving the second selection instruction based on the plurality of musical instrument mark, by described second select instruction carry at least one musical instrument mark be sent to described server, at least one musical instrument described mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
Second aspect, it is provided that a kind of song generates method, and described method includes:
Receiving the song information acquisition request that terminal sends, described song information obtains in request and carries Feature Words, when described Feature Words is the lyrics information that described terminal receives target song to be generated, described lyrics information is carried out feature extraction and obtains；
Based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music；
The described music score of Chinese operas and background music are sent to described terminal, make described terminal based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music to generate described target song.
Alternatively, described based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music, including:
Based on described Feature Words, from default emotion dictionary, obtain the affective characteristics information of described lyrics information, described default emotion dictionary stores the corresponding relation between Feature Words and affective characteristics；
Carry out music based on described affective characteristics information, obtain the music score of Chinese operas of described target song；
Based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, obtain the background music of described target song.
Alternatively, described carry out music based on described affective characteristics information, obtain the music score of Chinese operas of described target song, including:
Obtain the humming information of described lyrics information；
Described humming information is analyzed, obtains multiple note and the scale of the plurality of note；
Scale based on described affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of described target song.
Alternatively, described based on specify musical instrument the described music score of Chinese operas is dubbed in background music, obtain the background music of described target song, including:
Based on the scale of note each in the described music score of Chinese operas, from the tone information of described appointment musical instrument, obtain the tone information of described each note；
The tone information of note each in the described music score of Chinese operas is combined, obtains the background music of described target song.
Alternatively, described based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, before obtaining the background music of described target song, also include:
Sending musical instrument to described terminal and select information, described musical instrument selects information to include multiple musical instrument mark, makes described terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
When at least one musical instrument mark described in receiving described terminal and sending, musical instrument corresponding at least one musical instrument described mark is defined as described appointment musical instrument.
The third aspect, it is provided that a kind of terminal, described terminal includes:
Receiver module, for receiving the lyrics information of target song to be generated；
Characteristic extracting module, for described lyrics information is carried out feature extraction, obtains Feature Words；
First sending module, obtains request for sending song information to server, and described song information obtains in request and carries described Feature Words, makes described server return the music score of Chinese operas and the background music of described target song based on described Feature Words；
Generation module, for when receiving the music score of Chinese operas and the background music that described server sends, based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, generating described target song.
Alternatively, described characteristic extracting module includes:
Judging unit, is used for judging whether described lyrics information is text message；
Fisrt feature extraction unit, for when described lyrics information is text message, carrying out feature extraction to described lyrics information, obtain described Feature Words；
Text conversion units, for when described lyrics information is not text message, carrying out text conversion to described lyrics information, obtain lyrics text message；
Second feature extraction unit, for described lyrics text message is carried out feature extraction, obtains described Feature Words.
Alternatively, described generation module includes:
Converting unit, for based on the music score of Chinese operas described in described designated tone normal complexion, being converted to lyrics audio-frequency information by described lyrics information；
Assembled unit, for described lyrics audio-frequency information and described background music being combined, obtains described target song.
Alternatively, described terminal also includes:
First display module, for when receiving tone color and determining instruction, showing that multiple tone color identifies；
Determine module, for when receiving the first selection instruction based on the plurality of tone color mark, the tone color selecting tone color mark that instruction is carried corresponding by described first is defined as described appointment tone color, and described first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
Alternatively, described terminal also includes:
Second display module, for when receiving the musical instrument selection information that described server sends, showing that described musical instrument selects information, described musical instrument selects information to include multiple musical instrument mark；
Second sending module, for when receiving the second selection instruction based on the plurality of musical instrument mark, by described second select instruction carry at least one musical instrument mark be sent to described server, at least one musical instrument described mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
Fourth aspect, it is provided that a kind of server, described server includes:
Receiver module, the song information sent for receiving terminal obtains request, described song information obtains in request and carries Feature Words, when described Feature Words is the lyrics information that described terminal receives target song to be generated, described lyrics information is carried out feature extraction and obtains；
Determine module, for based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music；
Sending module, for the described music score of Chinese operas and background music are sent to described terminal, makes described terminal based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music to generate described target song.
Alternatively, described determine that module includes:
Acquiring unit, for based on described Feature Words, obtaining the affective characteristics information of described lyrics information from default emotion dictionary, stores the corresponding relation between Feature Words and affective characteristics in described default emotion dictionary；
Music unit, for carrying out music based on described affective characteristics information, obtains the music score of Chinese operas of described target song；
Dub in background music unit, for based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, obtaining the background music of described target song.
Alternatively, described music unit includes:
First obtains subelement, for obtaining the humming information of described lyrics information；
Analyze subelement, for described humming information is analyzed, obtain multiple note and the scale of the plurality of note；
Determine subelement, for the scale based on described affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of described target song.
Alternatively, unit of dubbing in background music described in includes:
Second obtains subelement, for the scale based on note each in the described music score of Chinese operas, from the tone information of described appointment musical instrument, obtains the tone information of described each note；
Combination subelement, for being combined by the tone information of note each in the described music score of Chinese operas, obtains the background music of described target song.
Alternatively, described determine that module also includes:
Transmitting element, selects information for sending musical instrument to described terminal, and described musical instrument selects information to include multiple musical instrument mark, makes described terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
Determine unit, for when at least one musical instrument described in receiving described terminal and sending identifies, musical instrument corresponding at least one musical instrument described mark being defined as described appointment musical instrument.
