CN104391980A - Song generating method and device - Google Patents
Song generating method and device Download PDFInfo
- Publication number
- CN104391980A CN104391980A CN201410743457.1A CN201410743457A CN104391980A CN 104391980 A CN104391980 A CN 104391980A CN 201410743457 A CN201410743457 A CN 201410743457A CN 104391980 A CN104391980 A CN 104391980A
- Authority
- CN
- China
- Prior art keywords
- song
- text
- described text
- feature
- lyrics
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/61—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
Abstract
An embodiment of the invention provides a song generating method and device. The method includes receiving a text input by a user; extracting the text feature information of the text; acquiring a song matching with the text feature information; performing voice synthesis processing on the text according to the song, and acquiring a fresh song with the text serving as the lyric. According to the scheme, after the text input by the user, the text feature information is extracted, the text feature information matches with the information corresponding to the lyrics of the existing song, the song matching with the text feature information can be acquired, the music of the successfully-matched song serves as the background music, the text serves as the fresh lyric of the background music, and the song generated through the text is acquired through voice synthesis.
Description
Technical field
The embodiment of the present invention relates to technical field of information processing, particularly relates to a kind of method and apparatus generating song.
Background technology
Text is the form of expression of written language, and a text can be a sentence, a paragraph or a chapter.
Process at present for text comprises two kinds of modes, and one is added text itself, delete or replace; Be adopt speech synthesis technique to be speech form by text-processing in another, the content expressed by speech form is identical with the content of text representation.
But, the expression of text or voice is only had to be inadequate in certain situation, as people can want when there being the mood of happiness or sadness to go to express by song, but owing to lacking the music theory knowledge of system, do not know how to set a song to music, most multipotency is write as text, and can not be still song by text-processing to the processing mode of text at present.
Summary of the invention
The embodiment of the present invention provides a kind of method and apparatus generating song, to realize text automatically to become song.
First aspect, embodiments provides a kind of method generating song, comprising:
Receive the text of user's input;
Extract the text feature information of described text;
Obtain the song with described text feature information matches;
According to described song, phonetic synthesis process is carried out to described text, obtain the new song that the lyrics are described text.
Second aspect, embodiments provides a kind of device generating song, comprising:
Received text module, for receiving the text of user's input;
Characteristic extracting module, for extracting the text feature information of described text;
Matching module, for obtaining the song with described text feature information matches;
Voice synthetic module, for carrying out phonetic synthesis process according to described song to described text, obtains the new song that the lyrics are described text.
The method and apparatus of the generation song that the embodiment of the present invention provides, after the text receiving user's input, by extracting the text feature information of text, and described text feature information is mated with the corresponding informance of the lyrics of existing song, thus the song with described text feature information matches can be obtained, by the music as a setting of dubbing in background music by the song that the match is successful, and using described text as the new lyrics corresponding to described background music, and pass through phonetic synthesis, achieve text generation song, add the mode of text-processing, meet more user's request.
Accompanying drawing explanation
In order to be illustrated more clearly in the present invention, introduce doing one to the accompanying drawing used required in the present invention simply below, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
A kind of process flow diagram generating the method for song that Fig. 1 a provides for the embodiment of the present invention one;
For carrying out the schematic diagram of the information of the song " blessing " of mating with text in the method for the generation song that Fig. 1 b provides for the embodiment of the present invention;
The schematic diagram of the text of user's input is received in the method for the generation song that Fig. 1 c provides for the embodiment of the present invention;
Fig. 1 d for after receiving the text shown in Fig. 1 c, the method for the generation song adopting the embodiment of the present invention one to provide and the design sketch that presents;
The method flow diagram with the song of described text feature information matches is obtained from the song data library lookup set up in advance in the method for the generation song that Fig. 2 provides for the embodiment of the present invention two;
A kind of structural representation generating the device of song that Fig. 3 provides for the embodiment of the present invention three.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, be described in further detail the technical scheme in the embodiment of the present invention below in conjunction with accompanying drawing, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Be understandable that; specific embodiment described herein is only for explaining the present invention; but not limitation of the invention; based on the embodiment in the present invention; those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not full content.
Embodiment one
Referring to Fig. 1 a, is a kind of process flow diagram generating the method for song that the embodiment of the present invention one provides.The method of the embodiment of the present invention can be performed by the device of the generation song being configured to hardware and/or software simulating, this implement device can be configured in chat software, as micro-letter, QQ and footpath between fields, footpath between fields etc., also can be configured in the server that the service of singing and Intelligent dialogue service can be provided, if provide in the robot of the service of singing and Intelligent dialogue service, can also be configured in all kinds of translation software, such as Baidu's translation.
The method comprises: operation 110 ~ operation 140.
In operation 110, receive the text of user's input.
Wherein, the text of user's input can for user's creation want to go to express by song and the text of reflection user happiness or sad mood, also can be that non-user that user obtains is original and the text of the mood that reflection user is glad or sad, whether no matter be that user is original, the text is all different from the lyrics of existing song.
In operation 120, extract the text feature information of described text.
Wherein, extract the text feature information of described text, preferably include:
Sentence cutting process is carried out to described text, obtains the subordinate sentence that described text packets contains;
Extract the sentence characteristics of the subordinate sentence that described text packets contains.
Wherein, the punctuation mark such as sentence cutting Main Basis fullstop, comma and realizing.
Further, extract the sentence characteristics of the subordinate sentence that described text packets contains, preferably include:
Extract at least one in the character quantity of the subordinate sentence that described text packets contains, described subordinate sentence in the simple or compound vowel of a Chinese syllable of each word and the tone of each word.
Be that " the waning city of lights is brilliant, and bustling with activity people's boiling is as extra large with the text of user's input." be described for example.
According to the punctuation mark ", " in the text that this user inputs and "." sentence cutting process is carried out to the text, obtain the first subordinate sentence that the text comprises " lights waning city brilliant " and the second subordinate sentence " bustling with activity people's boiling is as sea ", table 1 be the sentence characteristics of the subordinate sentence that the extraction text comprises.
Table 1
In table 1, a sound, two sound, three sound, the four tones of standard Chinese pronunciation and tone corresponding softly represent with " 1 ", " 2 ", " 3 ", " 4 " and " 0 " respectively.
It should be noted that, in table 1, list 3 sentence characteristics of subordinate sentence, also can using the another one sentence characteristics of the simple or compound vowel of a Chinese syllable of the last character in subordinate sentence as subordinate sentence.
Also it should be noted that, the text feature information of described text, except can comprising the sentence characteristics of subordinate sentence, can also comprise the affective characteristics of subordinate sentence, such as actively, passive or neutral.
In operation 130, obtain the song with described text feature information matches.
