CN106898339A - The chorus method and terminal of a kind of song - Google Patents
The chorus method and terminal of a kind of song Download PDFInfo
- Publication number
- CN106898339A CN106898339A CN201710198662.8A CN201710198662A CN106898339A CN 106898339 A CN106898339 A CN 106898339A CN 201710198662 A CN201710198662 A CN 201710198662A CN 106898339 A CN106898339 A CN 106898339A
- Authority
- CN
- China
- Prior art keywords
- recommended
- target
- combination
- song
- user
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0033—Recording/reproducing or transmission of music for electrophonic musical instruments
-
- 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
- G06F16/686—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/72442—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality for playing music files
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of song chorus method, including:When carrying initiation chorus ID and song identity chorus instruction is received, the range type that the initiation is chorused corresponding to ID is obtained;Determined for singing at least one target sound field type that the corresponding target song of the song identity lacks according to the range type for initiating to chorus corresponding to ID;Target recommended user's identifier combination that acquisition is matched with least one target sound field type, and the target recommended user identifier combination is recommended into the corresponding user of the ID.The present invention also provides a kind of terminal.Using the present invention, the corresponding user of range type that may be such that terminal can be bad to user recommended user carries out choral song, effectively improves the effect of recording song.
Description
Technical field
The present invention relates to electronic technology field, more particularly to a kind of song chorus method and terminal.
Background technology
As communication and the high speed development of information technology, mobile phone are also increasingly popularized, its function also increasingly increases, various music
Class product also arises at the historic moment, particularly K song class music products, wherein, user can sing class and carry out recording song by K, and share
Recording song.
At present, user, when recording song is carried out by K song class music products, is mostly that user selects corresponding music companion
Playing and follow musical background and captions carries out performance recording.But, some users cause to use because itself performance level is not high
Family is unsatisfied with the song that it is recorded, and using K song class music products share the enthusiasm of recording song so as to reduce user.
The content of the invention
Embodiment of the present invention technical problem to be solved is, there is provided the chorus method and terminal of a kind of song.Can make
The corresponding user of range type that obtaining terminal can be bad to user recommended user carries out choral song, effectively improves recording song
Bent effect.
Embodiment of the present invention first aspect provides a kind of song chorus method, it may include:
When carrying initiation chorus ID and song identity chorus instruction is received, obtain the initiation and chorus
Range type corresponding to ID;
Determined according to the range type for initiating to chorus corresponding to ID for singing the song identity correspondence
At least one target sound field type for lacking of target song;
Target recommended user's identifier combination for being matched with least one target sound field type of acquisition, and by the target
Recommended user's identifier combination recommends the corresponding user of the ID, so that the target recommended user identifies corresponding use
Family at least one targeted customer corresponding with the target recommended user identifier combination chorus to the target song.
Embodiment of the present invention second aspect provides a kind of terminal, it may include:
Acquiring unit, for when carrying initiation chorus ID and song identity chorus instruction is received, obtaining
Take the range type initiated corresponding to chorus ID;
Determining unit, for according to it is described initiate chorus ID corresponding to range type determine for described in singing
At least one target sound field type that the corresponding target song of song identity lacks;
Recommendation unit, for obtaining the target recommended user's mark group matched with least one target sound field type
Close, and the target recommended user identifier combination is recommended into the corresponding user of the ID, so that the target is recommended
The corresponding user of ID at least one targeted customer corresponding with the target recommended user identifier combination is to the target
Song is chorused.
In embodiments of the present invention, refer to when terminal receives carrying initiation chorus ID and song identity chorus
When making, the range type initiated corresponding to chorus ID is obtained, initiate to chorus corresponding to ID according to described
Range type determine, for singing at least one target sound field type that the corresponding target song of the song identity lacks, to obtain
The target recommended user's identifier combination matched with least one target sound field type is taken, and the target recommended user is marked
Combined recommendation is known to the corresponding user of the ID, may be such that the range class that terminal can be bad to user recommended user
The corresponding user of type carries out choral song, effectively improves the effect of recording song.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of network architecture schematic diagram provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic flow sheet of song chorus method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of terminal provided in an embodiment of the present invention;
Fig. 4 is the structural representation of another terminal provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
A kind of song chorus method provided in an embodiment of the present invention can apply to the scene of terminal recording song.
In embodiments of the present invention, described terminal may include:Mobile phone, panel computer, palm PC or mobile mutual
Networked devices (Mobile Internet Device, MID) etc., above-mentioned terminal is only citing, and non exhaustive, including but not limited to
Above-mentioned terminal.
In order to be best understood from scheme disclosed in the embodiment of the present invention, the network architecture being first applicable the embodiment of the present invention below
It is described.Fig. 1 is referred to, Fig. 1 is a kind of network architecture schematic diagram disclosed in the embodiment of the present invention.In the network shown in Fig. 1
In framework, terminal and song server can be included, terminal can be attached by network with song server, terminal can be to
Song service request obtains data.
Based on the network architecture shown in Fig. 1, the embodiment of the invention discloses a kind of song chorus method.Below in conjunction with attached
Fig. 2, describes in detail to song provided in an embodiment of the present invention chorus method, wherein, the executive agent of embodiment is terminal.
It is a kind of song chorus a kind of embodiment schematic flow sheet of method provided in an embodiment of the present invention referring to Fig. 2.This hair
A kind of song chorus method of bright embodiment comprises the following steps:
S100, when carrying initiation chorus ID and song identity chorus instruction is received, obtains the hair
Play the range type corresponding to chorus ID.
In embodiments of the present invention, when initiation chorus user need to carry out chorus target song with other users, Yong Huke
ID is chorused by the initiation of terminal to operate generation chorus instruction for target song, wherein, chorus instruction can be carried
Initiate chorus ID and song identity, it can be user account to initiate chorus ID, song identity can be for
The identifier of unique mark target song, such as song title.When terminal receives chorus instruction, terminal can be used in preset
Obtained in the database of the performance voice data for storing user and initiate corresponding at least one the performance audio number of chorus ID
According to.Further, terminal can also obtain song mark in corresponding at least one the performance voice data of chorus ID is initiated
Know corresponding performance voice data, be that terminal can obtain initiation chorus in the database of the performance voice data of storage user
The performance voice data of the target song that user once sang, wherein, singing data can be data of singing opera arias.
In embodiments of the present invention, voice data is sung when terminal gets the corresponding target of initiation chorus ID
Afterwards, terminal can sing voice data and be analyzed to target, obtain the range type initiated corresponding to chorus ID, its
In, range type may include the range types such as high pitch type, bass type, middle pitch type and rap types.It is understood that
The step is for obtaining the range type that initiation chorus user is good at when target song is sung.