The technical scheme that the embodiment of the present invention provides has the benefit that in embodiments of the present invention, when terminal receives the lyrics information of target song to be generated, this lyrics information can be carried out feature extraction by this terminal, obtain Feature Words, and then this Feature Words is sent to server, when server receives this Feature Words, it is possible to determine the music score of Chinese operas and the background music of target song according to this Feature Words, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after the music score of Chinese operas of target song and background music are sent to terminal by server, this terminal can also directly generate target song, further reduces the degree of participation of user, simplifies the operation generating song, thus improve the efficiency generating song.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme in the embodiment of the present invention, below the accompanying drawing used required during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is that a kind of song that the embodiment of the present invention provides generates method flow diagram；
Fig. 2 is that a kind of song that the embodiment of the present invention provides generates method flow diagram；
Fig. 3 is that a kind of song that the embodiment of the present invention provides generates method flow diagram；
Fig. 4 is the structural representation of a kind of terminal that the embodiment of the present invention provides；
Fig. 5 is the structural representation of a kind of server that the embodiment of the present invention provides.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Fig. 1 is that a kind of song that the embodiment of the present invention provides generates method flow diagram.Referring to Fig. 1, the method is applied in terminal, and the method includes:
Step 101: receive the lyrics information of target song to be generated.
Step 102: this lyrics information is carried out feature extraction, obtains Feature Words.
Step 103: sending song information to server and obtain request, this song information obtains in request and carries this Feature Words, makes server return the music score of Chinese operas and the background music of target song based on this Feature Words.
Step 104: when receiving the music score of Chinese operas and the background music that server sends, based on specifying tone color, lyrics information, the music score of Chinese operas and background music, generates target song.
In embodiments of the present invention, when terminal receives the lyrics information of target song to be generated, this lyrics information can be carried out feature extraction by this terminal, obtain Feature Words, and then this Feature Words is sent to server, to obtain the music score of Chinese operas and the background music of target song from server, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after terminal gets the music score of Chinese operas and the background music of target song, it is possible to directly generate target song, further reduce the degree of participation of user, simplify the operation generating song, thus improve the efficiency generating song.
Alternatively, this lyrics information is carried out feature extraction, obtains Feature Words, including:
Judge whether this lyrics information is text message；
When this lyrics information is text message, this lyrics information is carried out feature extraction, obtain this Feature Words；
When this lyrics information is not text message, this lyrics information is carried out text conversion, obtain lyrics text message；
This lyrics text message is carried out feature extraction, obtains this Feature Words.
Alternatively, based on specifying tone color, this lyrics information, this music score of Chinese operas and this background music, generate this target song, including:
Based on this this music score of Chinese operas of designated tone normal complexion, this lyrics information is converted to lyrics audio-frequency information；
This lyrics audio-frequency information and this background music are combined, obtain this target song.
Alternatively, based on specifying tone color, this lyrics information, this music score of Chinese operas and this background music, before generating this target song, also include:
When receiving tone color and determining instruction, show that multiple tone color identifies；
When receiving the first selection instruction based on the plurality of tone color mark, this first tone color selecting tone color mark that instruction is carried corresponding being defined as this appointment tone color, this first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
Alternatively, obtain to server transmission song information after asking, also include:
When receiving the musical instrument selection information that this server sends, showing that this musical instrument selects information, this musical instrument selects information to include multiple musical instrument mark；
When based on the plurality of musical instrument mark receive the second selection instruction time, by this second select instruction carry at least one musical instrument mark be sent to this server, this at least one musical instrument mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
Above-mentioned all optional technical schemes, all can according to arbitrarily combining formation optional embodiment of the present invention, and this is no longer repeated by the embodiment of the present invention one by one.
Fig. 2 is that a kind of song that the embodiment of the present invention provides generates method flow diagram.Referring to Fig. 2, the method is applied in server, and the method includes:
Step 201: receiving the song information acquisition request that terminal sends, this song information obtains in request and carries Feature Words, when this Feature Words is the lyrics information that terminal receives target song to be generated, this lyrics information is carried out feature extraction and obtains.
Step 202: based on this Feature Words, it is determined that the music score of Chinese operas of target song and background music.
Step 203: this music score of Chinese operas and background music are sent to terminal, makes terminal based on specifying tone color, lyrics information, the music score of Chinese operas and background music to generate target song.
In embodiments of the present invention, when server receives the song information acquisition request that terminal sends, it is possible to determine the music score of Chinese operas and the background music of target song according to this Feature Words, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after the music score of Chinese operas of target song and background music are sent to terminal by server, this terminal can also directly generate target song, further reduces the degree of participation of user, simplifies the operation generating song, thus improve the efficiency generating song.
Alternatively, based on this Feature Words, it is determined that the music score of Chinese operas of this target song and background music, including:
Based on this Feature Words, from default emotion dictionary, obtain the affective characteristics information of this lyrics information, this default emotion dictionary stores the corresponding relation between Feature Words and affective characteristics；
Carry out music based on this affective characteristics information, obtain the music score of Chinese operas of this target song；
Based on specifying musical instrument that this music score of Chinese operas is dubbed in background music, obtain the background music of this target song.
Alternatively, carry out music based on this affective characteristics information, obtain the music score of Chinese operas of this target song, including:
Obtain the humming information of this lyrics information；
This humming information is analyzed, obtains multiple note and the scale of the plurality of note；
Scale based on this affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of this target song.
Alternatively, based on specifying musical instrument that this music score of Chinese operas is dubbed in background music, obtain the background music of this target song, including:
Based on the scale of note each in this music score of Chinese operas, from the tone information of this appointment musical instrument, obtain the tone information of this each note；
The tone information of note each in this music score of Chinese operas is combined, obtains the background music of this target song.
Alternatively, based on specifying musical instrument that this music score of Chinese operas is dubbed in background music, before obtaining the background music of this target song, also include:
Sending musical instrument to this terminal and select information, this musical instrument selects information to include multiple musical instrument mark, makes this terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