This operation, specifically in existing song, utilizes described text feature information, obtains the song with described text matches.As previously mentioned, the text of user's input is different from the lyrics of existing song, therefore in this operation, specifically described text feature information can be mated with the corresponding informance of the lyrics of existing song, thus obtain the song with described text feature information matches.
In this operation, the sentence characteristics of text can be mated with the sentence characteristics of the lyrics in song, also other text feature information such as the affective characteristics of subordinate sentence in text can be mated with the character pair of the lyrics in song, the combinations matches of all right different text feature information.
Be described for the sentence characteristics of the sentence characteristics of text and the lyrics below.
Refer to Fig. 1 b, there is shown the first paragraph lyrics of song " blessing " and the music score of Chinese operas corresponding to the first paragraph lyrics.
Similarly, according to the operation of the sentence characteristics of extraction text, the sentence characteristics of the lyrics can be obtained.So that " do not ask, do not say, All is understood, and no word are necessary, and at the moment, snuggle up to candle light, let us is spent quietly." this part lyrics is example, the sentence characteristics of extraction is as shown in table 2.
Table 2
Similarly, the sentence characteristics of other songs existing can be obtained, be mated by the sentence characteristics of the text that the sentence characteristics of existing a large amount of song is inputted with user respectively, the song of mating with the sentence characteristics of text can be obtained.
As previously mentioned, when described text feature information comprises the sentence characteristics of text, at least one feature in the simple or compound vowel of a Chinese syllable of each word and the tone of each word in the character quantity of the subordinate sentence that described text packets contains, described subordinate sentence can be extracted, in other words, the quantity of the present embodiment to the sentence characteristics of text does not limit, similarly, obtaining with the operation of the song of described text feature information matches, the quantity of the sentence characteristics of the lyrics in song is not limited, can compare mate as long as get the song information corresponding with text feature information.
It should be noted that, with the corresponding informance of different text feature information and song, the effect of the new song obtained is different.Such as, " character quantities of the lyrics " corresponding with song with " character quantity of subordinate sentence " in the sentence characteristics of text mate, and obtain the subordinate sentence number of words that the song that the match is successful can be good at compatible text, timing is relatively good; And for example, mate with the simple or compound vowel of a Chinese syllable of each word " in the subordinate sentence " " simple or compound vowel of a Chinese syllable that in the lyrics, each word is corresponding " corresponding with song in the sentence characteristics of text, obtain the song that the match is successful and can be good at the rhythm corresponding to the simple or compound vowel of a Chinese syllable of each word of compatible text; For another example, the affective characteristics corresponding with song with the affective characteristics of text mates, and obtains the song that the match is successful and can keep the emotion keynote consistent with the text that user inputs.
In operation 140, according to described song, phonetic synthesis process is carried out to described text, obtain the new song that the lyrics are described text.
The technical scheme of the present embodiment, after the text receiving user's input, by extracting the text feature information of text, and described text feature information is mated with the corresponding informance of the lyrics of existing song, thus the song with described text feature information matches can be obtained, by the music as a setting of dubbing in background music by the song that the match is successful, and using described text as the new lyrics corresponding to described background music, and pass through phonetic synthesis, achieve text generation song, add the mode of text-processing, meet more user's request, user is without the need to possessing the music theory knowledge of system, the text automatic music composing of user's input can be embodied as.
On the basis of the present embodiment, when preferably carrying out phonetic synthesis process, by the music as a setting of dubbing in background music of described song, and the voice of corresponding beat are generated according to described music score of Chinese operas information, or the voice of corresponding beat and pitch are generated according to described music score of Chinese operas information, obtain described new song, the word content of described voice is described text.In other words, by the music as a setting of dubbing in background music of the song with described text feature information matches, and utilize to control described text with the music score of Chinese operas of the song of described text matches read aloud pause duration, obtain synthesizing song; Or by the music as a setting of dubbing in background music of the song with described text feature information matches, and the performance pause duration and the pitch that control described text with the music score of Chinese operas of the song of described text matches can be utilized, obtain synthesizing song.
The manner, while the text automatic music composing being embodied as user's input, can control the beat and/or the pitch that synthesize song further.
The method of the generation song that the embodiment of the present invention provides can be applied to several scenes, is described respectively below for five kinds of application scenarioss.
Application scenarios one: user uses chat software to sing and explains or blessing.
In the social chat softwares such as micro-letter, QQ, footpath between fields, footpath between fields, if user is ashamed of vindication, the method of the embodiment of the present invention can be adopted, user only need input passage, can automatically for the word of user's input be set a song to music, to help user's romance vindication, user can play this song automatically generated by the voice play function of chat software.
Such as, user inputs the text of one section of oneself creation in chat software interface as illustrated in figure 1 c, as follows:
The waning city of lights is brilliant
Bustling with activity people's boiling is as sea
Chilly and quiet as in vain clear and bright in my year Central China in you
See that fireworks illuminate the haze of the night sky
The hand of producing clouds with one turn of the hand and rain with another is confounded black and white
The sea turns into mulberry fields and vice versa in the dream of illusion
How many purities are all buried by common customs eventually
Your warm being always difficult to is only had to forget
Two, a city people
Poly-faling apart of making a return journey several times is hovered
Whether the future that you promise to undertake still exists
One, a city people
Success and failure, gain and loss one dream thousand years
Affection as high as the heaven and hatred as deep as the sea once
Wind volume dust already
" key generates song and sends " button in user click chat software interface as illustrated in figure 1 c, plays back, as shown in Figure 1 d automatically in the form of songs.
Application scenarios two: by the robot for providing the service of singing and Intelligent dialogue service, it is artificially routine that this sentences the little degree machine that can sing, and the text that this little Du robot is used for user to input, through process, generates new song, then preserves and play.
Be below scenario simulation:
User A:Hi, little Du robot
Little degree: Hi
User A: please for I compiles a song
Little degree: good, please say the lyrics
User A:(says passage)
Little degree: (singing out with graceful song).
A user A: listen very well! Please this head is sung and listen to I Amy user B
A little degree: out of question!
(user A gives user B little Du robot)
User B:Hi, little Du robot
Little degree: could you tell me it is user B
User B: yes
A little degree: user A has a first song to give you! (singing out the new song of the word generation of saying according to user A).
Application scenarios three: to the pithy formula class of user's input, the text that poem class etc. is not easily recited is write music for a song automatically, remembers with auxiliary specific crowd (as student) by singing.
Such as, the text of user's input is as follows, is pithy formula class text:
Jack per line two number is added, and absolute value adds not reversion.
Contrary sign strengthens reduction mutually, and large number determines and symbol.
Opposite number summation each other, result is that zero palpus be remembered.
To the song that above-mentioned pithy formula class text coupling one is similar, allow student pass through study song and help to remember faster.
Application scenarios four: can translate in Baidu in (TTS) to increase and sing function.