Specifically, terminal-pair target sings voice data being analyzed, the sound initiated corresponding to chorus ID is obtained
Field type can be specifically:First, terminal can sing voice data and be divided by preset at least one range type to target
Analysis, obtains the corresponding performance audio data fragment of every kind of range type.Specifically, terminal can obtain target sings voice data pair
The lyrics information answered, subordinate sentence is carried out to singing the every lyrics of the voice data as included by lyrics information, obtains every lyrics institute
Corresponding performance audio data fragment, and according to every preset lyrics and the corresponding relation of range type, obtain every kind of range
The corresponding performance audio data fragment of type.Secondly, when terminal obtains the corresponding performance audio data fragment of every kind of range type
Afterwards, terminal can be given a mark by preset code of points audio data fragment of singing corresponding to every kind of range type, be obtained
The corresponding fraction for singing audio data fragment of every kind of range type, wherein, the corresponding performance voice data of every kind of range type
The fraction of fragment can be with individual 0~100 point, certainly, if the corresponding multiple of range type sings audio data fragment, terminal can be adopted
The multiple marking fractions of marking acquisition are carried out respectively with code of points multiple performance audio data fragments corresponding to range type to ask
It is average again to obtain average, and using average as the corresponding fraction for singing audio data fragment of the music type, wherein,
Code of points can be the built-in singing marking rule of K song class music products.Specifically, when range type include high pitch type,
During four kinds of range types of bass type and rap types, then terminal will be processed and obtain 4 fractions, respectively fd (bass range classes
Type fraction), fg (high pitch range type scores), fr (rap ranges type scores) and fp (common range type scores).Finally,
Finally, terminal can obtain fraction the first pre-conditioned performance fraction of satisfaction in the corresponding performance fraction of every kind of range type,
And fraction the first pre-conditioned corresponding range type of performance fraction of satisfaction is set to the initiation chorus ID correspondence
Range type.Wherein, first it is pre-conditioned can be fraction highest sing fraction, or can also be fraction with other not
The performance fraction of the difference more than predetermined threshold value of the corresponding fraction of congener range type, specifically can be such as:Work as fd-fg>P2 and fd-
fr>During p2, terminal obtains the corresponding bass range types of fd and is set to initiate the corresponding range type of chorus ID;Work as fg-
fd>P2 and fg-fr>During p2, terminal obtains the corresponding high pitch range types of fg and is set to initiate the corresponding range of chorus ID
Type;Work as fr-fg>P2 and fr-fd>During p2, terminal obtains the corresponding rap ranges types of fr and is set to initiate chorus ID pair
The range type answered, wherein, p2 is predetermined threshold value.It is understood that initiate the corresponding range type of chorus ID can
Being to initiate the range type that the chorus corresponding user of ID is good at.
In embodiments of the present invention, every lyrics of terminal preset can be specifically with the corresponding relation of range type:First,
Terminal can obtain the corresponding music-book information of song identity, wherein, music-book information can be MIDI (Musical Instrument
Digital Interface, musical instrument digital interface) file, MIDI files include target song in each note it is initial when
Between and duration and each note pitch value, specifically, reference can be made to music-book information shown in following table one.
Table one
1863 | 201 | 0 |
2064 | 195 | 0 |
2259 | 270 | 0 |
2529 | 414 | 0 |
2943 | 165 | 0 |
3108 | 324 | 0 |
3707 | 385 | 56 |
Every a line shown in table one represents a note, and first is classified as the initial time of note, and unit is ms, and second is classified as
Note duration, unit is ms, and the 3rd is classified as note pitch value, wherein, pitch is that 0 expression note is rap.Secondly, eventually
End can obtain the corresponding lyrics information of target song, wherein, lyrics information includes lyrics character and corresponding of each character
Time beginning and duration.The lyrics information may include initial time and the duration of each lyrics character.Therefore, terminal can
Subordinate sentence is carried out to music-book information according to lyrics information, the music score letter corresponding to each lyrics included by lyrics information is obtained
Breath.Again, after terminal obtains the music-book information corresponding to each lyrics included by lyrics information, terminal can be to each sentence
Music-book information corresponding to the lyrics is analyzed, and sets the range type corresponding to each lyrics.Wherein, due to singing and can wrap
Include the range type such as high pitch, middle pitch, bass and rap, thus terminal can preset range type be the first range type, the second range
The range types such as type, the 3rd range type and the 4th range type, wherein, the first range type can be high pitch range class
Type, the second range type can be bass range type, and the 3rd range type can be common range type and the 4th range
Type can be rap range types.
In embodiments of the present invention, the music-book information corresponding to each lyrics of terminal-pair is analyzed, and sets each sentence
Range type corresponding to the lyrics can be specifically:Terminal can calculate the music-book information corresponding to each lyrics each song
The corresponding average pitch of word, when average pitch then sets the corresponding range type of this lyrics for high pitch more than preset first threshold value
Range type, the corresponding range type of this lyrics is then set for bass range class when average pitch is less than default Second Threshold
Type, the corresponding range type of this lyrics is then set when average pitch is 0 for rap range types, when average pitch belongs to it
The corresponding range type of then setting this lyrics of his scope is common range type.
In a particular application, the music-book information corresponding to each lyrics of terminal-pair is analyzed, and sets each lyrics
Corresponding range type can be specifically:To define the corresponding music-book information i of lyrics have a n note, and each note is held
The continuous time is tiI ∈ [1~n], the pitch of each note is piI ∈ [1~n], calculate the average pitch of eachThe corresponding range type of this lyrics is set if p > p0 (p0 is first threshold) for high pitch range class
Type, sets the corresponding range type of this lyrics for bass range type if p < p1 (p1 is Second Threshold), as p=0,
The corresponding range type of this lyrics is then set for rap range types, remaining many lyrics then sets corresponding range type
It is common range type.
S101, determines for singing the song identity according to the range type for initiating to chorus corresponding to ID
At least one target sound field type that corresponding target song lacks.
In embodiments of the present invention, general song all includes treble portion, bass part and rap parts, therefore, in order to carry
The expression effect of song high, the range type needed for the target song that terminal preset can give song recitals corresponding to mark includes high pitch
Range type, bass range type and rap range types.Or, terminal can also be divided from the music-book information for obtaining target song
Analysis music-book information, obtains at least one range type needed for for singing target song, specifically can such as, and terminal can also obtain mesh
The lyrics information of song is marked, every lyrics according to included by lyrics information obtain the music-book information piece corresponding to every lyrics
Section, the music-book information fragment corresponding to every lyrics of terminal-pair is analyzed range type, the corresponding range of every lyrics of acquisition
Type, so that terminal can obtain the range type included by music-book information.
In embodiments of the present invention, it is hair when terminal gets the range type initiated corresponding to chorus ID
Rise after chorus user is good at the range type of performance, to carry out chorus complementary with chorus user is initiated to need other users, since make up
The range type that user is bad at, therefore, terminal can be obtained except hair from least one range type needed for target song
Other range types risen outside the range type corresponding to chorus ID are to lack at least for singing target song
A kind of target sound field type.