When receiving this at least one musical instrument mark that this terminal sends, musical instrument corresponding for this at least one musical instrument mark is defined as this appointment musical instrument.
Above-mentioned all optional technical schemes, all can according to arbitrarily combining formation optional embodiment of the present invention, and this is no longer repeated by the embodiment of the present invention one by one.
Fig. 3 is that a kind of song that the embodiment of the present invention provides generates method flow diagram.Referring to Fig. 3, the method includes:
Step 301: terminal receives the lyrics information of target song to be generated, and this lyrics information is carried out feature extraction, obtains Feature Words.
Specifically, this terminal receives the lyrics information of target song to be generated, it is judged that whether this lyrics information is text message；When this lyrics information is text message, this lyrics information is carried out feature extraction, obtains Feature Words；When this lyrics information is not text message, this lyrics information is carried out text conversion, obtain lyrics text message, and this lyrics text message is carried out feature extraction, obtain Feature Words.
It should be noted that the lyrics information of target song can receive when song generates instruction in this terminal receives user's input.This song generates instruction and is used for indicating this terminal to generate target song, and this song generates instruction and can be triggered by user, this user can be triggered by predetermined registration operation, and this predetermined registration operation can be clicking operation, slide, voice operating etc., and this is not specifically limited by the embodiment of the present invention.
It addition, the lyrics information of this target song can be text message, it is also possible to being voice messaging, this is not specifically limited by the embodiment of the present invention.
Furthermore, in embodiments of the present invention, this terminal is possible not only to according to the method described above this lyrics information be carried out feature extraction and obtains Feature Words, certainly, this terminal can also carry out feature extraction according to other method, and such as, this terminal may determine that whether this lyrics information is voice messaging；When this lyrics information is voice messaging, this lyrics information is carried out feature extraction, obtains Feature Words；When this lyrics information is not voice messaging, this lyrics information being carried out voice conversion, obtain lyrics voice messaging, and this lyrics voice messaging is carried out feature extraction, obtain Feature Words, this is not specifically limited by the embodiment of the present invention.
It can further be stated that, when this lyrics information is carried out feature extraction by this terminal, feature extraction can be carried out for every lyrics in this lyrics information, thus obtaining the Feature Words of every lyrics, certainly, whole lyrics information directly can also be carried out feature extraction by this terminal, obtains the Feature Words of this whole lyrics information, and this is not specifically limited by the embodiment of the present invention.Additionally, the method that every lyrics in this lyrics information are carried out feature extraction by this terminal is identical with the method that whole lyrics information carries out feature extraction, and this feature extracting method is referred to correlation technique, and this lyrics information is carried out the method for text conversion and voice conversion by this terminal can also with reference to correlation technique, and this is no longer elaborated by the embodiment of the present invention.
Step 302: this terminal to server sends song information and obtains request, this song information obtains in request and carries this Feature Words.
It should be noted that this song information obtains request for asking to obtain the music score of Chinese operas and the background music of this target song from server.
Step 303: when server receives the song information acquisition request that this terminal sends, based on this Feature Words, from default emotion dictionary, obtain the affective characteristics information of this lyrics information, preset the corresponding relation between storage Feature Words and affective characteristics in emotion dictionary.
Specifically, when server receives the song information acquisition request that this terminal sends, this server can based on this Feature Words, in corresponding relation between the Feature Words and the affective characteristics that store from default emotion dictionary, obtain corresponding affective characteristics, and the affective characteristics of acquisition is defined as the affective characteristics information of this lyrics information.
It should be noted that affective characteristics information is for representing the emotion that this lyrics information comprises, such as " happiness ", " sadness ", " anger ", " passiveness ", " actively " etc., this is not limited by the embodiment of the present invention.
nullSuch as，When this Feature Words is " indifferently "、" anopia "、" fury " and " disappointment "，This server can feature based word " indifferently "，From the corresponding relation between Feature Words as shown in table 1 below and affective characteristics，Obtaining corresponding affective characteristics is " passiveness "，Feature based word " anopia "，From the corresponding relation between Feature Words as shown in table 1 below and affective characteristics，Obtaining corresponding affective characteristics is " sadness "，Feature based word " fury "，From the corresponding relation between Feature Words as shown in table 1 below and affective characteristics，Obtaining corresponding affective characteristics is " anger "，Feature based word " disappointment "，From the corresponding relation between Feature Words as shown in table 1 below and affective characteristics，Obtaining corresponding affective characteristics is " passiveness "，Therefore，Determine that the affective characteristics information of this lyrics information is for " passive、Sad、Angry ".
Table 1
It should be noted that the embodiment of the present invention only illustrates for the corresponding relation between Feature Words and the affective characteristics shown in above-mentioned table 1, the embodiment of the present invention is constituted restriction by above-mentioned table 1.
It can further be stated that, in embodiments of the present invention, preset emotion dictionary can arrange in advance, namely multiple Feature Words are obtained in advance, by emotion learning algorithm, the plurality of Feature Words is classified, so that it is determined that the affective characteristics of the plurality of Feature Words, the affective characteristics corresponding with the plurality of Feature Words by the plurality of Feature Words, it is stored in the corresponding relation between Feature Words and the affective characteristics in default emotion dictionary.
Additionally, in the process generating song, when the Feature Words that server sends based on terminal, when default emotion dictionary cannot find the affective characteristics of correspondence, this Feature Words can also be classified by this server by emotion learning algorithm, determine the affective characteristics of this Feature Words, and the affective characteristics of this Feature Words and this Feature Words is stored in the corresponding relation between Feature Words and the affective characteristics in default emotion dictionary, so that default emotion dictionary is updated.
Furthermore, this default emotion dictionary can adopt data base to store as storage medium, it is, of course, also possible to adopt other storage medium to store, this is not specifically limited by the embodiment of the present invention.
It should be noted that method Feature Words classified by emotion learning algorithm is referred to correlation technique, this is not specifically limited by the embodiment of the present invention.
Alternatively, in embodiments of the present invention, determine the affective characteristics information of this lyrics information not only by the method for above-mentioned steps 301-303, certainly, this terminal can also when receiving the lyrics information of target song, this lyrics information is sent to this server, when this server receives this lyrics information, this lyrics information is carried out feature extraction, obtains Feature Words, and based on this Feature Words, from default emotion dictionary, obtain the affective characteristics information of this lyrics information.That is to say, the operation that lyrics information carries out feature extraction performs not only by terminal, it is also possible to being performed by server, this is not specifically limited by the embodiment of the present invention.
Step 304: this server carries out music based on this affective characteristics information, obtains the music score of Chinese operas of target song.