In Baidu's translation, user inputs one section of text, and text user inputted is as source language, the translation of existing Baidu is supported to become another kind of language by source language translation, by increasing singing function in Baidu's translation, can by the translation process corresponding with the text that user inputs, using the new song that generates according to translation as pronunciation corresponding to translation, dubbing in background music of the song of mating with translation is included due in the new song that generates according to translation, the information such as beat or the rhythm, therefore, user is while seeing translation, namely translation is sung out by the mode of song by clicking the Action Button corresponding with singing function, thus add the interest of the translation pronunciation that user hears, be conducive to attracting more users.
Such as: user inputs Chinese happy birthday song, and Baidu's translation can be translated and become Italian and sing out by translation.
Application scenarios five: realize automatic music function in Baidu's music.
For Baidu's music increases an automatic music function, user just can be preserved a first one's own song by the lyrics uploading oneself creation and is shared with good friend.
Embodiment two
The present embodiment, on the basis of above-described embodiment, provides the preferred version obtained with this operation of song of described text feature information matches, is specifically optimized for and obtains the song with described text feature information matches from the song data library lookup set up in advance.
Refer to Fig. 2, obtain specifically comprising with the method for the song of described text feature information matches from the song data library lookup set up in advance in the method for the generation song that the present embodiment provides: operate 210 ~ operate 240.
In operation 210, in the song database set up in advance, search at least two songs obtained with described text feature information matches.
The technical scheme of the present embodiment comprises off-line part and online part, and wherein, the groundwork of off-line part is the collection of song, feature extraction, and the structure of song database.The groundwork of online part is: the text receiving user's input, and extracts the text feature information of described text; The song of mating most with described text feature information is searched from the described song database set up in advance; Using text as the new lyrics, and utilize dubbing in background music and the control information such as beat and/or musical note of the song of mating most, by speech synthesis technique, generate song.
This operation specifically first off-line build storehouse, namely set up song database in advance, then On-line matching, in the song database set up in advance, also namely search at least two songs obtained with described text feature information matches.
In operation 220, determine the syllable characteristic of described text respectively according to the music score of Chinese operas of described at least two songs.
With the text of aforementioned Fig. 1 b and aforementioned user input, " the waning city of lights is brilliant, and bustling with activity people's boiling is as sea." be described for example." the waning city of lights is brilliant, and bustling with activity people's boiling is as sea for text user inputted." carry out sentence cutting process, obtain the first subordinate sentence that described text packets contains " lights waning city brilliant " and the second subordinate sentence " bustling with activity people's boiling is as sea ", thus the sentence characteristics of text as shown in table 1 can be obtained.
It should be noted that, if the character quantity that each subordinate sentence of text comprises is fewer, so using the sentence characteristics of text as text feature information, thus the song with described text feature information matches can be obtained, if the character quantity that each subordinate sentence of text comprises is many, may cause using the sentence characteristics of text as text feature information, coupling is less than suitable song, now, need to carry out the cutting of phrase fragment to each subordinate sentence, obtain the complete phrase fragment of semanteme that each subordinate sentence comprises (such as, the first phrase fragment " city that lights are waning " that first subordinate sentence comprises and the second phrase fragment " brilliant "), thus according to extracting the similar mode of the sentence characteristics of text, extract the feature (as shown in table 3) of each phrase fragment, such as, the character quantity of each phrase fragment, the simple or compound vowel of a Chinese syllable and tone etc. of each word in each phrase fragment, using the feature of each phrase fragment as text feature information, thus obtain the song with described text feature information matches, improve song and be matched to power.It should be noted that, the function class of the phrase segment characterizations of text and the sentence characteristics of text seemingly, is all to obtain the song with text feature information matches.
Table 3
Suppose that the song shown in Fig. 1 b is and the wherein song at least two songs of the characteristic matching of described phrase fragment.
As shown in Figure 1 b, the lyrics of this song comprise two-layer, ground floor starts from " do not ask; do not say, All is understood, and no word are necessary ", to " fearness be only afraid of tear cunning gently " end, the second layer starts from " how much worrying; how much sorrow, the unavoidable bitter and pain of life ", terminates to " cold-peace focus drop drops in the heart ".The ground floor lyrics identical music score of Chinese operas corresponding to the second layer lyrics, the numbers and symbols combination specifically above the lyrics.The syllable characteristic of the described text determined according to the music score of Chinese operas of this song is as shown in table 4.It should be noted that, the syllable characteristic of described text can comprise at least one in the tone of lead-in in the simple or compound vowel of a Chinese syllable of lead-in in the character quantity of syllable, syllable and syllable.
Table 4
Table 5 is the part syllable characteristic of song " blessing ".
Table 5
In operation 230, according to the syllable characteristic of described text, what calculate described text and described at least two songs respectively mates total score.
In operation 240, mate the highest song of total score by described at least two songs, as the song with described text feature information matches.
It should be noted that, with the syllable characteristic of different texts and the character pair of song, the effect of the new song obtained is different.Such as, " character quantity of syllable " corresponding with song with " character quantity of syllable " in the syllable characteristic of text mates, and obtain the subordinate sentence number of words that the song that the match is successful can be good at compatible text, timing is relatively good; And for example, the simple or compound vowel of a Chinese syllable of lead-in " in the syllable " corresponding with song with the simple or compound vowel of a Chinese syllable of lead-in " in the syllable " in the syllable characteristic of text mates, and obtains the song that the match is successful and can be good at the rhythm corresponding to the simple or compound vowel of a Chinese syllable of the lead-in of compatible text.
The technical scheme of the present embodiment, comprises off-line part and online part, first by gathering song and characteristic of correspondence, builds with the off-line realizing song database, then receive the text of user's input online, and extract the text feature information of described text, the how first song with described text feature information matches is searched from the described song database set up in advance, the preliminary screening of song by text feature information realization, and the syllable characteristic of text is determined respectively by the music score of Chinese operas of each song, the described text obtained based on syllable characteristic mates total score with each song, thus the song of mating most with described text can be filtered out further, by the music as a setting of dubbing in background music by the song of mating most, and using described text as the new lyrics corresponding to described background music, and pass through phonetic synthesis, user is without the need to possessing the music theory knowledge of system, the text automatic music composing of user's input can be embodied as, improve the effect of the new song obtained further.
As a kind of concrete embodiment of operation 230, according to aforementioned hypothesis, suppose that the song shown in Fig. 1 b is the wherein song at least two songs of mating with the phrase segment characterizations of described text, therefore the syllable characteristic of the lyrics in the syllable characteristic of the text shown in table 4 and the song " blessing " shown in table 5 can be mated respectively, thus the text obtaining user's input and the song " blessing " in described at least two songs mate total score.Similarly, text and other songs in described at least two songs that can obtain user's input separately mate total score.