S102, target recommended user's identifier combination for being matched with least one target sound field type of acquisition, and by institute
State target recommended user's identifier combination and recommend the corresponding user of the ID.
In embodiments of the present invention, terminal equally can initiate the corresponding range type of chorus ID according to above-mentioned acquisition
Mode, obtain the corresponding range type of other users mark.So as to terminal can be from the corresponding range of other users mark
At least one ID to be recommended that every kind of target sound field type is matched is obtained in type.
In embodiments of the present invention, when terminal gets at least one use to be recommended that every kind of target sound field type is matched
After the mark of family, the range type corresponding to every kind of target sound field type at least that terminal can be as needed for for singing target song
Individual ID and initiation chorus ID are combined, and obtain at least one ID combination to be recommended, wherein, it is every kind of
The included corresponding range type of ID to be recommended of ID combination to be recommended is constituted for singing the target song
The number of the range type of Qu Suoxu and the included ID to be recommended of ID to be recommended combination with for singing mesh
The species number of the range type needed for mark song is consistent.It is that terminal can be in every kind of target sound field type corresponding at least one
An ID is selected in ID as ID to be recommended and chorus ID composition use to be recommended is initiated
Family identifier combination.Wherein, it is inconsistent between each ID combination to be recommended.So as to terminal can ensure that each combination is included
The corresponding range type of ID to be recommended disclosure satisfy that range type needed for for singing target song, effectively improve
The chorus of target song.
In embodiments of the present invention, after terminal obtains at least one ID to be recommended to be combined, terminal can be from least
Any one ID combination to be recommended is obtained in one ID to be recommended as target recommended user's identifier combination.
Further, after terminal obtains at least one ID to be recommended to be combined, terminal can also be treated from least one
Preferably go out an ID combination to be recommended in recommended user's identifier combination as target recommended user's identifier combination, specifically may be used
To be:Terminal obtains each included ID to be recommended of each ID combination to be recommended and distinguishes corresponding fundamental frequency letter
Breath, corresponding fundamental frequency information is distinguished according to each ID to be recommended that each ID combination to be recommended is included
The fundamental frequency similarity of each ID combination to be recommended is calculated, the fundamental frequency information combined in each ID to be recommended is similar
Fundamental frequency similarity is obtained in degree and meets the first at least one pre-conditioned fundamental frequency similarity, it is similar at least one fundamental frequency
Spend in corresponding at least one ID combination to be recommended and obtain any one ID combination to be recommended as the target
Recommended user's identifier combination.May be such that the recommended user's mark included by target recommended user's identifier combination is corresponded to respectively so as to this
User fundamental frequency information it is similar, effectively improve the chorus of choral song.
In embodiments of the present invention, first, terminal obtains included each of each ID to be recommended combination and waits to push away
Corresponding fundamental frequency information can be specifically respectively to recommend ID:Correspondence initiates chorus ID a, by after above-described embodiment
The ID to be recommended of multiple candidate affiliates that same one first song was sung with it can be obtained, result in formation of multiple
Combination, is subsequently only processed as sample a combination, define this ID to be recommended for including of combination be a, b,
C, has sung same song x jointly, and the singing data that these three users performance x is obtained is xa, xb, xc.Terminal can extract xa,
xb, xcFundamental frequency information (frame move 10ms, frame length 30ms), because people's frequency that vocal cords vibrations are produced in sounding is by sound channel mistake
A large amount of overtones can be produced after filter, for the ease of subsequent operation, it is therefore desirable to extracted from audio and directly show vocal cords vibration frequency
Fundamental tone, fundamental tone also determines the pitch of whole note, so obtains three fundamental frequency sequence mi a、mi b、mi cI ∈ [1, n], wherein n
It is the number of fundamental frequency.After terminal gets the corresponding fundamental frequency information of each ID in combination, terminal can be believed fundamental frequency
Breath carries out noise point filtering, unusual fundamental frequency zero setting, such as when the front and rear fundamental frequency value of a non-zero fundamental frequency is 0, then by this point
0 is designated as, and carries out medium filtering, 5 medium filterings of fundamental frequency such as are done to non-zero fundamental frequency sequence, so as to obtain new fundamental frequency letter
Breath.Finally, fundamental frequency information can be converted to terminal the pitch value of music-book information, such asThis
Sample has obtained new pitch value mi a、mi b、mi ci∈[1,n].Secondly, terminal each ID combination institute to be recommended according to
Including each ID to be recommended distinguish the fundamental frequency phase that corresponding fundamental frequency information calculates each ID to be recommended combination
Can be specifically like degree:Terminal can calculate fundamental frequency similarity
Again, terminal obtains fundamental frequency similarity satisfaction first in the fundamental frequency information similarity that each ID to be recommended is combined and presets
At least one fundamental frequency similarity of condition can be specifically:Obtain S < p3At least one fundamental frequency similarity of (threshold value).Finally,
Any one use to be recommended is obtained in the corresponding at least one ID combination to be recommended of at least one fundamental frequency similarity
Family identifier combination is used as the target recommended user identifier combination.
Further, when terminal obtains corresponding at least one ID to be recommended of at least one fundamental frequency information similarity
After combination, terminal can also be from the corresponding at least one ID combination to be recommended of at least one fundamental frequency information similarity preferably
Go out an ID combination to be recommended as target recommended user's identifier combination, can be specifically:Described in terminal acquisition at least
Each ID included by each ID combination to be recommended in one ID combination to be recommended is corresponded to respectively
Timbre information, included by each ID combination to be recommended in described at least one ID to be recommended combination
Each ID to be recommended distinguish during corresponding timbre information calculates described at least one ID combination to be recommended
The tone color similarity of each ID combination to be recommended, each in described at least one ID combination to be recommended is treated
Tone color similarity is obtained in the tone color similarity of recommended user's identifier combination and meets the second at least one pre-conditioned tone color phase
Like spending, obtaining any one in the corresponding at least one ID combination to be recommended of at least one tone color similarity waits to push away
ID combination is recommended as the target recommended user identifier combination.So as to this may be such that target recommended user identifier combination institute
Including recommended user's mark corresponding user respectively fundamental frequency information and timbre information it is all similar, effectively improve choral song
Chorus.