Specifically, this server can obtain the humming information of this lyrics information, and this humming information is analyzed, and obtains multiple note and the scale of the plurality of note；Scale based on this affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of target song.
Wherein, this server obtain humming information can be terminal carry song information obtain request in be sent to server, certainly, this server can also when carrying out, based on this affective characteristics information, the music score of Chinese operas that music obtains target song, humming information acquisition request is sent to terminal, when this terminal receives this humming information acquisition request, display humming information alert information, afterwards, record the humming information of user, and the humming information of recording is sent to this server, the opportunity obtaining humming information is not specifically limited by the embodiment of the present invention.
Carrying out humming based on this lyrics information obtain it should be noted that humming information is user, this is not specifically limited by the embodiment of the present invention.
It addition, this humming information is analyzed by this server, the method obtaining the scale of multiple note and the plurality of note is referred to correlation technique, and this is not specifically limited by the embodiment of the present invention.
nullWherein，This server is based on this affective characteristics information、The scale of the plurality of note and the plurality of note，The operation determining the music score of Chinese operas of target song can be: this server is based on this affective characteristics information，From the corresponding relation between affective characteristics information and the music score of Chinese operas information of storage，Obtain corresponding music score of Chinese operas information，This music score of Chinese operas information can include note、Corresponding relation between scale and the music score of Chinese operas，Afterwards，For each note in the plurality of note，This server can based on the scale of this note He this note，Note from this music score of Chinese operas information、In corresponding relation between scale and the music score of Chinese operas，Obtain the corresponding music score of Chinese operas，And according to the sequencing of the plurality of note，The music score of Chinese operas of the plurality of note is ranked up and combines，Obtain the music score of Chinese operas of target song，Wherein，The sequencing of the plurality of note is the order of the plurality of note in this humming information.
It should be noted that and the music score of Chinese operas not only includes note and scale, it is also possible to include other music element, therefore, after this server gets multiple notes of target song and the scale of the plurality of note, it is necessary to based on the scale of the plurality of note and the plurality of note, obtain the music score of Chinese operas of target song.
It should be noted that, corresponding relation between this affective characteristics information and music score of Chinese operas information, and note, corresponding relation between scale and the music score of Chinese operas can be arranged in advance, that is to say, this server can obtain number of songs in advance, the lyrics information of this number of songs is analyzed, obtain the affective characteristics information of this number of songs, affective characteristics information based on this number of songs, this number of songs is classified, the music score of Chinese operas belonging to of a sort song is analyzed, to determine the note of such song, corresponding relation between scale and the music score of Chinese operas, and then store the corresponding relation between the affective characteristics information of such song and music score of Chinese operas information.
Alternatively, server carries out music not only by said method based on this affective characteristics information, certainly, in practical application, this server can also carry out music by other method, such as, this server is based on this affective characteristics information, from the corresponding relation between affective characteristics information and the music score of Chinese operas section of storage, obtain corresponding music score of Chinese operas section, this music score of Chinese operas section includes multiple note and the scale of the plurality of note, for each note in multiple notes in the music score of Chinese operas section of acquisition, scale based on this note He this note, note from storage, in corresponding relation between scale and the music score of Chinese operas, obtain the corresponding music score of Chinese operas, and according to the sequencing of the plurality of note in this music score of Chinese operas section, the music score of Chinese operas corresponding for the plurality of note is ranked up and combines, obtain the music score of Chinese operas of target song.
It should be noted that, corresponding relation between affective characteristics information and music score of Chinese operas section is also prior setting, that is to say, this server can obtain number of songs in advance, the lyrics information of this number of songs is analyzed, obtain the affective characteristics information of this number of songs, owing in a song, the affective characteristics of every lyrics is likely to difference, therefore, for song every in this number of songs, this server can obtain the affective characteristics of every lyrics in this song from the affective characteristics information of this song, and the affective characteristics of every lyrics and the music score of Chinese operas section of this every the lyrics are stored in the corresponding relation between affective characteristics information and music score of Chinese operas section.
Step 305: this server, based on specifying musical instrument that the music score of Chinese operas of target song is dubbed in background music, obtains the background music of target song.
Specifically, this server can the scale of each note in the music score of Chinese operas of based target song, from the tone information specifying musical instrument, obtain the tone information of each note, the tone information of note each in the music score of Chinese operas of target song is combined, obtains the background music of target song.
Owing to the tone information of each musical instrument is different, and for same musical instrument, the note of different scales is also different at the tone information of this musical instrument, and such as, piano is different with the tone information of guitar, and the tone information of the note of different scales is also different in piano, therefore, this server can the scale of each note in the music score of Chinese operas of based target song, from the tone information specifying musical instrument, obtain the tone information of each note, thus exactly the music score of Chinese operas of this target song being dubbed in background music.
It should be noted that, specifying musical instrument can be the acquiescence musical instrument of storage in this server, certainly, in order to determine the background music of target song according to the different demands of different user, this appointment musical instrument can also be determined by user, that is to say, the music score of Chinese operas of target song is dubbed in background music by server based on appointment musical instrument, before obtaining the background music of target song, musical instrument can also be sent to terminal and select information, this musical instrument selects information to include multiple musical instrument mark, when terminal receives the musical instrument selection information that server sends, show that this musical instrument selects information, when this terminal receives the second selection instruction based on the plurality of musical instrument mark, at least one musical instrument mark carried in this second selection instruction is sent to server.When server receives at least one musical instrument mark that terminal sends, being defined as specifying musical instrument by musical instrument corresponding for this at least one musical instrument mark, each musical instrument in this at least one musical instrument mark is designated the arbitrary musical instrument mark in the plurality of musical instrument mark.
It should be noted that musical instrument mark is for unique this musical instrument that identifies, and this musical instrument mark can be the title of this musical instrument, image etc., and this is not specifically limited by the embodiment of the present invention.
It addition, second selects instruction for selecting at least one musical instrument to identify identifying from the plurality of musical instrument, and second selects instruction can be triggered by user, and this user can be triggered by predetermined registration operation, and this is not specifically limited by the embodiment of the present invention.