Further, according to described syllable characteristic, what calculate described text and described at least two songs respectively mates total score, preferably includes:
What calculate described text and described at least two songs according to the following equation respectively mates total score:
Wherein, Q represents described text; Arbitrary song at least two songs described in S represents; What Score (Q, S) represented described text and described arbitrary song mates total score; F
i(Q, S) represents the matching degree of i-th feature of described text and the character pair of described arbitrary song; λ
irepresent the weight that described i-th feature is corresponding; I-th feature of described text is the syllable characteristic of described text, specifically can comprise at least one in the tone of lead-in in the simple or compound vowel of a Chinese syllable of lead-in in the character quantity of syllable in text, syllable and syllable.
Such as, the matching degree F of the character quantity of syllable in described text and the character quantity of the middle syllable of song " blessing " is calculated
1(Q, S), the matching degree F of the simple or compound vowel of a Chinese syllable of lead-in in syllable in the simple or compound vowel of a Chinese syllable of lead-in and song " blessing " in syllable in described text
2(Q, S), and the matching degree F of the tone of lead-in in syllable in the tone of lead-in and song " blessing " in syllable in described text
3(Q, S), then passes through the weight λ that the character quantity of syllable in text is corresponding
1, the weight λ that in syllable, the simple or compound vowel of a Chinese syllable of lead-in is corresponding
2with weight λ corresponding in the tone of lead-in in syllable
3, thus obtain text and the song " blessing " of user's input mate total score.
As previously mentioned, with the syllable characteristic of different texts and the character pair of song, the effect of the new song obtained is different.
This preferred embodiment, after the matching degree of the character pair of the syllable characteristic and song that calculate different texts, by controlling weight corresponding to different syllable characteristics, the music effect that syllable characteristic that in the new song obtained, weight is higher is corresponding can be strengthened, weaken the music effect that the lower syllable characteristic of weight is corresponding simultaneously, be conducive to the effect of the new music controlling with becoming more meticulous to obtain.
As the embodiment that the another kind of operation 230 is concrete, according to aforementioned explanation, the function class of the phrase segment characterizations of text and the sentence characteristics of text seemingly, all to obtain the song with text feature information matches, therefore for user input text and song " blessing " for, the syllable characteristic of the text shown in table 4 can be mated respectively with the syllable characteristic of the lyrics in the song " blessing " shown in table 5, and the phrase segment characterizations of the text shown in table 3 is mated respectively with the sentence characteristics of the lyrics in the song " blessing " shown in table 1, thus obtain text and the song " blessing " in described at least two songs of user's input mate total score.Similarly, text and other songs in described at least two songs that can obtain user's input separately mate total score.
What preferably calculate described text and described at least two songs according to the following equation respectively mates total score:
Wherein, Q represents described text; Arbitrary song at least two songs described in S represents; What Score (Q, S) represented described text and described arbitrary song mates total score; F
i(Q, S) represents the matching degree of i-th feature of described text and the character pair of described arbitrary song; λ
irepresent the weight that described i-th feature is corresponding; I-th feature of described text is text feature corresponding to the syllable characteristic of described text and described text feature information, and specific in this example, i-th feature of described text is the syllable characteristic of described text and the phrase segment characterizations of described text.
The difference of present embodiment and above-mentioned embodiment is, the scope calculating i-th feature of the described text of coupling total score is different, specifically, in above-mentioned embodiment, the scope of i-th feature of described text is the syllable characteristic of described text, in present embodiment, the scope of i-th feature of described text is text feature corresponding to the syllable characteristic of described text and described text feature information.Correspondingly, in the present embodiment, more feature weight can be controlled, be conducive to the effect of the new music controlling with becoming more meticulous further to obtain.
In above-mentioned two kinds of embodiments, the matching degree F of i-th feature of described text and the character pair of described arbitrary song
i(Q, S) can be determined by following formula:
F
i(Q,S)＝EditDistance(Q
i,S
i)
Wherein, EditDistance (Q
i, S
i) be the editing distance between i-th feature of described text and the character pair of described arbitrary song.
In embodiments of the present invention, each feature is in fact all a digital sequence, and wherein, rhythm auxiliary sequence can be converted into Serial No. by the method for numbering.Each feature when comparing the text of user's input and song, be actually the comparison of two Serial No.s, therefore can be calculated the matching degree of character pair in arbitrary feature and song in text by the mode of editing distance.
In the present embodiment, the foundation of described song database, can comprise:
Obtain the song information of song and correspondence, wherein, described song information comprises: the lyrics and the music score of Chinese operas, also comprises at least one feature in the sentence characteristics of the lyrics and the syllable characteristic of the music score of Chinese operas;
By the song of acquisition and corresponding song information corresponding stored, obtain described song database.
Wherein, the sentence characteristics of the described lyrics can comprise:
At least one item in the simple or compound vowel of a Chinese syllable that in the character quantity of every lyrics, every lyrics, each word is corresponding and the tone of each word.
Example in embodiment one and embodiment two describes in detail, repeats no more.
Embodiment three
Refer to Fig. 3, a kind of device generating song that the present embodiment provides comprises: received text module 310, characteristic extracting module 320, matching module 330 and voice synthetic module 340.
Wherein, received text module 310 is for receiving the text of user's input; Characteristic extracting module 320 is for extracting the text feature information of described text; Matching module 330 is for obtaining the song with described text feature information matches; Voice synthetic module 340, for carrying out phonetic synthesis process according to described song to described text, obtains the new song that the lyrics are described text.
The technical scheme of the present embodiment, after the text receiving user's input, by extracting the text feature information of text, and described text feature information is mated with the corresponding informance of the lyrics of existing song, thus the song with described text feature information matches can be obtained, by the music as a setting of dubbing in background music by the song that the match is successful, and using described text as the new lyrics corresponding to described background music, and pass through phonetic synthesis, user, without the need to possessing the music theory knowledge of system, can be embodied as the text automatic music composing of user's input.
In such scheme, described characteristic extracting module 320 preferably includes: sentence cutting submodule and feature extraction submodule.
Wherein, the described text that sentence cutting submodule is used for described received text module receives carries out sentence cutting process, obtains the subordinate sentence that described text packets contains; The sentence characteristics of subordinate sentence of feature extraction submodule for extracting described text packets and containing.
Further, described feature extraction submodule specifically may be used for: extract at least one in the character quantity of the subordinate sentence that described text packets contains, described subordinate sentence in the simple or compound vowel of a Chinese syllable of each word and the tone of each word.
In such scheme, described matching module 330 specifically may be used for: obtain the song with described text feature information matches from the song data library lookup set up in advance.
Described matching module 330 specifically can comprise: song is searched submodule, feature determination submodule, mark calculating sub module and coupling and determined submodule.
Wherein, song searches submodule for searching at least two songs obtained with described text feature information matches in the song database set up in advance; Feature determination submodule is used for the syllable characteristic determining described text according to the music score of Chinese operas of described at least two songs respectively; Mark calculating sub module is used for according to the syllable characteristic of described text, and what calculate described text and described at least two songs respectively mates total score; Coupling determines that submodule is for mating the highest song of total score by described at least two songs, as the song with described text feature information matches.