In embodiments of the present invention, first, terminal obtains each during described at least one ID to be recommended is combined
Corresponding timbre information can be specifically each included ID of ID combination to be recommended respectively:For initiating to close
ID a is sung, by that can obtain multiple candidate affiliates' that same one first song was sung with it after above-described embodiment
Matching ID, result in formation of multiple combination, is subsequently only processed as sample a combination, defines this combination
Including ID to be recommended be a, b, c, sung same song x jointly, these three users sing the performance number that x is obtained
According to being xa, xb, xc.Terminal can extract corresponding mfcc characteristic sequences y to xa, xb, xciI ∈ [1, n], correspondence extracting method is such as
Under:Terminal is moved by frame of 10ms, and 30ms carries out framing for frame length to singing data xi, is extracted 13 to every frame data and is tieed up static state mfcc
Feature, wherein terminal-pair extract 13 dimension static state mfcc features per frame data can specifically be become per frame data by discrete fourier
Change, modulus square, triangle filter function group, take the logarithm to carry out obtaining 13 with the step such as discrete cosine transform and tie up static state mfcc spies
Levy.After terminal gets 13 dimensions static state mfcc features, terminal is using the 13 dimension mfcc feature calculation first-order differences for extracting
With second differnce totally 39 dimensional feature sequences ies a, yb, yc.And Gauss model training is carried out to ya, yb, yc, using EM Algorithm for Training
256 dimension mixed Gauss model za, zb, zc.Last terminal can calculate the likelihood value k of ya and zbab, the likelihood value k of yb and zaba、yb
With the likelihood value k of zcbc, yc and zb likelihood value kcb, yc and za likelihood value kca, ya and zc likelihood value kac.Specifically, seemingly
Right value is calculated by the following method:Gauss hybrid models represent by M single Gauss, e.g.,
Wherein,Represent the weight of each GaussTable
Show that j-th likelihood value of gauss hybrid models estimates that the likelihood function that matching degree l is calculated (represents each herein as follows
Sample calculates likelihood probability, then weighted sum in each Gauss, the probability multiplication of last N number of feature):Parameter:θj=(aj, uj, ∑j), θ=
(θ1,......,θm)T。
Secondly, each the ID combination to be recommended of terminal in described at least one ID combination to be recommended
Each included ID to be recommended distinguishes corresponding timbre information and calculates at least one ID group to be recommended
The tone color similarity of each in conjunction ID combination to be recommended can be specifically:Meter tone color similarity Q=kab+kba+kcb
+kca+kac+kbc.Again, each the ID combination to be recommended of terminal at least one ID combination to be recommended
Tone color similarity in obtain tone color similarity and meet the second at least one pre-conditioned tone color similarity and can be specifically:Obtain
Tone color similarities of the Q more than p4 (threshold value) is taken, finally, terminal is treated at least one tone color similarity corresponding at least one
Any one ID combination to be recommended is obtained in recommended user's identifier combination as the target recommended user identifier combination.
In embodiments of the present invention, after terminal obtains target recommended user's identifier combination, terminal can obtain the target
Each target recommended user mark included by recommended user's identifier combination is corresponding for singing the target song respectively
Singing songses data, according to the corresponding range type of each target recommended user mark, in each target recommended user
Mark obtains the corresponding singing songses data slot of each target recommended user mark in corresponding singing songses data respectively,
The corresponding singing songses data slot of each target recommended user mark is carried out into song synthesis, the target song is obtained
Bent corresponding synthesis song is simultaneously exported.This make user can audition chorus the chorus of the song, improve user experience.
In embodiments of the present invention, when the corresponding user of initiation chorus ID need to determine to invite target recommended user mark
When the corresponding user of other targeted customers mark in knowledge combination is chorused, user can be identified to other mesh by targeted customer
Mark ID sends chorus request, and when every other targeted customer mark returns to respond request, user can be with other targets
The corresponding targeted customer's chorus target song of ID, terminal can carry out recording the target song of the chorus and being issued.
In embodiments of the present invention, refer to when terminal receives carrying initiation chorus ID and song identity chorus
When making, the range type initiated corresponding to chorus ID is obtained, initiate to chorus corresponding to ID according to described
Range type determine, for singing at least one target sound field type that the corresponding target song of the song identity lacks, to obtain
The target recommended user's identifier combination matched with least one target sound field type is taken, and the target recommended user is marked
Combined recommendation is known to the corresponding user of the ID, may be such that the range class that terminal can be bad to user recommended user
The corresponding user of type carries out choral song, effectively improves the effect of recording song.
Below in conjunction with accompanying drawing 3 and 4, a kind of terminal provided in an embodiment of the present invention is introduced.It should be noted that
A kind of terminal shown in accompanying drawing 3 and 4, the method for performing embodiment illustrated in fig. 2 of the present invention, for convenience of description, only shows
The part related to the embodiment of the present invention, particular technique details is not disclosed, and refer to the embodiment shown in Fig. 2 of the present invention.
Fig. 3 is referred to, to the embodiment of the invention provides a kind of structural representation of terminal.As shown in figure 3, the present invention is real
The terminal for applying example can include:
Acquiring unit 100, for when receive carry initiate chorus ID and song identity chorus instruct when,
Obtain the range type initiated corresponding to chorus ID;
Determining unit 200, for being determined for singing according to the range type for initiating to chorus corresponding to ID
At least one target sound field type that the corresponding target song of the song identity lacks;
Recommendation unit 300, for obtaining the target recommended user matched with least one target sound field type mark
Combination, and the target recommended user identifier combination is recommended into the corresponding user of the ID, so that the target is pushed away
The corresponding user of ID at least one targeted customer corresponding with the target recommended user identifier combination is recommended to the mesh
Mark song is chorused.
Wherein, the acquiring unit 100 includes:
First obtains subelement, for obtaining institute in the database of the preset performance voice data for storing user
State the corresponding target of initiation chorus ID and sing voice data;
Second obtains subelement, is carried out for singing voice data to the target by preset at least one range type
Analysis, obtains the corresponding performance audio data fragment of every kind of range type;
3rd obtains subelement, for by the preset corresponding performance audio data fragment of code of points kind range type
Scored, obtained the corresponding performance fraction of every kind of range type;
First sets subelement, for the every kind of range type is corresponding sing fraction in obtain fraction and meet first
Pre-conditioned performance fraction, and the fraction the first pre-conditioned corresponding range type of performance fraction of satisfaction is set to institute
State the corresponding range type of initiation chorus ID.
Wherein, the determining unit 200 includes:
4th obtains subelement, the music-book information for obtaining the target song;
Analysis subelement, for analyzing the music-book information, obtains at least needed for for singing the target song
Plant range type;
Determination subelement, for according to it is described initiate chorus ID corresponding to range type and described for singing
At least one range type needed for the target song determines to lack for singing the corresponding target song of the song identity
At least one target sound field type.
Wherein, the recommendation unit 300 includes:
5th obtains subelement, for the corresponding relation according to preset range type and ID, obtains respectively every
Plant corresponding at least one ID to be recommended of target sound field type;
6th obtains subelement, for corresponding at least one ID of every kind of target sound field type and the initiation
Chorus ID is combined, and obtains at least one ID combination to be recommended, wherein, every kind of ID group to be recommended
The corresponding range type of ID to be recommended included by closing constitutes the range type needed for for singing the target song;
Second sets subelement, to be recommended for obtaining any one at least one ID combination to be recommended
ID is combined as the target recommended user identifier combination.