Step 306: the music score of Chinese operas and the background music of this target song are sent to this terminal by this server.
In order to make terminal generate target song, after this server determines the music score of Chinese operas and the background music of this target song, the music score of Chinese operas of this target song and background music can be sent to this terminal by this server.
Step 307: when this terminal receives the music score of Chinese operas and the background music that server sends, based on specifying tone color, the lyrics information of target song, the music score of Chinese operas and background music, generate target song.
Specifically, when this terminal receives the music score of Chinese operas and the background music that server sends, based on the music score of Chinese operas of designated tone normal complexion target song, the lyrics information of target song is converted to lyrics audio-frequency information, and the background music of this lyrics audio-frequency information and target song is combined, obtain target song.
It should be noted that, specifying tone color can be the acquiescence tone color of storage in this terminal, certainly, in order to determine the tone color of target song according to the different demands of different user, this appointment tone color can also be determined by user, that is to say, this terminal is based on specifying tone color, the lyrics information of target song, the music score of Chinese operas and background music, before generating target song, this terminal can also when receiving tone color and determining instruction, show that multiple tone color identifies, when this terminal receives the first selection instruction based on the plurality of tone color mark, the tone color selecting the tone color carried in instruction mark corresponding by first is defined as specifying tone color, first selects the tone color carried in instruction to be designated the arbitrary tone color mark in the plurality of tone color mark.
Wherein, multiple tone colors mark of this terminal demonstration can be stored in this terminal local, can certainly be stored in server, when the plurality of tone color mark stores in the server, this terminal can send tone color to server and obtain request, when server receives the acquisition request of this tone color, it is possible to multiple tone colors of storage mark is sent to this terminal.
It should be noted that tone color mark is for unique this tone color that identifies, and this tone color mark can be the feature of this tone color, title etc., and this is not specifically limited by the embodiment of the present invention.
It addition, this tone color determines that instruction is for determining the tone color of target song, and this tone color determines that instruction can be triggered by user, and this user can be triggered by predetermined registration operation, and this is not specifically limited by the embodiment of the present invention.Furthermore, selecting instruction for selecting a tone color mark identifying from the plurality of tone color, and this selection instruction can also be triggered by user, this user can also be triggered by predetermined registration operation, and this is not specifically limited by the embodiment of the present invention equally.
Alternatively, this appointment tone color can also is that this terminal acquires from humming information, that is to say, this appointment tone color can be user self.
Wherein, this terminal is based on the music score of Chinese operas of designated tone normal complexion target song, the operation that the lyrics information of target song is converted to lyrics audio-frequency information can be: this terminal is according to the music score of Chinese operas of target song, the lyrics information of target song is converted to the first audio-frequency information, tone color in first audio-frequency information is adjusted to appointment tone color, obtain the second audio-frequency information, and the second audio-frequency information is defined as lyrics audio-frequency information.
It should be noted that, the method that the lyrics information of target song is converted to the first audio-frequency information is referred to correlation technique by this terminal, and the tone color in the first audio-frequency information is adjusted to the method specifying tone color can also with reference to correlation technique, this is no longer elaborated by the embodiment of the present invention.
It addition, the method that the background music of this lyrics audio-frequency information and target song is combined is referred to correlation technique by this terminal, this is no longer elaborated by the embodiment of the present invention equally.
Further, in embodiments of the present invention, when this terminal is based on specifying tone color, the lyrics information of target song, the music score of Chinese operas and background music, before generating target song, this terminal can also show this music score of Chinese operas, when this terminal receives the music score of Chinese operas amendment instruction of the happy element of designated tone in this music score of Chinese operas, the music element of this music score of Chinese operas middle finger allocation can also be revised as in the amendment instruction of this music score of Chinese operas the music element carried by this terminal.Additionally, this terminal can also play this background music, when this terminal receives the audio modification instruction of designated tone frequency frame in this background music, the audio-frequency information of designated tone frequency frame in this background music can also be revised as in this audio modification instruction the audio-frequency information carried by this terminal.
It should be noted that as described above, the music score of Chinese operas is possible not only to include note and scale, it is also possible to include other music element, that is to say, it is possible to each element in this music score of Chinese operas is called music element.And the music element of specifying in this music score of Chinese operas can be the arbitrary music element in this music score of Chinese operas, this is not specifically limited by the embodiment of the present invention.
It addition, music score of Chinese operas amendment instruction is for modifying to the appointment music element in this music score of Chinese operas, and the amendment instruction of this music score of Chinese operas can be triggered by user, and this user can be triggered by predetermined registration operation, and this is not specifically limited by the embodiment of the present invention.
It can further be stated that, background music can include multiple audio frame, and when this terminal plays background music, the all right progress displaying bar of this terminal, this progress bar can to should multiple audio frames in background audio, that is to say, when the appointment position clicked in this progress bar, audio frame corresponding for this appointment position can be determined this appointment audio frame, and trigger the audio modification instruction specifying audio frame.Therefore, in this background music, designated tone frequency frame can arbitrary audio frame in multiple audio frames of including of this background music, and the clicking operation of this progress bar can be triggered by user, that is to say, this audio modification instruction can be triggered by user, this audio modification instruction is for modifying to the audio-frequency information that the audio frame in this background audio is corresponding, and this is not specifically limited by the embodiment of the present invention.
Wherein, music element each in this music score of Chinese operas can be modified by this terminal according to above-mentioned, audio frame each in this background music can also be modified, thus being accurate to each music element, or each audio frame, it is not necessary to the whole music score of Chinese operas or background music are modified, not only simple to operate, improve the efficiency that song generates, it is also possible to make the song ultimately generated reach the demand of user.
In embodiments of the present invention, when terminal receives the lyrics information of target song to be generated, this lyrics information can be carried out feature extraction by this terminal, obtain Feature Words, and then this Feature Words is sent to server, when server receives this Feature Words, it is possible to determine the music score of Chinese operas and the background music of target song according to this Feature Words, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after the music score of Chinese operas of target song and background music are sent to terminal by server, this terminal can also directly generate target song, further reduces the degree of participation of user, simplifies the operation generating song, thus improve the efficiency generating song.