Further, described mark calculating sub module specifically may be used for, and what calculate described text and described at least two songs according to the following equation respectively mates total score:
Wherein, Q represents described text; Arbitrary song at least two songs described in S represents; What Score (Q, S) represented described text and described arbitrary song mates total score; F
i(Q, S) represents the matching degree of i-th feature of described text and the character pair of described arbitrary song; λ
irepresent the weight that described i-th feature is corresponding; I-th feature of described text can be described syllable characteristic, or is text feature corresponding to described syllable characteristic and described text feature information.
Further, the matching degree F of i-th feature of described text and the character pair of described arbitrary song
i(Q, S) can be determined by following formula:
F
i(Q,S)＝EditDistance(Q
i,S
i)
Wherein, EditDistance (Q
i, S
i) be the editing distance between i-th feature of described text and the character pair of described arbitrary song.
In such scheme, described device can also comprise: module is set up in song acquisition module and storehouse.
Wherein, song acquisition module is for obtaining the song information of song and correspondence, and wherein, described song information comprises: the lyrics and the music score of Chinese operas, also comprises at least one feature in the sentence characteristics of the lyrics and the syllable characteristic of the music score of Chinese operas; Module is set up for by the song of described song acquisition module acquisition and corresponding song information corresponding stored in storehouse, obtains described song database.
Wherein, the sentence characteristics of the described lyrics can comprise: at least one item in the simple or compound vowel of a Chinese syllable that in the character quantity of every lyrics, every lyrics, each word is corresponding and the tone of each word.
In such scheme, described voice synthetic module 340 specifically may be used for: when carrying out phonetic synthesis process, by the music as a setting of dubbing in background music of described song, and the voice of corresponding beat are generated according to described music score of Chinese operas information, or the voice of corresponding beat and pitch are generated according to described music score of Chinese operas information, obtain described new song, the word content of described voice is described text.
The device of the generation song that the embodiment of the present invention provides can perform the method for the generation song that any embodiment of the present invention provides, and possesses the corresponding function module and the beneficial effect of manner of execution.
Last it is noted that above each embodiment is only for illustration of technical scheme of the present invention, but not be limited; In embodiment preferred embodiment, be not limited, to those skilled in the art, the present invention can have various change and change.All do within spirit of the present invention and principle any amendment, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (20)
1. generate a method for song, it is characterized in that, comprising:
Receive the text of user's input;
Extract the text feature information of described text;
Obtain the song with described text feature information matches;
According to described song, phonetic synthesis process is carried out to described text, obtain the new song that the lyrics are described text.
2. method according to claim 1, is characterized in that, extracts the text feature information of described text, comprising:
Sentence cutting process is carried out to described text, obtains the subordinate sentence that described text packets contains;
Extract the sentence characteristics of the subordinate sentence that described text packets contains.
3. method according to claim 2, is characterized in that, extracts the sentence characteristics of the subordinate sentence that described text packets contains, comprising:
Extract at least one in the character quantity of the subordinate sentence that described text packets contains, described subordinate sentence in the simple or compound vowel of a Chinese syllable of each word and the tone of each word.
4. method according to claim 1, is characterized in that, obtains the song with described text feature information matches, comprising:
The song with described text feature information matches is obtained from the song data library lookup set up in advance.
5. method according to claim 4, is characterized in that, obtains, with the song of described text feature information matches, comprising from the song data library lookup set up in advance:
At least two songs obtained with described text feature information matches are searched in the song database set up in advance;
The syllable characteristic of described text is determined respectively according to the music score of Chinese operas of described at least two songs;
According to the syllable characteristic of described text, what calculate described text and described at least two songs respectively mates total score;
The highest song of total score is mated, as the song with described text feature information matches by described at least two songs.
6. method according to claim 5, is characterized in that, according to described syllable characteristic, what calculate described text and described at least two songs respectively mates total score, comprising:
What calculate described text and described at least two songs according to the following equation respectively mates total score:
Wherein, Q represents described text; Arbitrary song at least two songs described in S represents; What Score (Q, S) represented described text and described arbitrary song mates total score; F
i(Q, S) represents the matching degree of i-th feature of described text and the character pair of described arbitrary song; λ
irepresent the weight that described i-th feature is corresponding; I-th feature of described text is described syllable characteristic, or is text feature corresponding to described syllable characteristic and described text feature information.
7. method according to claim 6, is characterized in that, the matching degree F of i-th feature of described text and the character pair of described arbitrary song
i(Q, S) is determined by following formula:
F
i(Q,S)＝EditDistance(Q
i,S
i)
Wherein, EditDistance (Q
i, S
i) be the editing distance between i-th feature of described text and the character pair of described arbitrary song.
8. method according to claim 4, is characterized in that, the foundation of described song database, comprising:
Obtain the song information of song and correspondence, wherein, described song information comprises: the lyrics and the music score of Chinese operas, also comprises at least one feature in the sentence characteristics of the lyrics and the syllable characteristic of the music score of Chinese operas;
By the song of acquisition and corresponding song information corresponding stored, obtain described song database.
9. method according to claim 8, is characterized in that, the sentence characteristics of the described lyrics comprises:
At least one item in the simple or compound vowel of a Chinese syllable that in the character quantity of every lyrics, every lyrics, each word is corresponding and the tone of each word.
10., according to the arbitrary described method of claim 1-9, it is characterized in that, according to described song, phonetic synthesis process is carried out to described text, obtain the new song that the lyrics are described text, comprising:
When carrying out phonetic synthesis process, by the music as a setting of dubbing in background music of described song, and generate the voice of corresponding beat according to described music score of Chinese operas information, or generate the voice of corresponding beat and pitch according to described music score of Chinese operas information, obtain described new song, the word content of described voice is described text.
11. 1 kinds of devices generating song, is characterized in that, comprising:
Received text module, for receiving the text of user's input;
Characteristic extracting module, for extracting the text feature information of described text;
Matching module, for obtaining the song with described text feature information matches;
Voice synthetic module, for carrying out phonetic synthesis process according to described song to described text, obtains the new song that the lyrics are described text.
12. devices according to claim 11, is characterized in that, described characteristic extracting module comprises:
Sentence cutting submodule, carries out sentence cutting process for the described text received described received text module, obtains the subordinate sentence that described text packets contains;
Feature extraction submodule, for extracting the sentence characteristics of the subordinate sentence that described text packets contains.
13. devices according to claim 12, is characterized in that, described feature extraction submodule, specifically for: extract at least one in the character quantity of the subordinate sentence that described text packets contains, described subordinate sentence in the simple or compound vowel of a Chinese syllable of each word and the tone of each word.