Wherein, the second setting subelement includes:
7th obtains subelement, each to be recommended user mark included for obtaining each ID combination to be recommended
Know corresponding fundamental frequency information respectively;
8th obtains subelement, for according to each included use to be recommended of each ID combination to be recommended
Corresponding fundamental frequency information calculates the fundamental frequency similarity that each ID to be recommended is combined to family mark respectively;
9th obtains subelement, for obtaining fundamental frequency in the fundamental frequency information similarity that each ID to be recommended is combined
Similarity meets the first at least one pre-conditioned fundamental frequency similarity;
3rd sets subelement, in the corresponding at least one ID group to be recommended of at least one fundamental frequency similarity
Any one ID combination to be recommended is obtained in conjunction as the target recommended user identifier combination.
Wherein, it is described 3rd set subelement specifically for:
Obtain included by each the ID combination to be recommended in described at least one ID combination to be recommended
Each ID distinguishes corresponding timbre information;
Included by each ID combination to be recommended in described at least one ID combination to be recommended
Each ID to be recommended distinguishes corresponding timbre information and calculates every during described at least one ID to be recommended is combined
The tone color similarity of individual ID combination to be recommended;
The tone color of each the ID combination to be recommended in described at least one ID combination to be recommended is similar
Tone color similarity is obtained in degree and meets the second at least one pre-conditioned tone color similarity;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one tone color similarity
ID combination to be recommended is used as the target recommended user identifier combination.
Wherein, the recommendation unit 300 includes:
Tenth obtains subelement, recommends to use for obtaining each target included by the target recommended user identifier combination
Family identifies the corresponding singing songses data for singing the target song respectively;
11st obtains subelement, for according to the corresponding range type of each target recommended user mark, described
Each target recommended user is obtained corresponding to each target recommended user mark in identifying corresponding singing songses data respectively
Singing songses data slot;
Synthesis subelement, for the corresponding singing songses data slot of each target recommended user mark to be carried out
Song synthesizes, and obtains the corresponding synthesis song of the target song and exports.
Wherein it is possible to understand, the function of each functional module of the unit in the terminal of the present embodiment can be according to Fig. 2 institutes
Method in the embodiment of the method stated is implemented, and it implements process and is referred to the correlation of above method embodiment retouches
State, no longer repeated herein.
In embodiments of the present invention, refer to when terminal receives carrying initiation chorus ID and song identity chorus
When making, the range type initiated corresponding to chorus ID is obtained, initiate to chorus corresponding to ID according to described
Range type determine, for singing at least one target sound field type that the corresponding target song of the song identity lacks, to obtain
The target recommended user's identifier combination matched with least one target sound field type is taken, and the target recommended user is marked
Combined recommendation is known to the corresponding user of the ID, may be such that the range class that terminal can be bad to user recommended user
The corresponding user of type carries out choral song, effectively improves the effect of recording song.
Fig. 4 is referred to, to the embodiment of the invention provides the structural representation of another terminal.As shown in figure 4, terminal
1000 can include:At least one processor 1001, such as CPU, at least one network interface 1004, user interface 1003 is deposited
Reservoir 1005, at least one communication bus 1002.Wherein, communication bus 1002 is used to realize that the connection between these components to be led to
Letter.Wherein, user interface 1003 can include display screen (Display), keyboard (Keyboard), and optional user interface 1003 is also
Wireline interface, the wave point of standard can be included.Network interface 1004 can optionally include the wireline interface of standard, wireless
Interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory, or non-labile memory (non-
Volatile memory), for example, at least one magnetic disk storage.Memory 1005 optionally can also be that at least one is located at
Away from the storage device of aforementioned processor 1001.As shown in figure 4, as can in a kind of memory 1005 of computer-readable storage medium
With including operating system, network communication module, Subscriber Interface Module SIM and communication connection application program.
In the terminal 1000 shown in Fig. 4, user interface 1003 is mainly used in providing the user the interface of input, obtains and uses
The data of family input;Network interface 1004 is used to be connected with NEWS SERVER, obtains the data that NEWS SERVER sends;And locate
Reason device 1001 can be used for calling the communication connection application program stored in memory 1005, and specifically perform following operation:
When carrying initiation chorus ID and song identity chorus instruction is received, obtain the initiation and chorus
Range type corresponding to ID;
Determined according to the range type for initiating to chorus corresponding to ID for singing the song identity correspondence
At least one target sound field type for lacking of target song;
Target recommended user's identifier combination for being matched with least one target sound field type of acquisition, and by the target
Recommended user's identifier combination recommends the corresponding user of the ID, so that the target recommended user identifies corresponding use
Family at least one targeted customer corresponding with the target recommended user identifier combination chorus to the target song.
Wherein, the processor 1001 obtains the range type initiated corresponding to chorus ID and includes:
The initiation chorus ID is obtained in the database of the preset performance voice data for storing user
Corresponding target sings voice data;
Voice data is sung to the target to be analyzed, obtain every kind of range class by preset at least one range type
The corresponding performance audio data fragment of type;
Scored by the preset corresponding audio data fragment of singing of code of points kind range type, obtained every kind of sound
The corresponding performance fraction of field type;
The every kind of range type is corresponding sing fraction in obtain fraction and meet the first pre-conditioned performance fraction,
And the fraction the first pre-conditioned corresponding range type of performance fraction of satisfaction is set to the initiation chorus ID
Corresponding range type.
Wherein, the processor 1001 is determined for drilling according to the range type for initiating to chorus corresponding to ID
Singing at least one target sound field type that the corresponding target song of the song identity lacks includes:
Obtain the music-book information of the target song;
The music-book information is analyzed, at least one range type needed for for singing the target song is obtained;
According to it is described initiate chorus ID corresponding to range type and described for singing the target song institute
At least one range type for needing is determined for singing at least one target that the corresponding target song of the song identity lacks
Range type.
Wherein, the processor 1001 obtains the target recommended user mark matched with least one target sound field type
Knowing combination includes:
According to preset range type and the corresponding relation of ID, every kind of target sound field type is obtained respectively corresponding
At least one ID to be recommended;
Group is carried out to corresponding at least one ID of every kind of target sound field type and initiation chorus ID
Close, obtain at least one ID combination to be recommended, wherein, the included use to be recommended of every kind of ID combination to be recommended
Mark corresponding range type in family constitutes the range type needed for for singing the target song;
Any one ID combination to be recommended is obtained at least one ID combination to be recommended as institute
State target recommended user's identifier combination.
Wherein, to obtain any one at least one ID to be recommended combination to be recommended for the processor 1001
ID combination includes as the target recommended user identifier combination:
Obtain each included ID to be recommended of each ID combination to be recommended and distinguish corresponding fundamental frequency letter
Breath;
Corresponding base is distinguished according to each ID to be recommended that each ID combination to be recommended is included
Frequency information calculates the fundamental frequency similarity of each ID combination to be recommended;
Fundamental frequency similarity satisfaction first is obtained in the fundamental frequency information similarity that each ID to be recommended is combined to preset
At least one fundamental frequency similarity of condition;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one fundamental frequency similarity
ID combination to be recommended is used as the target recommended user identifier combination.