Fig. 4 is the structural representation of a kind of terminal that the embodiment of the present invention provides.Referring to Fig. 4, this terminal includes:
Receiver module 401, for receiving the lyrics information of target song to be generated；
Characteristic extracting module 402, for this lyrics information is carried out feature extraction, obtains Feature Words；
First sending module 403, obtains request for sending song information to server, and this song information obtains in request and carries this Feature Words, makes this server return the music score of Chinese operas and the background music of this target song based on this Feature Words；
Generation module 404, for when receiving the music score of Chinese operas and the background music that this server sends, based on specifying tone color, this lyrics information, this music score of Chinese operas and this background music, generating this target song.
Alternatively, this characteristic extracting module 402 includes:
Judging unit, is used for judging whether this lyrics information is text message；
Fisrt feature extraction unit, for when this lyrics information is text message, carrying out feature extraction to this lyrics information, obtain this Feature Words；
Text conversion units, for when this lyrics information is not text message, carrying out text conversion to this lyrics information, obtain lyrics text message；
Second feature extraction unit, for this lyrics text message is carried out feature extraction, obtains this Feature Words.
Alternatively, this generation module 404 includes:
Converting unit, for based on this this music score of Chinese operas of designated tone normal complexion, being converted to lyrics audio-frequency information by this lyrics information；
Assembled unit, for this lyrics audio-frequency information and this background music being combined, obtains this target song.
Alternatively, this terminal also includes:
First display module, for when receiving tone color and determining instruction, showing that multiple tone color identifies；
Determine module, for when receiving the first selection instruction based on the plurality of tone color mark, this first tone color selecting tone color mark that instruction is carried corresponding is defined as this appointment tone color, and this first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
Alternatively, this terminal also includes:
Second display module, for when receiving the musical instrument selection information that this server sends, showing that this musical instrument selects information, this musical instrument selects information to include multiple musical instrument mark；
Second sending module, for when receiving the second selection instruction based on the plurality of musical instrument mark, by this second select instruction carry at least one musical instrument mark be sent to this server, this at least one musical instrument mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
In embodiments of the present invention, when terminal receives the lyrics information of target song to be generated, this lyrics information can be carried out feature extraction by this terminal, obtain Feature Words, and then this Feature Words is sent to server, to obtain the music score of Chinese operas and the background music of target song from server, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after terminal gets the music score of Chinese operas and the background music of target song, it is possible to directly generate target song, further reduce the degree of participation of user, simplify the operation generating song, thus improve the efficiency generating song.
It should be understood that the terminal that above-described embodiment provides is when generating song, only it is illustrated with the division of above-mentioned each functional module, in practical application, as desired above-mentioned functions distribution can be completed by different functional modules, it is divided into different functional modules, to complete all or part of function described above by the internal structure of terminal.It addition, the terminal that above-described embodiment provides generates embodiment of the method with song and belongs to same design, it implements process and refers to embodiment of the method, repeats no more here.
Fig. 5 is the structural representation of a kind of server that the embodiment of the present invention provides.Referring to Fig. 5, this server includes:
Receiver module 501, the song information sent for receiving terminal obtains request, and this song information obtains in request and carries Feature Words, when this Feature Words is the lyrics information that this terminal receives target song to be generated, this lyrics information is carried out feature extraction and obtains；
Determine module 502, for based on this Feature Words, it is determined that the music score of Chinese operas of this target song and background music；
Sending module 503, for this music score of Chinese operas and background music are sent to this terminal, makes this terminal based on specifying tone color, this lyrics information, this music score of Chinese operas and this background music to generate this target song.
Alternatively, this determines that module 502 includes:
Acquiring unit, for based on this Feature Words, obtaining the affective characteristics information of this lyrics information from default emotion dictionary, stores the corresponding relation between Feature Words and affective characteristics in this default emotion dictionary；
Music unit, for carrying out music based on this affective characteristics information, obtains the music score of Chinese operas of this target song；
Dub in background music unit, for based on specifying musical instrument that this music score of Chinese operas is dubbed in background music, obtaining the background music of this target song.
Alternatively, this music unit includes:
First obtains subelement, for obtaining the humming information of this lyrics information；
Analyze subelement, for this humming information is analyzed, obtain multiple note and the scale of the plurality of note；
Determine subelement, for the scale based on this affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of this target song.
Alternatively, this unit of dubbing in background music includes:
Second obtains subelement, for the scale based on note each in this music score of Chinese operas, from the tone information of this appointment musical instrument, obtains the tone information of this each note；
Combination subelement, for being combined by the tone information of note each in this music score of Chinese operas, obtains the background music of this target song.
Alternatively, this determines that module 502 also includes:
Transmitting element, selects information for sending musical instrument to this terminal, and this musical instrument selects information to include multiple musical instrument mark, makes this terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
Determine unit, for when receiving this at least one musical instrument mark that this terminal sends, musical instrument corresponding for this at least one musical instrument mark being defined as this appointment musical instrument.
In embodiments of the present invention, when server receives the song information acquisition request that terminal sends, it is possible to determine the music score of Chinese operas and the background music of target song according to this Feature Words, thus decreasing the degree of participation that the music score of Chinese operas and background music are created by user.And after the music score of Chinese operas of target song and background music are sent to terminal by server, this terminal can also directly generate target song, further reduces the degree of participation of user, simplifies the operation generating song, thus improve the efficiency generating song.
It should be understood that the server that above-described embodiment provides is when generating song, only it is illustrated with the division of above-mentioned each functional module, in practical application, as desired above-mentioned functions distribution can be completed by different functional modules, it is divided into different functional modules, to complete all or part of function described above by the internal structure of server.It addition, the server that above-described embodiment provides generates embodiment of the method with song and belongs to same design, it implements process and refers to embodiment of the method, repeats no more here.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can be completed by hardware, can also be completed by the hardware that program carrys out instruction relevant, described program can be stored in a kind of computer-readable recording medium, storage medium mentioned above can be read only memory, disk or CD etc..
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within protection scope of the present invention.

Claims (20)

1. a song generates method, it is characterised in that described method includes:
Receive the lyrics information of target song to be generated；
Described lyrics information is carried out feature extraction, obtains Feature Words；
Sending song information to server and obtain request, described song information obtains in request and carries described Feature Words, makes described server return the music score of Chinese operas and the background music of described target song based on described Feature Words；
When receiving the music score of Chinese operas and the background music that described server sends, based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, generate described target song.
2. the method for claim 1, it is characterised in that described described lyrics information is carried out feature extraction, obtains Feature Words, including:
Judge whether described lyrics information is text message；
When described lyrics information is text message, described lyrics information is carried out feature extraction, obtain described Feature Words；
When described lyrics information is not text message, described lyrics information is carried out text conversion, obtain lyrics text message；
Described lyrics text message is carried out feature extraction, obtains described Feature Words.
3. method as claimed in claim 1 or 2, it is characterised in that described generate described target song based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, including:
Based on the music score of Chinese operas described in described designated tone normal complexion, described lyrics information is converted to lyrics audio-frequency information；
Described lyrics audio-frequency information and described background music are combined, obtain described target song.
4. the method as described in claim 1-3 any claim, it is characterised in that described based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, before generating described target song, also includes:
When receiving tone color and determining instruction, show that multiple tone color identifies；
When receiving the first selection instruction based on the plurality of tone color mark, the tone color selecting tone color mark that instruction is carried corresponding by described first is defined as described appointment tone color, and described first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
5. the method for claim 1, it is characterised in that described after server transmission song information acquisition request, also includes:
When receiving the musical instrument selection information that described server sends, showing that described musical instrument selects information, described musical instrument selects information to include multiple musical instrument mark；
When receiving the second selection instruction based on the plurality of musical instrument mark, by described second select instruction carry at least one musical instrument mark be sent to described server, at least one musical instrument described mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
6. a song generates method, it is characterised in that described method includes:
Receiving the song information acquisition request that terminal sends, described song information obtains in request and carries Feature Words, when described Feature Words is the lyrics information that described terminal receives target song to be generated, described lyrics information is carried out feature extraction and obtains；
Based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music；
The described music score of Chinese operas and background music are sent to described terminal, make described terminal based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music to generate described target song.
7. method as claimed in claim 6, it is characterised in that described based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music, including:
Based on described Feature Words, from default emotion dictionary, obtain the affective characteristics information of described lyrics information, described default emotion dictionary stores the corresponding relation between Feature Words and affective characteristics；
Carry out music based on described affective characteristics information, obtain the music score of Chinese operas of described target song；
Based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, obtain the background music of described target song.
8. method as claimed in claim 7, it is characterised in that described carry out music based on described affective characteristics information, obtains the music score of Chinese operas of described target song, including:
Obtain the humming information of described lyrics information；
Described humming information is analyzed, obtains multiple note and the scale of the plurality of note；
Scale based on described affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of described target song.
9. method as claimed in claim 7, it is characterised in that described obtain the background music of described target song based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, including:
Based on the scale of note each in the described music score of Chinese operas, from the tone information of described appointment musical instrument, obtain the tone information of described each note；
The tone information of note each in the described music score of Chinese operas is combined, obtains the background music of described target song.
10. the method as described in claim 7-9 any claim, it is characterised in that described based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, before obtaining the background music of described target song, also includes:
Sending musical instrument to described terminal and select information, described musical instrument selects information to include multiple musical instrument mark, makes described terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
When at least one musical instrument mark described in receiving described terminal and sending, musical instrument corresponding at least one musical instrument described mark is defined as described appointment musical instrument.
11. a terminal, it is characterised in that described terminal includes:
Receiver module, for receiving the lyrics information of target song to be generated；
Characteristic extracting module, for described lyrics information is carried out feature extraction, obtains Feature Words；
First sending module, obtains request for sending song information to server, and described song information obtains in request and carries described Feature Words, makes described server return the music score of Chinese operas and the background music of described target song based on described Feature Words；
Generation module, for when receiving the music score of Chinese operas and the background music that described server sends, based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music, generating described target song.
12. terminal as claimed in claim 11, it is characterised in that described characteristic extracting module includes:
Judging unit, is used for judging whether described lyrics information is text message；
Fisrt feature extraction unit, for when described lyrics information is text message, carrying out feature extraction to described lyrics information, obtain described Feature Words；
Text conversion units, for when described lyrics information is not text message, carrying out text conversion to described lyrics information, obtain lyrics text message；
Second feature extraction unit, for described lyrics text message is carried out feature extraction, obtains described Feature Words.
13. the terminal as described in claim 11 or 12, it is characterised in that described generation module includes:
Converting unit, for based on the music score of Chinese operas described in described designated tone normal complexion, being converted to lyrics audio-frequency information by described lyrics information；
Assembled unit, for described lyrics audio-frequency information and described background music being combined, obtains described target song.
14. the terminal as described in claim 11-13 any claim, it is characterised in that described terminal also includes:
First display module, for when receiving tone color and determining instruction, showing that multiple tone color identifies；
Determine module, for when receiving the first selection instruction based on the plurality of tone color mark, the tone color selecting tone color mark that instruction is carried corresponding by described first is defined as described appointment tone color, and described first selects the tone color that instruction is carried to be designated in the plurality of tone color mark arbitrary tone color mark.
15. terminal as claimed in claim 11, it is characterised in that described terminal also includes:
Second display module, for when receiving the musical instrument selection information that described server sends, showing that described musical instrument selects information, described musical instrument selects information to include multiple musical instrument mark；
Second sending module, for when receiving the second selection instruction based on the plurality of musical instrument mark, by described second select instruction carry at least one musical instrument mark be sent to described server, at least one musical instrument described mark in each musical instrument be designated the plurality of musical instrument mark in arbitrary musical instrument mark.
16. a server, it is characterised in that described server includes:
Receiver module, the song information sent for receiving terminal obtains request, described song information obtains in request and carries Feature Words, when described Feature Words is the lyrics information that described terminal receives target song to be generated, described lyrics information is carried out feature extraction and obtains；
Determine module, for based on described Feature Words, it is determined that the music score of Chinese operas of described target song and background music；
Sending module, for the described music score of Chinese operas and background music are sent to described terminal, makes described terminal based on specifying tone color, described lyrics information, the described music score of Chinese operas and described background music to generate described target song.
17. server as claimed in claim 16, it is characterised in that described determine that module includes:
Acquiring unit, for based on described Feature Words, obtaining the affective characteristics information of described lyrics information from default emotion dictionary, stores the corresponding relation between Feature Words and affective characteristics in described default emotion dictionary；
Music unit, for carrying out music based on described affective characteristics information, obtains the music score of Chinese operas of described target song；
Dub in background music unit, for based on specifying musical instrument that the described music score of Chinese operas is dubbed in background music, obtaining the background music of described target song.
18. server as claimed in claim 17, it is characterised in that described music unit includes:
First obtains subelement, for obtaining the humming information of described lyrics information；
Analyze subelement, for described humming information is analyzed, obtain multiple note and the scale of the plurality of note；
Determine subelement, for the scale based on described affective characteristics information, the plurality of note and the plurality of note, it is determined that the music score of Chinese operas of described target song.
19. server as claimed in claim 17, it is characterised in that described in unit of dubbing in background music include:
Second obtains subelement, for the scale based on note each in the described music score of Chinese operas, from the tone information of described appointment musical instrument, obtains the tone information of described each note；
Combination subelement, for being combined by the tone information of note each in the described music score of Chinese operas, obtains the background music of described target song.
20. the server as described in claim 17-19 any claim, it is characterised in that described determine that module also includes:
Transmitting element, selects information for sending musical instrument to described terminal, and described musical instrument selects information to include multiple musical instrument mark, makes described terminal select at least one musical instrument to identify identifying from the plurality of musical instrument；
Determine unit, for when at least one musical instrument described in receiving described terminal and sending identifies, musical instrument corresponding at least one musical instrument described mark being defined as described appointment musical instrument.
CN201610057485.7A 2016-01-27 2016-01-27 Song generation method, terminal and server Active CN105740394B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610057485.7A CN105740394B (en) 2016-01-27 2016-01-27 Song generation method, terminal and server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610057485.7A CN105740394B (en) 2016-01-27 2016-01-27 Song generation method, terminal and server