14. devices according to claim 11, is characterized in that, described matching module specifically for: obtain the song with described text feature information matches from the song data library lookup set up in advance.
15. devices according to claim 14, is characterized in that, described matching module specifically comprises:
Song searches submodule, for searching at least two songs obtained with described text feature information matches in the song database set up in advance;
Feature determination submodule, for determining the syllable characteristic of described text respectively according to the music score of Chinese operas of described at least two songs;
Mark calculating sub module, for the syllable characteristic according to described text, what calculate described text and described at least two songs respectively mates total score;
Coupling determines submodule, for mating the highest song of total score by described at least two songs, as the song with described text feature information matches.
16. devices according to claim 15, is characterized in that, described mark calculating sub module specifically for, what calculate described text and described at least two songs according to the following equation respectively mates total score:
Wherein, Q represents described text; Arbitrary song at least two songs described in S represents; What Score (Q, S) represented described text and described arbitrary song mates total score; F
i(Q, S) represents the matching degree of i-th feature of described text and the character pair of described arbitrary song; λ
irepresent the weight that described i-th feature is corresponding; I-th feature of described text is described syllable characteristic, or is text feature corresponding to described syllable characteristic and described text feature information.
17. devices according to claim 16, is characterized in that, the matching degree F of i-th feature of described text and the character pair of described arbitrary song
i(Q, S) is determined by following formula:
F
i(Q,S)＝EditDistance(Q
i,S
i)
Wherein, EditDistance (Q
i, S
i) be the editing distance between i-th feature of described text and the character pair of described arbitrary song.
18. devices according to claim 14, is characterized in that, described device also comprises:
Song acquisition module, for obtaining the song information of song and correspondence, wherein, described song information comprises: the lyrics and the music score of Chinese operas, also comprises at least one feature in the sentence characteristics of the lyrics and the syllable characteristic of the music score of Chinese operas;
Module is set up in storehouse, for by the song of described song acquisition module acquisition and corresponding song information corresponding stored, obtains described song database.
19. devices according to claim 18, is characterized in that, the sentence characteristics of the described lyrics comprises:
At least one item in the simple or compound vowel of a Chinese syllable that in the character quantity of every lyrics, every lyrics, each word is corresponding and the tone of each word.
20., according to the arbitrary described device of claim 11-19, is characterized in that, described voice synthetic module specifically for:
When carrying out phonetic synthesis process, by the music as a setting of dubbing in background music of described song, and generate the voice of corresponding beat according to described music score of Chinese operas information, or generate the voice of corresponding beat and pitch according to described music score of Chinese operas information, obtain described new song, the word content of described voice is described text.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410743457.1A CN104391980B (en) | 2014-12-08 | 2014-12-08 | The method and apparatus for generating song |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410743457.1A CN104391980B (en) | 2014-12-08 | 2014-12-08 | The method and apparatus for generating song |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104391980A true CN104391980A (en) | 2015-03-04 |
| CN104391980B CN104391980B (en) | 2019-03-08 |
Family
ID=52609884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410743457.1A Active CN104391980B (en) | 2014-12-08 | 2014-12-08 | The method and apparatus for generating song |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104391980B (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN105096962A (en) * | 2015-05-22 | 2015-11-25 | 努比亚技术有限公司 | Information processing method and terminal |
| CN105513607A (en) * | 2015-11-25 | 2016-04-20 | 网易传媒科技（北京）有限公司 | Method and apparatus for music composition and lyric writing |
| CN105740394A (en) * | 2016-01-27 | 2016-07-06 | 广州酷狗计算机科技有限公司 | Music generation method, terminal, and server |
| CN106339152A (en) * | 2016-08-30 | 2017-01-18 | 维沃移动通信有限公司 | Generation method of lyrics poster and mobile terminal |
| CN106373580A (en) * | 2016-09-05 | 2017-02-01 | 北京百度网讯科技有限公司 | Singing synthesis method based on artificial intelligence and device |
| CN106557298A (en) * | 2016-11-08 | 2017-04-05 | 北京光年无限科技有限公司 | Background towards intelligent robot matches somebody with somebody sound outputting method and device |
| CN106776517A (en) * | 2016-12-20 | 2017-05-31 | 科大讯飞股份有限公司 | Automatic compose poem method and apparatus and system |
| CN106898341A (en) * | 2017-01-04 | 2017-06-27 | 清华大学 | A kind of individualized music generation method and device based on common semantic space |
| 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 |
| CN107799119A (en) * | 2016-09-07 | 2018-03-13 | 中兴通讯股份有限公司 | Audio preparation method, apparatus and system |
| WO2018121368A1 (en) * | 2016-12-30 | 2018-07-05 | 阿里巴巴集团控股有限公司 | Method for generating music to accompany lyrics and related apparatus |
| CN108428441A (en) * | 2018-02-09 | 2018-08-21 | 咪咕音乐有限公司 | Multimedia file producting method, electronic equipment and storage medium |
| CN108765162A (en) * | 2018-05-10 | 2018-11-06 | 阿里巴巴集团控股有限公司 | A kind of finance data output method, device and electronic equipment |
| CN108877753A (en) * | 2018-06-15 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Music synthesis method and system, terminal and computer readable storage medium |
| WO2018232623A1 (en) * | 2017-06-21 | 2018-12-27 | Microsoft Technology Licensing, Llc | Providing personalized songs in automated chatting |
| CN109166564A (en) * | 2018-07-19 | 2019-01-08 | 平安科技（深圳）有限公司 | For the method, apparatus and computer readable storage medium of lyrics text generation melody |
| CN109241312A (en) * | 2018-08-09 | 2019-01-18 | 广东数相智能科技有限公司 | Compose a poem to a given tune of ci method, apparatus and the terminal device of melody |