Wherein, the processor 1001 is in corresponding at least one use to be recommended of at least one fundamental frequency information similarity
Family identifier combination obtains any one ID combination to be recommended to be included as the target recommended user identifier combination:
Obtain included by each the ID combination to be recommended in described at least one ID combination to be recommended
Each ID distinguishes corresponding timbre information;
Included by each ID combination to be recommended in described at least one ID combination to be recommended
Each ID to be recommended distinguishes corresponding timbre information and calculates every during described at least one ID to be recommended is combined
The tone color similarity of individual ID combination to be recommended;
The tone color of each the ID combination to be recommended in described at least one ID combination to be recommended is similar
Tone color similarity is obtained in degree and meets the second at least one pre-conditioned tone color similarity;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one tone color similarity
ID combination to be recommended is used as the target recommended user identifier combination.
Wherein, that the target recommended user identifier combination is recommended into the ID is corresponding for the processor 1001
User includes:
Obtain the corresponding use of each target recommended user mark difference included by the target recommended user identifier combination
In the singing songses data for singing the target song;
According to the corresponding range type of each target recommended user mark, in each target recommended user mark point
The corresponding singing songses data slot of each target recommended user mark is obtained in not corresponding singing songses data;
The corresponding singing songses data slot of each target recommended user mark is carried out into song synthesis, institute is obtained
State the corresponding synthesis song of target song and export.
Wherein it is possible to understand, the function of each functional module of the unit in the terminal of the present embodiment can be according to Fig. 2 institutes
Method in the embodiment of the method stated is implemented, and it implements process and is referred to the correlation of above method embodiment retouches
State, no longer repeated herein.
In embodiments of the present invention, refer to when terminal receives carrying initiation chorus ID and song identity chorus
When making, the range type initiated corresponding to chorus ID is obtained, initiate to chorus corresponding to ID according to described
Range type determine, for singing at least one target sound field type that the corresponding target song of the song identity lacks, to obtain
The target recommended user's identifier combination matched with least one target sound field type is taken, and the target recommended user is marked
Combined recommendation is known to the corresponding user of the ID, may be such that the range class that terminal can be bad to user recommended user
The corresponding user of type carries out choral song, effectively improves the effect of recording song.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method, can be
The hardware of correlation is instructed to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Above disclosed is only present pre-ferred embodiments, can not limit the right model of the present invention with this certainly
Enclose, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (14)
1. a kind of song chorus method, it is characterised in that methods described includes:
When receive carry initiate chorus ID and song identity chorus instruct when, obtain it is described initiate chorus user
The corresponding range type of mark;
Determined for singing the corresponding mesh of the song identity according to the range type for initiating to chorus corresponding to ID
At least one target sound field type that mark song lacks;
Target recommended user's identifier combination that acquisition is matched with least one target sound field type, and the target is recommended
ID combined recommendation gives the corresponding user of the ID so that the target recommended user identify corresponding user with
The target recommended user identifier combination corresponding at least one targeted customer chorus to the target song.
2. the method for claim 1, it is characterised in that the acquisition sound initiated corresponding to chorus ID
Field type includes:
The initiation chorus ID correspondence is obtained in the database of the preset performance voice data for storing user
Target sing voice data;
Voice data is sung to the target to be analyzed, obtain every kind of range type pair by preset at least one range type
The performance audio data fragment answered;
Scored by the preset corresponding audio data fragment of singing of code of points kind range type, obtained every kind of range class
The corresponding performance fraction of type;
The every kind of range type is corresponding sing fraction in obtain fraction and meet the first pre-conditioned performance fraction, and will
The fraction meets the first pre-conditioned corresponding range type of performance fraction and is set to the initiation chorus ID correspondence
Range type.
3. method as claimed in claim 2, it is characterised in that it is described according to it is described initiate chorus ID corresponding to sound
Field type determines to include for singing at least one target sound field type that the corresponding target song of the song identity lacks:
Obtain the music-book information of the target song;
The music-book information is analyzed, at least one range type needed for for singing the target song is obtained;
According to it is described initiate chorus ID corresponding to range type and it is described for singing the target song needed for
At least one range type is determined for singing at least one target range that the corresponding target song of the song identity lacks
Type.
4. method as claimed in claim 3, it is characterised in that the acquisition is matched with least one target sound field type
Target recommended user's identifier combination include:
According to preset range type and the corresponding relation of ID, every kind of target sound field type is obtained respectively corresponding at least
One ID to be recommended;
Corresponding at least one ID of every kind of target sound field type and initiation chorus ID are combined, are obtained
At least one ID combination to be recommended is obtained, wherein, the included user to be recommended mark of every kind of ID combination to be recommended
Know corresponding range type and constitute range type needed for for singing the target song;
Any one ID combination to be recommended is obtained at least one ID combination to be recommended as the mesh
Mark recommended user's identifier combination.
5. method as claimed in claim 4, it is characterised in that described at least one ID combination to be recommended
Obtain any one ID combination to be recommended includes as the target recommended user identifier combination:
Obtain each included ID to be recommended of each ID combination to be recommended and distinguish corresponding fundamental frequency information;
Corresponding fundamental frequency letter is distinguished according to each ID to be recommended that each ID combination to be recommended is included
Breath calculates the fundamental frequency similarity of each ID combination to be recommended;
Fundamental frequency similarity satisfaction first is obtained in the fundamental frequency information similarity that each ID to be recommended is combined pre-conditioned
At least one fundamental frequency similarity;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one fundamental frequency similarity to wait to push away
ID combination is recommended as the target recommended user identifier combination.
6. method as claimed in claim 5, it is characterised in that described corresponding at least one fundamental frequency information similarity
At least one ID combination to be recommended obtains any one ID combination to be recommended and is marked as the target recommended user
Knowing combination includes:
Obtain each included by each the ID combination to be recommended in described at least one ID combination to be recommended
ID distinguishes corresponding timbre information;
Each ID to be recommended in described at least one ID combination to be recommended combines each included
ID to be recommended respectively corresponding timbre information calculate in described at least one ID combination to be recommended each treat
The tone color similarity of recommended user's identifier combination;
In the tone color similarity of each the ID combination to be recommended in described at least one ID combination to be recommended
Obtain tone color similarity and meet the second at least one pre-conditioned tone color similarity;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one tone color similarity to wait to push away
ID combination is recommended as the target recommended user identifier combination.