Publications (2)

Publication Number Publication Date
CN105740394A true CN105740394A (en) 2016-07-06
CN105740394B CN105740394B (en) 2019-02-26

Family

ID=56246741

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610057485.7A Active CN105740394B (en) 2016-01-27 2016-01-27 Song generation method, terminal and server

Country Status (1)

Country Link
CN (1) CN105740394B (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106652984A (en) * 2016-10-11 2017-05-10 张文铂 Automatic song creation method via computer
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
CN106780673A (en) * 2017-02-13 2017-05-31 杨金强 A kind of animation method and system
CN107122493A (en) * 2017-05-19 2017-09-01 北京金山安全软件有限公司 song playing method and device
CN108492817A (en) * 2018-02-11 2018-09-04 北京光年无限科技有限公司 A kind of song data processing method and performance interactive system based on virtual idol
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
CN109841224A (en) * 2017-11-27 2019-06-04 北京京东尚科信息技术有限公司 Multi-medium play method, system and electronic equipment
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
CN110148393A (en) * 2018-02-11 2019-08-20 阿里巴巴集团控股有限公司 Music generating method, device and system and data processing method
TWI713958B (en) * 2018-12-22 2020-12-21 淇譽電子科技股份有限公司 Automated songwriting generation system and method thereof
WO2021012503A1 (en) * 2019-07-22 2021-01-28 平安科技（深圳）有限公司 Song generation method, apparatus, computer device, and storage medium
CN112331234A (en) * 2020-10-27 2021-02-05 北京百度网讯科技有限公司 Song multimedia synthesis method, device, electronic device and storage medium
CN112489608A (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 generating songs, electronic equipment and storage medium
CN113792178A (en) * 2021-08-31 2021-12-14 北京达佳互联信息技术有限公司 A song generation method, device, electronic device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050144016A1 (en) * 2003-12-03 2005-06-30 Christopher Hewitt Method, software and apparatus for creating audio compositions
CN101901598A (en) * 2010-06-30 2010-12-01 北京捷通华声语音技术有限公司 Humming synthesis method and system
CN103440862A (en) * 2013-08-16 2013-12-11 北京奇艺世纪科技有限公司 Method, device and equipment for synthesizing voice and music
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
CN105070283A (en) * 2015-08-27 2015-11-18 百度在线网络技术（北京）有限公司 Singing voice scoring method and apparatus

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050144016A1 (en) * 2003-12-03 2005-06-30 Christopher Hewitt Method, software and apparatus for creating audio compositions
CN101901598A (en) * 2010-06-30 2010-12-01 北京捷通华声语音技术有限公司 Humming synthesis method and system
CN103440862A (en) * 2013-08-16 2013-12-11 北京奇艺世纪科技有限公司 Method, device and equipment for synthesizing voice and music
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
CN105070283A (en) * 2015-08-27 2015-11-18 百度在线网络技术（北京）有限公司 Singing voice scoring method and apparatus

Cited By (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106652984A (en) * 2016-10-11 2017-05-10 张文铂 Automatic song creation method via computer
CN106652984B (en) * 2016-10-11 2020-06-02 张文铂 Method for automatically composing songs by using computer
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
CN106780673A (en) * 2017-02-13 2017-05-31 杨金强 A kind of animation method and system
CN107122493A (en) * 2017-05-19 2017-09-01 北京金山安全软件有限公司 song playing method and device
CN107122493B (en) * 2017-05-19 2020-04-28 北京金山安全软件有限公司 Song playing method and device
CN109841224A (en) * 2017-11-27 2019-06-04 北京京东尚科信息技术有限公司 Multi-medium play method, system and electronic equipment
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
CN110148393B (en) * 2018-02-11 2023-12-15 阿里巴巴集团控股有限公司 Music generation method, device and system and data processing method
CN108492817A (en) * 2018-02-11 2018-09-04 北京光年无限科技有限公司 A kind of song data processing method and performance interactive system based on virtual idol
CN110148393A (en) * 2018-02-11 2019-08-20 阿里巴巴集团控股有限公司 Music generating method, device and system and data processing method
CN108492817B (en) * 2018-02-11 2020-11-10 北京光年无限科技有限公司 Song data processing method based on virtual idol and singing interaction system
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
TWI713958B (en) * 2018-12-22 2020-12-21 淇譽電子科技股份有限公司 Automated songwriting generation system and method thereof
WO2021012503A1 (en) * 2019-07-22 2021-01-28 平安科技（深圳）有限公司 Song generation method, apparatus, computer device, and storage medium
CN112489608A (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 generating songs, electronic equipment and storage medium
CN112489608B (en) * 2019-08-22 2024-07-16 北京峰趣互联网信息服务有限公司 Method, device, electronic device and storage medium for generating songs
CN112331234A (en) * 2020-10-27 2021-02-05 北京百度网讯科技有限公司 Song multimedia synthesis method, device, electronic device and storage medium
US20210407479A1 (en) * 2020-10-27 2021-12-30 Beijing Baidu Netcom Science And Technology Co., Ltd. Method for song multimedia synthesis, electronic device and storage medium
CN113792178A (en) * 2021-08-31 2021-12-14 北京达佳互联信息技术有限公司 A song generation method, device, electronic device and storage medium

Also Published As

Publication number Publication date
CN105740394B (en) 2019-02-26

Similar Documents

Publication Publication Date Title
CN105740394A (en) Music generation method, terminal, and server
CN110189741B (en) Audio synthesis method, device, storage medium and computer equipment
US7368652B2 (en) Music search system and music search apparatus
EP3843083A1 (en) Method, system, and computer-readable medium for creating song mashups
JP3557917B2 (en) Automatic composer and storage medium
US20060230909A1 (en) Operating method of a music composing device
EP2096626A1 (en) Method for visualizing audio data
US10496250B2 (en) System and method for implementing an intelligent automatic music jam session
CN105161087A (en) Automatic harmony method, device, and terminal automatic harmony operation method
CN104050961A (en) Voice synthesis device, voice synthesis method, and recording medium having a voice synthesis program stored thereon
US11776516B2 (en) Methods and systems for vocalist part mapping
US7053291B1 (en) Computerized system and method for building musical licks and melodies
CN101930732B (en) Music producing method and device based on user input voice and intelligent terminal
JP2015031738A (en) Chord progression estimation detection apparatus and chord progression estimation detection program
KR100687683B1 (en) A storage medium storing a performance control data generating device, a method of generating performance control data, and a program for executing the method
US20240005896A1 (en) Music generation method and apparatus
EP2793222B1 (en) Method for implementing an automatic music jam session
CN1130686C (en) Style change apparatus and karaoke apparatus
KR101975193B1 (en) Automatic composition apparatus and computer-executable automatic composition method
JP2001318677A (en) Portable telephone set
Müller et al. Computational methods for melody and voice processing in music recordings (Dagstuhl seminar 19052)
KR101020557B1 (en) Sheet music generating device and method for producing user-created music contents
KR20140054810A (en) System and method for producing music recorded, and apparatus applied to the same
JP2007241015A (en) Voice evaluation system
CN111883090A (en) Method and device for making audio file based on mobile terminal

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 510660 Guangzhou City, Guangzhou, Guangdong, Whampoa Avenue, No. 315, self - made 1-17

Applicant after: Guangzhou KuGou Networks Co., Ltd.

Address before: 510000 B1, building, No. 16, rhyme Road, Guangzhou, Guangdong, China 13F

Applicant before: Guangzhou KuGou Networks Co., Ltd.

GR01 Patent grant
GR01 Patent grant