| CN109493845A (en) * | 2019-01-02 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | For generating the method and device of audio |
| CN109599079A (en) * | 2017-09-30 | 2019-04-09 | 腾讯科技（深圳）有限公司 | A kind of generation method and device of music |
| CN109643533A (en) * | 2016-06-30 | 2019-04-16 | 莱福思科有限公司 | Device and method for unit composition |
| CN109801618A (en) * | 2017-11-16 | 2019-05-24 | 深圳市腾讯计算机系统有限公司 | A kind of generation method and device of audio-frequency information |
| 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 |
| CN110097886A (en) * | 2019-04-29 | 2019-08-06 | 贵州小爱机器人科技有限公司 | Intension recognizing method and device, storage medium, terminal |
| CN110516110A (en) * | 2019-07-22 | 2019-11-29 | 平安科技（深圳）有限公司 | Song generation method, device, computer equipment and storage medium |
| WO2020000751A1 (en) * | 2018-06-29 | 2020-01-02 | 平安科技（深圳）有限公司 | Automatic composition method and apparatus, and computer device and storage medium |
| CN110852093A (en) * | 2018-07-26 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Text information generation method and device, computer equipment and storage medium |
| CN111339352A (en) * | 2020-01-22 | 2020-06-26 | 华为技术有限公司 | Audio generation method and device 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 |
| CN112420008A (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 recording songs, electronic equipment and storage medium |
| CN113282270A (en) * | 2021-06-25 | 2021-08-20 | 杭州网易云音乐科技有限公司 | Music gift generation method, music gift display method and device, medium and computing equipment |
| CN109522427B (en) * | 2018-09-30 | 2021-12-10 | 北京光年无限科技有限公司 | Intelligent robot-oriented story data processing method and device |
| CN113793578A (en) * | 2021-08-12 | 2021-12-14 | 咪咕音乐有限公司 | Tune generation method, device, equipment and computer readable storage medium |
| CN111339352B (en) * | 2020-01-22 | 2024-04-26 | 花瓣云科技有限公司 | Audio generation method, device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002262348A (en) * | 2001-02-27 | 2002-09-13 | Matsushita Electric Ind Co Ltd | Authentication system and mobile phone with card function |
| CN1584979A (en) * | 2004-06-01 | 2005-02-23 | 安徽中科大讯飞信息科技有限公司 | Method for outputting mixed with background sound and text sound in speech synthetic system |
| US20090306987A1 (en) * | 2008-05-28 | 2009-12-10 | National Institute Of Advanced Industrial Science And Technology | Singing synthesis parameter data estimation system |
| CN101694772A (en) * | 2009-10-21 | 2010-04-14 | 北京中星微电子有限公司 | Method for converting text into rap music and device thereof |
| 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 |
| CN102053998A (en) * | 2009-11-04 | 2011-05-11 | 周明全 | Method and system device for retrieving songs based on voice modes |
| CN102193992A (en) * | 2010-03-11 | 2011-09-21 | 姜胡彬 | System and method for generating custom songs |
| CN102201233A (en) * | 2011-05-20 | 2011-09-28 | 北京捷通华声语音技术有限公司 | Mixed and matched speech synthesis method and system thereof |
| US20140174279A1 (en) * | 2012-12-21 | 2014-06-26 | The Hong Kong University Of Science And Technology | Composition using correlation between melody and lyrics |
-
2014
- 2014-12-08 CN CN201410743457.1A patent/CN104391980B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002262348A (en) * | 2001-02-27 | 2002-09-13 | Matsushita Electric Ind Co Ltd | Authentication system and mobile phone with card function |
| CN1584979A (en) * | 2004-06-01 | 2005-02-23 | 安徽中科大讯飞信息科技有限公司 | Method for outputting mixed with background sound and text sound in speech synthetic system |
| US20090306987A1 (en) * | 2008-05-28 | 2009-12-10 | National Institute Of Advanced Industrial Science And Technology | Singing synthesis parameter data estimation system |
| CN101694772A (en) * | 2009-10-21 | 2010-04-14 | 北京中星微电子有限公司 | Method for converting text into rap music and device thereof |
| CN102053998A (en) * | 2009-11-04 | 2011-05-11 | 周明全 | Method and system device for retrieving songs based on voice modes |
| CN102193992A (en) * | 2010-03-11 | 2011-09-21 | 姜胡彬 | System and method for generating custom songs |
| 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 |
| CN102201233A (en) * | 2011-05-20 | 2011-09-28 | 北京捷通华声语音技术有限公司 | Mixed and matched speech synthesis method and system thereof |
| US20140174279A1 (en) * | 2012-12-21 | 2014-06-26 | The Hong Kong University Of Science And Technology | Composition using correlation between melody and lyrics |
Non-Patent Citations (2)
| Title |
|---|
| YUNG-JI SHER ET AL.: ""Develop a HMM-based Taiwanese text-to-speech system"", 《2010 2ND INTERNATIONAL CONFERENCE ON SOFTWARE TECHNOLOGY AND ENGINEERING》 * |
| 诗词家园: ""格律匹配"", 《HTTP://WWW.SHICIJIAYUAN.COM/MARCH.ASP》 * |
Cited By (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096962A (en) * | 2015-05-22 | 2015-11-25 | 努比亚技术有限公司 | Information processing method and terminal |
| CN105096962B (en) * | 2015-05-22 | 2019-04-16 | 努比亚技术有限公司 | A kind of information processing method and terminal |
| 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 |
| CN105513607B (en) * | 2015-11-25 | 2019-05-17 | 网易传媒科技（北京）有限公司 | A kind of method and apparatus write words of setting a song to music |
| CN105513607A (en) * | 2015-11-25 | 2016-04-20 | 网易传媒科技（北京）有限公司 | Method and apparatus for music composition and lyric writing |
| CN105740394A (en) * | 2016-01-27 | 2016-07-06 | 广州酷狗计算机科技有限公司 | Music generation method, terminal, and server |
| CN109643533A (en) * | 2016-06-30 | 2019-04-16 | 莱福思科有限公司 | Device and method for unit composition |
| CN109643533B (en) * | 2016-06-30 | 2022-11-08 | 莱福思科有限公司 | Apparatus and method for unit composition |
| CN106339152B (en) * | 2016-08-30 | 2019-10-15 | 维沃移动通信有限公司 | A kind of generation method and mobile terminal of lyrics poster |
| CN106339152A (en) * | 2016-08-30 | 2017-01-18 | 维沃移动通信有限公司 | Generation method of lyrics poster and mobile terminal |
| CN106373580B (en) * | 2016-09-05 | 2019-10-15 | 北京百度网讯科技有限公司 | The method and apparatus of synthesis song based on artificial intelligence |
| CN106373580A (en) * | 2016-09-05 | 2017-02-01 | 北京百度网讯科技有限公司 | Singing synthesis method based on artificial intelligence and device |
| CN107799119A (en) * | 2016-09-07 | 2018-03-13 | 中兴通讯股份有限公司 | Audio preparation method, apparatus and system |
| CN106557298A (en) * | 2016-11-08 | 2017-04-05 | 北京光年无限科技有限公司 | Background towards intelligent robot matches somebody with somebody sound outputting method and device |
| CN106776517A (en) * | 2016-12-20 | 2017-05-31 | 科大讯飞股份有限公司 | Automatic compose poem method and apparatus and system |
| CN106776517B (en) * | 2016-12-20 | 2020-07-14 | 科大讯飞股份有限公司 | Automatic poetry method, device and system |
| CN108268530A (en) * | 2016-12-30 | 2018-07-10 | 阿里巴巴集团控股有限公司 | Dub in background music generation method and the relevant apparatus of a kind of lyrics |
| 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 |
| WO2018121368A1 (en) * | 2016-12-30 | 2018-07-05 | 阿里巴巴集团控股有限公司 | Method for generating music to accompany lyrics and related apparatus |
| CN106898341A (en) * | 2017-01-04 | 2017-06-27 | 清华大学 | A kind of individualized music generation method and device based on common semantic space |
| 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 |
| WO2018232623A1 (en) * | 2017-06-21 | 2018-12-27 | Microsoft Technology Licensing, Llc | Providing personalized songs in automated chatting |
| US11587541B2 (en) * | 2017-06-21 | 2023-02-21 | Microsoft Technology Licensing, Llc | Providing personalized songs in automated chatting |
| CN109716326A (en) * | 2017-06-21 | 2019-05-03 | 微软技术许可有限责任公司 | Personalized song is provided in automatic chatting |
| CN109599079B (en) * | 2017-09-30 | 2022-09-23 | 腾讯科技（深圳）有限公司 | Music generation method and device |
| CN109599079A (en) * | 2017-09-30 | 2019-04-09 | 腾讯科技（深圳）有限公司 | A kind of generation method and device of music |
| CN109801618A (en) * | 2017-11-16 | 2019-05-24 | 深圳市腾讯计算机系统有限公司 | A kind of generation method and device of audio-frequency information |
| 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 |
| CN108428441A (en) * | 2018-02-09 | 2018-08-21 | 咪咕音乐有限公司 | Multimedia file producting method, electronic equipment and storage medium |
| CN108765162A (en) * | 2018-05-10 | 2018-11-06 | 阿里巴巴集团控股有限公司 | A kind of finance data output method, device and electronic equipment |
| CN108877753B (en) * | 2018-06-15 | 2020-01-21 | 百度在线网络技术（北京）有限公司 | Music synthesis method and system, terminal and computer readable storage medium |
| CN108877753A (en) * | 2018-06-15 | 2018-11-23 | 百度在线网络技术（北京）有限公司 | Music synthesis method and system, terminal and computer readable storage medium |
| US10971125B2 (en) | 2018-06-15 | 2021-04-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Music synthesis method, system, terminal and computer-readable storage medium |
| WO2020000751A1 (en) * | 2018-06-29 | 2020-01-02 | 平安科技（深圳）有限公司 | Automatic composition method and apparatus, and computer device and storage medium |
| CN109166564A (en) * | 2018-07-19 | 2019-01-08 | 平安科技（深圳）有限公司 | For the method, apparatus and computer readable storage medium of lyrics text generation melody |
| CN110852093A (en) * | 2018-07-26 | 2020-02-28 | 腾讯科技（深圳）有限公司 | Text information generation method and device, computer equipment and storage medium |
| CN109241312A (en) * | 2018-08-09 | 2019-01-18 | 广东数相智能科技有限公司 | Compose a poem to a given tune of ci method, apparatus and the terminal device of melody |
| CN109241312B (en) * | 2018-08-09 | 2021-08-31 | 广东数相智能科技有限公司 | Melody word filling method and device and terminal equipment |
| CN109522427B (en) * | 2018-09-30 | 2021-12-10 | 北京光年无限科技有限公司 | Intelligent robot-oriented story data processing method and device |
| CN109493845A (en) * | 2019-01-02 | 2019-03-19 | 百度在线网络技术（北京）有限公司 | For generating the method and device of audio |
| CN110097886A (en) * | 2019-04-29 | 2019-08-06 | 贵州小爱机器人科技有限公司 | Intension recognizing method and device, storage medium, terminal |
| CN110097886B (en) * | 2019-04-29 | 2021-09-10 | 贵州小爱机器人科技有限公司 | Intention recognition method and device, storage medium and terminal |
| CN112185321A (en) * | 2019-06-14 | 2021-01-05 | 微软技术许可有限责任公司 | Song generation |
| 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 |
| CN110516110A (en) * | 2019-07-22 | 2019-11-29 | 平安科技（深圳）有限公司 | Song generation method, device, computer equipment and storage medium |
| CN112420008A (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 recording songs, electronic equipment and storage medium |
| CN111339352A (en) * | 2020-01-22 | 2020-06-26 | 华为技术有限公司 | Audio generation method and device and storage medium |
| CN111339352B (en) * | 2020-01-22 | 2024-04-26 | 花瓣云科技有限公司 | Audio generation method, device and storage medium |
| CN113282270A (en) * | 2021-06-25 | 2021-08-20 | 杭州网易云音乐科技有限公司 | Music gift generation method, music gift display method and device, medium and computing equipment |
| CN113282270B (en) * | 2021-06-25 | 2024-01-26 | 杭州网易云音乐科技有限公司 | Music gift generation method, music gift display device, medium and computing device |
| CN113793578A (en) * | 2021-08-12 | 2021-12-14 | 咪咕音乐有限公司 | Tune generation method, device, equipment and computer readable storage medium |
| CN113793578B (en) * | 2021-08-12 | 2023-10-20 | 咪咕音乐有限公司 | Method, device and equipment for generating tune and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104391980B (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104391980A (en) | Song generating method and device | |
| CN108962217B (en) | Speech synthesis method and related equipment | |
| US10891928B2 (en) | Automatic song generation | |
| Agawu | Music as discourse: Semiotic adventures in romantic music | |
| CN108806655B (en) | Automatic generation of songs | |
| US20210158795A1 (en) | Generating audio for a plain text document | |
| JP2018537727A (en) | Automated music composition and generation machines, systems and processes employing language and / or graphical icon based music experience descriptors | |
| Schneider | Music and gestures: A historical introduction and survey of earlier research | |
| CN101504643A (en) | Speech processing system, speech processing method, and speech processing program | |
| CN109326280B (en) | Singing synthesis method and device and electronic equipment | |
| Duinker | Diversification and Post-Regionalism in North American Hip-Hop Flow | |
| Gibbon | Prosody: The rhythms and melodies of speech | |
| CN108922505B (en) | Information processing method and device | |
| CN116129868A (en) | Method and system for generating structured photo | |
| Le et al. | Emotional Vietnamese Speech Synthesis Using Style-Transfer Learning. | |
| Hunt | Composition as Commentary: Voice and Poetry in Electroacoustic Music | |
| Ekpenyong et al. | Towards an unrestricted domain TTS system for African tone languages | |
| Utz | The Rediscovery of Presence: Intercultural Passages through Vocal Spaces between Speech and Song 1 | |
| Laws | Beckett in New Musical Composition | |
| CN116645957B (en) | Music generation method, device, terminal, storage medium and program product | |
| Tarasti | Musical Semiotics–a Discipline, its History and Theories, Past and Present 1 | |
| Ninoshvili | The poetics of pop polyphony: Translating georgian Song for the World | |
| Andrews | Polyrhythmicity in Language, Music and Society | |
| Liu et al. | A model of extended paragraph vector for document categorization and trend analysis | |
| Essam | Melopoetics of the contemporary “National Anthem” of Egypt and its translations: A case study |
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 |