7. method as claimed in claim 6, it is characterised in that described that the target recommended user identifier combination is recommended into institute
Stating the corresponding user of ID includes:
Each target recommended user mark obtained included by the target recommended user identifier combination is corresponding for drilling respectively
Sing the singing songses data of the target song;
According to the corresponding range type of each target recommended user mark, it is right respectively to be identified in each target recommended user
The corresponding singing songses data slot of each target recommended user mark is obtained in the singing songses data answered;
The corresponding singing songses data slot of each target recommended user mark is carried out into song synthesis, the mesh is obtained
The corresponding synthesis song of mark song is simultaneously exported.
8. a kind of terminal, it is characterised in that the terminal includes:
Acquiring unit, for when carrying initiation chorus ID and song identity chorus instruction is received, obtaining institute
State the range type for initiating to chorus corresponding to ID;
Determining unit, for being determined for singing the song according to the range type for initiating to chorus corresponding to ID
Identify at least one target sound field type that corresponding target song lacks;
Recommendation unit, for obtaining the target recommended user's identifier combination matched with least one target sound field type, and
The target recommended user identifier combination is recommended into the corresponding user of the ID, so that the target recommended user marks
Know corresponding user at least one targeted customer corresponding with the target recommended user identifier combination to enter the target song
Row chorus.
9. terminal as claimed in claim 7, it is characterised in that the acquiring unit includes:
First obtains subelement, for obtaining the hair in the database of the preset performance voice data for storing user
Play the corresponding target of chorus ID and sing voice data;
Second obtains subelement, is divided for singing voice data to the target by preset at least one range type
Analysis, obtains the corresponding performance audio data fragment of every kind of range type;
3rd obtains subelement, for being carried out by the preset corresponding audio data fragment of singing of code of points kind range type
Scoring, obtains the corresponding performance fraction of every kind of range type;
First sets subelement, for the every kind of range type is corresponding sing fraction in obtain fraction and meet first and preset
The performance fraction of condition, and the fraction the first pre-conditioned corresponding range type of performance fraction of satisfaction is set to the hair
Play the corresponding range type of chorus ID.
10. terminal as claimed in claim 9, it is characterised in that the determining unit includes:
4th obtains subelement, the music-book information for obtaining the target song;
Analysis subelement, for analyzing the music-book information, obtains at least one sound needed for for singing the target song
Field type;
Determination subelement, for according to it is described initiate chorus ID corresponding to range type and described for described in singing
At least one range type needed for target song determine for sing the corresponding target song of the song identity lack to
A kind of few target sound field type.
11. terminals as claimed in claim 10, it is characterised in that the recommendation unit includes:
5th obtains subelement, for the corresponding relation according to preset range type and ID, every kind of mesh is obtained respectively
Corresponding at least one ID to be recommended of mark with phonetic symbols field type;
6th obtains subelement, for being chorused to corresponding at least one ID of every kind of target sound field type and the initiation
ID is combined, and obtains at least one ID combination to be recommended, wherein, every kind of ID combination institute to be recommended
Including the corresponding range type of ID to be recommended constitute for singing the target song needed for range type;
Second sets subelement, for obtaining any one user to be recommended at least one ID combination to be recommended
Identifier combination is used as the target recommended user identifier combination.
12. terminals as claimed in claim 11, it is characterised in that the second setting subelement includes:
7th obtains subelement, each to be recommended ID point included for obtaining each ID combination to be recommended
Not corresponding fundamental frequency information;
8th obtains subelement, for according to each included user's mark to be recommended of described each ID combination to be recommended
Know the fundamental frequency similarity that corresponding fundamental frequency information respectively calculates each ID combination to be recommended;
9th obtains subelement, similar for obtaining fundamental frequency in the fundamental frequency information similarity that each ID to be recommended is combined
Degree meets the first at least one pre-conditioned fundamental frequency similarity;
3rd sets subelement, in the corresponding at least one ID combination to be recommended of at least one fundamental frequency similarity
Any one ID combination to be recommended is obtained as the target recommended user identifier combination.
13. terminals as claimed in claim 12, it is characterised in that it is described 3rd set subelement specifically for:
Obtain each included by each the ID combination to be recommended in described at least one ID combination to be recommended
ID distinguishes corresponding timbre information;
Each ID to be recommended in described at least one ID combination to be recommended combines each included
ID to be recommended respectively corresponding timbre information calculate in described at least one ID combination to be recommended each treat
The tone color similarity of recommended user's identifier combination;
In the tone color similarity of each the ID combination to be recommended in described at least one ID combination to be recommended
Obtain tone color similarity and meet the second at least one pre-conditioned tone color similarity;
Any one is obtained in the corresponding at least one ID combination to be recommended of at least one tone color similarity to wait to push away
ID combination is recommended as the target recommended user identifier combination.
14. terminals as claimed in claim 13, it is characterised in that the recommendation unit includes:
Tenth obtains subelement, for obtaining each target recommended user mark included by the target recommended user identifier combination
Know the corresponding singing songses data for singing the target song respectively;
11st obtains subelement, for the range type corresponding according to each target recommended user mark, it is described each
Target recommended user obtains the corresponding song of each target recommended user mark in identifying corresponding singing songses data respectively
Singing data fragment;
Synthesis subelement, for the corresponding singing songses data slot of each target recommended user mark to be carried out into song
Synthesis, obtains the corresponding synthesis song of the target song and exports.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710198662.8A CN106898339B (en) | 2017-03-29 | 2017-03-29 | Song chorusing method and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710198662.8A CN106898339B (en) | 2017-03-29 | 2017-03-29 | Song chorusing method and terminal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106898339A true CN106898339A (en) | 2017-06-27 |
CN106898339B CN106898339B (en) | 2020-05-26 |
Family
ID=59192864
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710198662.8A Active CN106898339B (en) | 2017-03-29 | 2017-03-29 | Song chorusing method and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106898339B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107704230A (en) * | 2017-09-11 | 2018-02-16 | 上海与德科技有限公司 | A kind of wheat sequence controlling method and control device |
CN107798561A (en) * | 2017-10-25 | 2018-03-13 | 网易传媒科技(北京)有限公司 | Audio broadcasting, sharing method and device, storage medium and electronic equipment |
CN107993637A (en) * | 2017-11-03 | 2018-05-04 | 厦门快商通信息技术有限公司 | A kind of karaoke lyrics segmenting method and system |
CN110418182A (en) * | 2019-07-19 | 2019-11-05 | 福建星网视易信息系统有限公司 | Chorus method of networking and computer readable storage medium |
CN111383669A (en) * | 2020-03-19 | 2020-07-07 | 杭州网易云音乐科技有限公司 | Multimedia file uploading method, device, equipment and computer readable storage medium |
CN111563690A (en) * | 2020-05-15 | 2020-08-21 | 河南职业技术学院 | Online music learning system based on internet |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1173006A (en) * | 1996-08-06 | 1998-02-11 | 雅马哈株式会社 | Music apparatus for independently producing multiple chorus parts through single channel |
CN101068283A (en) * | 2007-06-08 | 2007-11-07 | 无敌科技(西安)有限公司 | Interactive voice response system and generating corresponding data method thereof |
CN101159135A (en) * | 2007-11-22 | 2008-04-09 | 无敌科技(西安)有限公司 | System providing sound data group in identical diapason according to voice data and method thereof |
CN102568460A (en) * | 2010-12-28 | 2012-07-11 | 张泽铭 | Networking multi-person asynchronous chorus video work system and implementation method thereof |
CN104966527A (en) * | 2015-05-27 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Karaoke processing method, apparatus, and system |
CN105006234A (en) * | 2015-05-27 | 2015-10-28 | 腾讯科技(深圳)有限公司 | Karaoke processing method and apparatus |
US20150310850A1 (en) * | 2012-12-04 | 2015-10-29 | National Institute Of Advanced Industrial Science And Technology | System and method for singing synthesis |
CN105243093A (en) * | 2015-09-11 | 2016-01-13 | 福建星网视易信息系统有限公司 | Singer recommendation method and apparatus |
CN105575393A (en) * | 2015-12-02 | 2016-05-11 | 中国传媒大学 | Personalized song recommendation method based on voice timbre |
CN106095925A (en) * | 2016-06-12 | 2016-11-09 | 北京邮电大学 | A kind of personalized song recommendations system based on vocal music feature |
-
2017
- 2017-03-29 CN CN201710198662.8A patent/CN106898339B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1173006A (en) * | 1996-08-06 | 1998-02-11 | 雅马哈株式会社 | Music apparatus for independently producing multiple chorus parts through single channel |
CN101068283A (en) * | 2007-06-08 | 2007-11-07 | 无敌科技(西安)有限公司 | Interactive voice response system and generating corresponding data method thereof |
CN101159135A (en) * | 2007-11-22 | 2008-04-09 | 无敌科技(西安)有限公司 | System providing sound data group in identical diapason according to voice data and method thereof |
CN102568460A (en) * | 2010-12-28 | 2012-07-11 | 张泽铭 | Networking multi-person asynchronous chorus video work system and implementation method thereof |
US20150310850A1 (en) * | 2012-12-04 | 2015-10-29 | National Institute Of Advanced Industrial Science And Technology | System and method for singing synthesis |
CN104966527A (en) * | 2015-05-27 | 2015-10-07 | 腾讯科技(深圳)有限公司 | Karaoke processing method, apparatus, and system |
CN105006234A (en) * | 2015-05-27 | 2015-10-28 | 腾讯科技(深圳)有限公司 | Karaoke processing method and apparatus |
CN105243093A (en) * | 2015-09-11 | 2016-01-13 | 福建星网视易信息系统有限公司 | Singer recommendation method and apparatus |
CN105575393A (en) * | 2015-12-02 | 2016-05-11 | 中国传媒大学 | Personalized song recommendation method based on voice timbre |
CN106095925A (en) * | 2016-06-12 | 2016-11-09 | 北京邮电大学 | A kind of personalized song recommendations system based on vocal music feature |
Non-Patent Citations (2)
Title |
---|
BO SHAO ; DINGDING WANG ; TAO LI ; MITSUNORI OGIHARA: "Music Recommendation Based on Acoustic Features and User Access Patterns", 《IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING 》 * |
牛滨,孔令志,罗森林,潘丽敏,郭亮: "基于MFCC和GMM的个性音乐推荐模型", 《北京理工大学学报》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107704230A (en) * | 2017-09-11 | 2018-02-16 | 上海与德科技有限公司 | A kind of wheat sequence controlling method and control device |
CN107798561A (en) * | 2017-10-25 | 2018-03-13 | 网易传媒科技(北京)有限公司 | Audio broadcasting, sharing method and device, storage medium and electronic equipment |
CN107798561B (en) * | 2017-10-25 | 2021-08-13 | 网易传媒科技(北京)有限公司 | Audio playing and sharing method and device, storage medium and electronic equipment |
CN107993637A (en) * | 2017-11-03 | 2018-05-04 | 厦门快商通信息技术有限公司 | A kind of karaoke lyrics segmenting method and system |
CN110418182A (en) * | 2019-07-19 | 2019-11-05 | 福建星网视易信息系统有限公司 | Chorus method of networking and computer readable storage medium |
CN110418182B (en) * | 2019-07-19 | 2022-05-03 | 福建星网视易信息系统有限公司 | Networking chorus method and computer readable storage medium |
CN111383669A (en) * | 2020-03-19 | 2020-07-07 | 杭州网易云音乐科技有限公司 | Multimedia file uploading method, device, equipment and computer readable storage medium |
CN111383669B (en) * | 2020-03-19 | 2022-02-18 | 杭州网易云音乐科技有限公司 | Multimedia file uploading method, device, equipment and computer readable storage medium |
CN111563690A (en) * | 2020-05-15 | 2020-08-21 | 河南职业技术学院 | Online music learning system based on internet |
Also Published As
Publication number | Publication date |
---|---|
CN106898339B (en) | 2020-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106898339A (en) | The chorus method and terminal of a kind of song | |
CN106652997B (en) | Audio synthesis method and terminal | |
CN106991163A (en) | A kind of song recommendations method based on singer's sound speciality | |
CN103823867B (en) | Humming type music retrieval method and system based on note modeling | |
CN109785820A (en) | A kind of processing method, device and equipment | |
WO2018045988A1 (en) | Method and device for generating digital music score file of song, and storage medium | |
CN106898340A (en) | The synthetic method and terminal of a kind of song | |
CN106528678B (en) | A kind of song processing method and processing device | |
CN109166564A (en) | For the method, apparatus and computer readable storage medium of lyrics text generation melody | |
CN107103915A (en) | A kind of audio data processing method and device | |
CN106375780B (en) | A kind of multimedia file producting method and its equipment | |
CN104219570B (en) | Audio signal playing method and device | |
CN105679324A (en) | Voiceprint identification similarity scoring method and apparatus | |
CN106302987A (en) | A kind of audio frequency recommends method and apparatus | |
CN106997769A (en) | Trill recognition methods and device | |
CN108877835A (en) | Evaluate the method and system of voice signal | |
US9037278B2 (en) | System and method of predicting user audio file preferences | |
CN112632318A (en) | Audio recommendation method, device and system and storage medium | |
KR101813704B1 (en) | Analyzing Device and Method for User's Voice Tone | |
CN106970950A (en) | The lookup method and device of similar audio data | |
CN106503181A (en) | A kind of audio data processing method and device | |
JP6314884B2 (en) | Reading aloud evaluation device, reading aloud evaluation method, and program | |
CN101370216B (en) | Emotional processing and playing method for mobile phone audio files | |
Ibnyahya et al. | A method for matching room impulse responses with feedback delay networks | |
KR20070016750A (en) | Ubiquitous music information retrieval system and method based on query pool with feedback of customer characteristics |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |