CN110134825A - Music retrieval method and device - Google Patents
Music retrieval method and device Download PDFInfo
- Publication number
- CN110134825A CN110134825A CN201910402006.4A CN201910402006A CN110134825A CN 110134825 A CN110134825 A CN 110134825A CN 201910402006 A CN201910402006 A CN 201910402006A CN 110134825 A CN110134825 A CN 110134825A
- Authority
- CN
- China
- Prior art keywords
- music
- loudness
- sound
- climax
- peak value
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000003252 repetitive effect Effects 0.000 claims description 26
- 230000001174 ascending effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
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
- G06F16/68—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
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to a kind of music retrieval method and devices, wherein method includes: to receive the retrieval information of target music, retrieving information includes musical theme and music duration, climax musical database based on building, the candidate music that screening matches with musical theme and music duration, candidate music is shown in the search interface of target user according to preset rules, so as to target user from candidate music background music of the selection target music as target object.Target music is searched for by way of musical theme and music duration, allows to directly screen required music duration, the step of user cuts music duration is avoided, not only saves the time, but also improve efficiency.
Description
Technical field
The present invention relates to music retrieval technical fields, and in particular to a kind of music retrieval method and device.
Background technique
Music plays highly important role in people's lives, also there is long history inside information, wherein for
For most people, prefer the part for the climax for directly going to listen to music, the climax parts of general music can be expressed accurately
The information such as the emotion of transmitting.Also therefore, usual people when making PPT either propaganda film can select that sound is added
Happy climax parts serve as background music, further to increase the effect of expression.
But people are when selecting background music at present, be all mostly set out come under by music software it is corresponding
Then whole song is cut according to required duration, the serious time for wasting PPT or propaganda film production, certain journey
The efficiency of work is reduced on degree.
Summary of the invention
In view of this, directly being screened the purpose of the present invention is to provide a kind of music retrieval method and device with realizing
To the target music of required music duration, eliminates and reduce the time, improve work efficiency.
In order to achieve the above object, the present invention adopts the following technical scheme:
A kind of music retrieval method, comprising:
Receive the retrieval information of target music；The retrieval information includes musical theme and music duration；
Climax musical database based on building, the candidate that screening matches with the musical theme and the music duration
Music；
The candidate music is shown in the search interface of target user according to preset rules, so as to the target user from
Background music of the target music as target object is selected in the candidate music.
Optionally, before the retrieval information described above for receiving target music, further includes:
The corresponding complete audio file of total data frame of per song in song library is acquired, the complete audio file includes
Complete loudness of a sound data and/or complete lyrics data；
The complete loudness of a sound data and/or the complete lyrics data are handled, the height of the per song is obtained
Damp duration partially corresponding with the climax parts；
The climax musical database is constructed based on the climax parts and the corresponding duration of the climax parts.
Optionally, described above that the complete loudness of a sound data and/or the complete lyrics data are handled, obtain institute
State the climax parts and the corresponding duration of the climax parts of per song, comprising:
Obtain whole loudness of a sound peak values corresponding with the complete loudness of a sound data；
Maximum loudness of a sound peak value is chosen from whole loudness of a sound peak values；
Identify the head end loudness of a sound peak value and end loudness of a sound peak value at the maximum loudness of a sound peak value both ends；
The difference for comparing maximum the loudness of a sound peak value and the head end loudness of a sound peak value, obtains head end difference；
The difference for comparing maximum the loudness of a sound peak value and the end loudness of a sound peak value, obtains end difference；
If the head end difference is greater than head end preset threshold, the head end loudness of a sound peak value corresponding time point is the sound
The starting point of happy climax parts；
If the end difference is greater than end preset threshold, the end loudness of a sound peak value corresponding time point is the sound
The end point of happy climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
Optionally, described above that the complete loudness of a sound data and/or the complete lyrics data are handled, obtain institute
State the climax parts and the corresponding duration of the climax parts of per song, comprising:
Identify the repetitive rate of every lyrics in the complete lyrics data；
Compare the repetitive rate and default repetition rate threshold；
If the repetitive rate is greater than the default repetition rate threshold, the corresponding lyrics of the repetitive rate are the music
Climax parts；
The lyrics start the starting point that corresponding time point is the climax parts, and the lyrics terminate the corresponding time
Point is the end point of the climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
Optionally, the search interface described above that the candidate music is shown in target user according to preset rules, packet
It includes:
The candidate music is shown in the mesh according to the sequence of the similarity degree with the musical theme from high to low
The search interface of user is marked, and/or,
The target is shown in by the candidate music and according to the sequence ascending with the difference of the music duration
The search interface of user.
A kind of music retrieval device, comprising:
Receiving module, for receiving the retrieval information of target music；When the retrieval information includes musical theme and music
It is long；
Screening module, for the climax musical database based on building, when screening is with the musical theme and the music
The matched candidate music of appearance；
Display module, for the candidate music to be shown in the search interface of target user according to preset rules, so as to
The target user selects background music of the target music as target object from the candidate music.
Optionally, music retrieval device described above, further includes:
Acquisition module, it is described complete for acquiring the corresponding complete audio file of total data frame of per song in song library
Whole audio file includes complete loudness of a sound data and/or complete lyrics data；
Processing module obtains described for handling the complete loudness of a sound data and/or the complete lyrics data
The climax parts of per song and the corresponding duration of the climax parts；
Module is constructed, for constructing the climax music based on the climax parts and the corresponding duration of the climax parts
Database.
Optionally, processing module described above is specifically used for:
Obtain whole loudness of a sound peak values corresponding with the complete loudness of a sound data；
Maximum loudness of a sound peak value is chosen from whole loudness of a sound peak values；
Identify the head end loudness of a sound peak value and end loudness of a sound peak value at the maximum loudness of a sound peak value both ends；
The difference for comparing maximum the loudness of a sound peak value and the head end loudness of a sound peak value, obtains head end difference；
The difference for comparing maximum the loudness of a sound peak value and the end loudness of a sound peak value, obtains end difference；
If the head end difference is greater than head end preset threshold, the head end loudness of a sound peak value corresponding time point is the sound
The starting point of happy climax parts；
If the end difference is greater than end preset threshold, the end loudness of a sound peak value corresponding time point is the sound
The end point of happy climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
Optionally, processing module described above is specifically used for:
Identify the repetitive rate of every lyrics in the complete lyrics data；
Compare the repetitive rate and default repetition rate threshold；
If the repetitive rate is greater than the default repetition rate threshold, the corresponding lyrics of the repetitive rate are the music
Climax parts；
The lyrics start the starting point that corresponding time point is the climax parts, and the lyrics terminate the corresponding time
Point is the end point of the climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
Optionally, display module described above is specifically used for:
The candidate music is shown in the mesh according to the sequence of the similarity degree with the musical theme from high to low
The search interface of user is marked, and/or,
The target is shown in by the candidate music and according to the sequence ascending with the difference of the music duration
The search interface of user.
Of the invention a kind of music retrieval method and device, pass through the retrieval information for receiving target music, retrieve packet
Musical theme and music duration are included, the climax musical database based on building, screening matches with musical theme and music duration
Candidate music, candidate music is shown in the search interface of target user according to preset rules, so that target user is from candidate
Background music of the selection target music as target object in music realizes the side that user passes through musical theme and music duration
Formula retrieves music, directly obtains the desired target music to match with theme and duration, is then directly answered
It uses in the files such as required PPT or propaganda film, eliminates the troublesome operation that user cuts music, not only saved the time, but also mention
The high efficiency of work.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow chart of music retrieval method provided in an embodiment of the present invention.
Fig. 2 is another flow chart of music retrieval method provided in an embodiment of the present invention.
Fig. 3 is a kind of structural schematic diagram of music retrieval device provided in an embodiment of the present invention.
Fig. 4 is another structural schematic diagram of music retrieval device provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical solution of the present invention will be carried out below
Detailed description.Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art are obtained all without making creative work
Other embodiment belongs to the range that the present invention is protected.
Fig. 1 is a kind of flow chart of music retrieval method provided in an embodiment of the present invention.
As shown in Figure 1, a kind of music retrieval method provided in this embodiment can specifically include following steps:
S101, the retrieval information for receiving target music.
Receive the retrieval information of target music, wherein retrieval information includes musical theme and music duration, and user can be straight
Input duration is connect to select required music, can be one of function of music player software into search interface,
Can be an individual application software can choose in order to enable better ensuring that the quantity of music as existing sound
One additional function of happy playout software, the method as one of retrieval music.
The retrieval information for receiving target music, text information, pictorial information and voice messaging including receiving user's input
Etc. contents, no matter in any manner, as long as relevant information can be effectively captured.Most conventional mode is that user is straight
Connect input word content, such as dream of, 30 seconds, can be completed, special symbol also can be set, for example, before lookup it is defeated
Enter, indicates that the retrieval information received is the climax music for including corresponding duration, certainly, specific symbol is not forced
It limits, as long as can be realized retrieval climax music.Such as the mode of voice input, speech retrieval information is received, then
It is retrieved, can also be with automatic identification music, inquiry obtains relevant musical from music libraries；For another example, picture is inputted, figure is passed through
The mode of piece retrieval recognizes relevant musical content, and then receives the retrieval information of target music.No matter any side is used
Formula is finally accomplished that by way of retrieval information of user's input comprising musical theme and music duration, belongs to this
Within the protection scope of invention.
S102, the climax musical database based on building, appearance when screening and retrieve the musical theme and music in information
Matched candidate music.
After receiving the retrieval information of user, inquiry and inspection in the climax musical database built in advance automatically
The music that musical theme and music duration in rope information match, is defined as candidate music, in climax musical database
When middle screening target music, content relevant to musical theme can be preferentially screened, then on the basis of musical theme, then into
The target music to match with the music duration in retrieval information is screened to one step, and then is retrieved with target music matching degree most
High candidate music.
S103, the search interface that candidate music is shown in target user according to preset rules.
Candidate music may be very much, are successively shown in the search interface of user, preset rules therein include: will be candidate
Music is shown in the search interface of target user according to the sequence of the similarity degree with musical theme from high to low, and/or, it will wait
Select music and the search interface that target user is shown according to the sequence ascending with the difference of music duration.Also it can be set
Candidate music, is shown in the search interface of user by threshold value in such a way that musical theme and music duration are comprehensive, for example, with sound
The similarity degree of happy theme is 100%, and the difference with music duration is then preferentially to be shown in the search interface of user within 3 seconds.
Wherein, the content of display includes the relevant informations such as song title, the duration of climax parts and lyrics content, so that user is more intuitive
The all information of candidate music is recognized on ground, target music required for preferably selecting so as to user, and target music is made
For the background music of target object, wherein the target object can be PPT and/or propaganda film.If not complete with music duration
Complete matched candidate music, it is preferential to show that duration is greater than the candidate music for retrieving the music duration in information.
For example, certain teacher, in upper public course, the PPT of entire resources material may be very long, reach 100 multipages, it is few
Entire PPT adds background music completely, first is that the sound given lessons is influenced, second is that prolonged background music will lead to student fiber crops
Wood reduces the enthusiasm of study.Even heavy when talking about some by the time for generally also having 3 minutes for whole song
If whole song is put into PPT when wanting chapter, the progress given lessons is directly affected, usual teacher is also selection when giving lessons
It in the corresponding chapters and sections of PPT needed for the climax parts of whole song are loaded into, but is all in advance to be downloaded whole song,
Then it goes to cut whole song according to required length of time again, and during cutting, it is difficult to ensure that good climax portion
It is point complete corresponding with duration, largely affect the Production Time of PPT.According to a kind of music provided by the present invention
The step of search method, directly retrieval obtain the climax parts of target music, completely left out cutting, is directly loaded into and is wanted
In the chapters and sections of application, high efficiency and accuracy ensure that.Similarly, in the manufacturing process of propaganda film or other need to use
Into the documenting of background music, the troublesome operation for individually going to cut music again is similarly eliminated, workload is reduced, has
Improve work efficiency to effect.
A kind of music retrieval method of the present embodiment, by the retrieval information for receiving target music；Retrieving information includes sound
Happy theme and music duration, the climax musical database based on building, the time that screening matches with musical theme and music duration
Music is selected, candidate music is shown in the search interface of target user according to preset rules, so that target user is from candidate music
Middle selection target music realizes user and is retrieved by way of musical theme and music duration to music, directly obtained
The desired target music to match with theme and duration, then directly applies it to the texts such as required PPT or propaganda film
In part, the troublesome operation that user cuts music is eliminated, has not only been saved the time, but also improve the efficiency of work.
Fig. 2 is another flow chart of music retrieval method provided in an embodiment of the present invention.As shown in Fig. 2, the present embodiment
Music retrieval method embodiment shown in Fig. 1 on the basis of, further in further detail to technical solution of the present invention carry out
Description.As shown in Fig. 2, the music retrieval method of the present embodiment specifically can with the following steps are included:
The corresponding complete audio file of total data frame of per song in S201, acquisition song library.
Wherein, complete audio file includes complete loudness of a sound data and/or complete lyrics data, to all in audio file
Content is acquired, and better ensures that the accuracy of data result.
S202, in complete audio file complete loudness of a sound data and/or complete lyrics data handle, obtain every head
The corresponding duration of climax parts and climax parts of music.
It, can be with if obtaining the climax parts and the corresponding duration of climax parts of per song by complete loudness of a sound data are as follows:
Whole loudness of a sound peak values corresponding with complete loudness of a sound data are got first, each time point corresponding loudness of a sound peak value is all caught
It grasps, is then compared all loudness of a sound peak values captured, choose maximum loudness of a sound peak value from whole loudness of a sound peak values, and most
Loudness of a sound peak value corresponding time point and lyrics por-tion are a part of climax parts greatly, then identify maximum loudness of a sound peak value both ends
Head end loudness of a sound peak value and end loudness of a sound peak value；Define any one of the corresponding time point left side time shaft of maximum loudness of a sound peak value
Loudness of a sound peak value is head end loudness of a sound peak value, defines any one loudness of a sound peak of time shaft on the right side of maximum loudness of a sound peak value corresponding time point
Value is end loudness of a sound peak value, after obtaining head end loudness of a sound peak value and end loudness of a sound peak value, more maximum loudness of a sound peak value and multiple head
The difference for holding loudness of a sound peak value, obtains head end difference, head end difference have it is multiple, similarly, more maximum loudness of a sound peak value and multiple ends
The difference of loudness of a sound peak value, obtains end difference, and end difference also has multiple, is then respectively compared multiple head end differences and head end is pre-
If the size of threshold value, when obtaining a head end loudness of a sound peak value greater than head end preset threshold, head end at this time can be determined
Loudness of a sound peak value corresponding time point is the starting point of music climax parts, similarly, if end difference is greater than end preset threshold,
End loudness of a sound peak value corresponding time point is the end point of music climax parts, therefore, has just obtained rising for music climax parts
Initial point and end point have also determined that the time difference between starting point and end point, which is music climax portion
Divide corresponding duration.
It can also be by handling complete lyrics data, climax parts and the climax parts for obtaining per song are corresponding
Duration, identify the repetitive rate of every lyrics in complete lyrics data first, usually in a first complete music, climax parts
It is the highest part of repetitive rate, generally can all repeats to sing 3 times or more, compare repetitive rate and default repetition rate threshold, presets weight
Multiple rate threshold value is fixed value, can voluntarily be set, if repetitive rate is greater than default repetition rate threshold, repetitive rate is corresponding
The lyrics are the climax parts of music, and each lyrics all go to differentiate its repetitive rate, can not also given threshold, directly screening weight
The multiple highest lyrics of rate are the climax parts of the song, can be specifically manually set according to the actual situation, Neng Gouzhun
True to obtain the climax parts of music, the lyrics of climax parts start corresponding time point just and are the starting of climax parts
Point, the lyrics terminate corresponding time point just and are the end point of climax parts, determine the time difference between starting point and end point,
The as corresponding duration of climax parts.
S203, the climax parts based on per song and the corresponding duration of climax parts construct climax musical database.
The musical database of existing music player software is the database of whole song, and the climax that the present invention constructs
Musical database is only to include the climax parts of per song, store the climax parts of per song as individual file
Get up, after then receiving retrieval information, climax music is screened directly from climax musical database.It is first when constructing database
The corresponding complete audio file of total data frame of per song in song library is first acquired, all data such as including prelude also include
Complete loudness of a sound data and complete lyrics data, have obtained the climax parts and climax parts of per song through the above steps
Corresponding duration, what is be just mutually matched is stored in climax musical database.Database can also include multiple subdatas
Library, such as one database of a theme dream of that one subdata base of theme, one subdata base of love theme are also possible to
Subdata base is defined according to duration, a subdata base in 20 seconds, a numerical data base in 20 seconds to 40 seconds, specific son
The classification situation of database is no longer described in detail, as long as belonging to protection of the invention using the principle of the present invention
Within the scope of.
S204, the retrieval information for receiving target music.
S205, the climax musical database based on building, appearance when screening and retrieve the musical theme and music in information
Matched candidate music.
S206, the search interface that candidate music is shown in target user according to preset rules.
It about explaining in detail for S204-S206 step, has elaborated in the above-described embodiments, in the present embodiment
No longer illustrated again.
Wherein can with the following steps are included:
Obtain the mark for the target music that user chooses from search interface；According to the mark of target music, target sound is determined
It is happy；Using target music as the background music of target object.It chooses so that clearly giving expression to target music to the entire of application
Process.
Fig. 3 is a kind of structural schematic diagram of music retrieval device provided in an embodiment of the present invention.
As shown in figure 3, a kind of music retrieval device of the present embodiment, comprising:
Receiving module 10, for receiving the retrieval information of target music；Retrieving information includes musical theme and music duration；
Screening module 20, for the climax musical database based on building, screening and appearance when musical theme and music
The candidate music matched；
Display module 30, for candidate music to be shown in the search interface of target user according to preset rules, so as to mesh
Mark the user's background music of selection target music as target object from candidate music.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
A kind of music retrieval device of the present embodiment receives the retrieval information of target music by receiving module；Retrieval letter
Breath includes musical theme and music duration, then utilizes climax musical database of the screening module based on building, screening and music
The candidate music that theme and music duration match, then candidate music is shown according to preset rules by target by screening module
The search interface of user, so as to target user from candidate music selection target music, realize user by musical theme and
The mode of music duration retrieves music, directly obtains the desired target music to match with theme and duration, so
It is directly applied it in the files such as required PPT or propaganda film afterwards, eliminates user and go to cut the troublesome operation of music again, both
It has saved the time, and has improved the efficiency of work.
Fig. 4 is another structural schematic diagram of music retrieval device provided in an embodiment of the present invention.
It is further more detailed to this hair on the basis of the music retrieval device embodiment shown in Fig. 3 of the present embodiment
Bright technical solution is described.As shown in figure 4, the music retrieval device of the present embodiment can also may include:
Acquisition module 40, for acquiring the corresponding complete audio file of total data frame of per song in song library, completely
Audio file includes complete loudness of a sound data and/or complete lyrics data；
Processing module 50 obtains per song for handling complete loudness of a sound data and/or complete lyrics data
Climax parts and the corresponding duration of climax parts；
Module 60 is constructed, for constructing climax musical database based on climax parts and the corresponding duration of climax parts.
Further, on the basis of the above embodiments, the processing module 50 in the present embodiment is specifically used for:
Obtain whole loudness of a sound peak values corresponding with complete loudness of a sound data；
Maximum loudness of a sound peak value is chosen from whole loudness of a sound peak values；
Identify the head end loudness of a sound peak value and end loudness of a sound peak value at maximum loudness of a sound peak value both ends；
The difference for comparing maximum loudness of a sound peak value Yu head end loudness of a sound peak value, obtains head end difference；
The difference for comparing maximum loudness of a sound peak value Yu end loudness of a sound peak value, obtains end difference；
If head end difference is greater than head end preset threshold, head end loudness of a sound peak value corresponding time point is music climax parts
Starting point；
If end difference is greater than end preset threshold, end loudness of a sound peak value corresponding time point is music climax parts
End point；
Determine time difference between starting point and end point as the corresponding duration of climax parts.
Further, on the basis of the above embodiments, the processing module 50 in the present embodiment is specifically used for:
Identify the repetitive rate of every lyrics in complete lyrics data；
Compare repetitive rate and default repetition rate threshold；
If repetitive rate is greater than default repetition rate threshold, the corresponding lyrics of repetitive rate are the climax parts of music；
The lyrics start the starting point that corresponding time point is climax parts, and the lyrics terminate corresponding time point as climax parts
End point；
Determine time difference between starting point and end point as the corresponding duration of climax parts.
Further, on the basis of the above embodiments, the display module 30 of the present embodiment is specifically used for:
Candidate music is shown in the retrieval of target user according to the sequence of the similarity degree with musical theme from high to low
Interface, and/or,
By candidate music and retrieval circle for being shown in target user according to the sequence ascending with the difference of music duration
Face.
About the associated description in above-mentioned apparatus embodiment, detailed Jie has been carried out in the embodiment of corresponding method
Continue explanation, is no longer described in detail in a device.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
It should be noted that in the description of the present invention, term " first ", " second " etc. are used for description purposes only, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present invention, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of music retrieval method characterized by comprising
Receive the retrieval information of target music；The retrieval information includes musical theme and music duration；
Climax musical database based on building, the candidate sound that screening matches with the musical theme and the music duration
It is happy；
The candidate music is shown in the search interface of target user according to preset rules, so that the target user is from described
Background music of the target music as target object is selected in candidate music.
2. music retrieval method according to claim 1, which is characterized in that it is described receive target music retrieval information it
Before, further includes:
The corresponding complete audio file of total data frame of per song in song library is acquired, the complete audio file includes complete
Loudness of a sound data and/or complete lyrics data；
The complete loudness of a sound data and/or the complete lyrics data are handled, the climax portion of the per song is obtained
Divide duration corresponding with the climax parts；
The climax musical database is constructed based on the climax parts and the corresponding duration of the climax parts.
3. music retrieval method according to claim 2, which is characterized in that it is described to the complete loudness of a sound data and/or
The complete lyrics data is handled, and the climax parts and the corresponding duration of the climax parts of the per song are obtained,
Include:
Obtain whole loudness of a sound peak values corresponding with the complete loudness of a sound data；
Maximum loudness of a sound peak value is chosen from whole loudness of a sound peak values；
Identify the head end loudness of a sound peak value and end loudness of a sound peak value at the maximum loudness of a sound peak value both ends；
The difference for comparing maximum the loudness of a sound peak value and the head end loudness of a sound peak value, obtains head end difference；
The difference for comparing maximum the loudness of a sound peak value and the end loudness of a sound peak value, obtains end difference；
If the head end difference is greater than head end preset threshold, the head end loudness of a sound peak value corresponding time point is that the music is high
The starting point of damp part；
If the end difference is greater than end preset threshold, the end loudness of a sound peak value corresponding time point is that the music is high
The end point of damp part；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
4. music retrieval method according to claim 2, which is characterized in that it is described to the complete loudness of a sound data and/or
The complete lyrics data is handled, and the climax parts and the corresponding duration of the climax parts of the per song are obtained,
Include:
Identify the repetitive rate of every lyrics in the complete lyrics data；
Compare the repetitive rate and default repetition rate threshold；
If the repetitive rate is greater than the default repetition rate threshold, the corresponding lyrics of the repetitive rate are the climax of the music
Part；
The lyrics start the starting point that corresponding time point is the climax parts, and the lyrics terminate corresponding time point and are
The end point of the climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
5. music retrieval method according to claim 1, which is characterized in that it is described by the candidate music according to default rule
Then it is shown in the search interface of target user, comprising:
The candidate music is shown in the target according to the sequence of the similarity degree with the musical theme from high to low to use
The search interface at family, and/or,
The target user is shown in by the candidate music and according to the sequence ascending with the difference of the music duration
Search interface.
6. a kind of music retrieval device characterized by comprising
Receiving module, for receiving the retrieval information of target music；The retrieval information includes musical theme and music duration；
Screening module, for the climax musical database based on building, screening and appearance when the musical theme and the music
Matched candidate music；
Display module, for the candidate music to be shown in the search interface of target user according to preset rules, so as to described
Target user selects background music of the target music as target object from the candidate music.
7. music retrieval device according to claim 6, which is characterized in that further include:
Acquisition module, for acquiring the corresponding complete audio file of total data frame of per song in song library, the complete sound
Frequency file includes complete loudness of a sound data and/or complete lyrics data；
Processing module obtains every head for handling the complete loudness of a sound data and/or the complete lyrics data
The climax parts of music and the corresponding duration of the climax parts；
Module is constructed, for constructing the climax music data based on the climax parts and the corresponding duration of the climax parts
Library.
8. music retrieval device according to claim 7, which is characterized in that the processing module is specifically used for:
Obtain whole loudness of a sound peak values corresponding with the complete loudness of a sound data；
Maximum loudness of a sound peak value is chosen from whole loudness of a sound peak values；
Identify the head end loudness of a sound peak value and end loudness of a sound peak value at the maximum loudness of a sound peak value both ends；
The difference for comparing maximum the loudness of a sound peak value and the head end loudness of a sound peak value, obtains head end difference；
The difference for comparing maximum the loudness of a sound peak value and the end loudness of a sound peak value, obtains end difference；
If the head end difference is greater than head end preset threshold, the head end loudness of a sound peak value corresponding time point is that the music is high
The starting point of damp part；
If the end difference is greater than end preset threshold, the end loudness of a sound peak value corresponding time point is that the music is high
The end point of damp part；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
9. music retrieval device according to claim 7, which is characterized in that the processing module is specifically used for:
Identify the repetitive rate of every lyrics in the complete lyrics data；
Compare the repetitive rate and default repetition rate threshold；
If the repetitive rate is greater than the default repetition rate threshold, the corresponding lyrics of the repetitive rate are the climax of the music
Part；
The lyrics start the starting point that corresponding time point is the climax parts, and the lyrics terminate corresponding time point and are
The end point of the climax parts；
Determine time difference between the starting point and the end point as the corresponding duration of the climax parts.
10. music retrieval device according to claim 6, which is characterized in that the display module is specifically used for:
The candidate music is shown in the target according to the sequence of the similarity degree with the musical theme from high to low to use
The search interface at family, and/or,
The target user is shown in by the candidate music and according to the sequence ascending with the difference of the music duration
Search interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402006.4A CN110134825A (en) | 2019-05-15 | 2019-05-15 | Music retrieval method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402006.4A CN110134825A (en) | 2019-05-15 | 2019-05-15 | Music retrieval method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110134825A true CN110134825A (en) | 2019-08-16 |
Family
ID=67574005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910402006.4A Pending CN110134825A (en) | 2019-05-15 | 2019-05-15 | Music retrieval method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110134825A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339350A (en) * | 2020-03-27 | 2020-06-26 | 腾讯音乐娱乐科技（深圳）有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120316660A1 (en) * | 2011-06-07 | 2012-12-13 | Jiebo Luo | Automatically selecting thematically representative music |
| CN102903357A (en) * | 2011-07-29 | 2013-01-30 | 华为技术有限公司 | Method, device and system for extracting chorus of song |
| CN104282322A (en) * | 2014-10-29 | 2015-01-14 | 深圳市中兴移动通信有限公司 | Mobile terminal and method and device for identifying chorus part of song thereof |
| CN104978974A (en) * | 2014-10-22 | 2015-10-14 | 腾讯科技（深圳）有限公司 | Audio processing method and device |
| CN106446260A (en) * | 2016-10-18 | 2017-02-22 | 刘洋 | Self-learning music pushing method and system |
| CN107862065A (en) * | 2017-11-16 | 2018-03-30 | 联想(北京)有限公司 | Multimedia file broadcasting control method and multimedia equipment |
| US9965532B2 (en) * | 2015-04-14 | 2018-05-08 | Disney Enterprises, Inc. | Asset-data integration |
| CN108090140A (en) * | 2017-12-04 | 2018-05-29 | 维沃移动通信有限公司 | A kind of playback of songs method and mobile terminal |
| CN108920591A (en) * | 2018-06-27 | 2018-11-30 | Oppo广东移动通信有限公司 | Recall video creation method and relevant apparatus |
| CN109255048A (en) * | 2018-09-17 | 2019-01-22 | 深圳市心版图科技有限公司 | A kind of music storage and extraction system based on big data |
-
2019
- 2019-05-15 CN CN201910402006.4A patent/CN110134825A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120316660A1 (en) * | 2011-06-07 | 2012-12-13 | Jiebo Luo | Automatically selecting thematically representative music |
| CN102903357A (en) * | 2011-07-29 | 2013-01-30 | 华为技术有限公司 | Method, device and system for extracting chorus of song |
| CN104978974A (en) * | 2014-10-22 | 2015-10-14 | 腾讯科技（深圳）有限公司 | Audio processing method and device |
| CN104282322A (en) * | 2014-10-29 | 2015-01-14 | 深圳市中兴移动通信有限公司 | Mobile terminal and method and device for identifying chorus part of song thereof |
| US9965532B2 (en) * | 2015-04-14 | 2018-05-08 | Disney Enterprises, Inc. | Asset-data integration |
| CN106446260A (en) * | 2016-10-18 | 2017-02-22 | 刘洋 | Self-learning music pushing method and system |
| CN107862065A (en) * | 2017-11-16 | 2018-03-30 | 联想(北京)有限公司 | Multimedia file broadcasting control method and multimedia equipment |
| CN108090140A (en) * | 2017-12-04 | 2018-05-29 | 维沃移动通信有限公司 | A kind of playback of songs method and mobile terminal |
| CN108920591A (en) * | 2018-06-27 | 2018-11-30 | Oppo广东移动通信有限公司 | Recall video creation method and relevant apparatus |
| CN109255048A (en) * | 2018-09-17 | 2019-01-22 | 深圳市心版图科技有限公司 | A kind of music storage and extraction system based on big data |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339350A (en) * | 2020-03-27 | 2020-06-26 | 腾讯音乐娱乐科技（深圳）有限公司 | Data processing method, data processing device, storage medium and electronic equipment |
| CN111339350B (en) * | 2020-03-27 | 2023-11-28 | 腾讯音乐娱乐科技（深圳）有限公司 | Data processing method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10977299B2 (en) | Systems and methods for consolidating recorded content | |
| CN106652997A (en) | Audio synthesis method and terminal | |
| US7533091B2 (en) | Methods, systems, and computer-readable media for generating a suggested list of media items based upon a seed | |
| KR20070121810A (en) | Synthesis of composite news stories | |
| EP3872806B1 (en) | Text-to-speech from media content item snippets | |
| US20050149330A1 (en) | Speech synthesis system | |
| US20100332483A1 (en) | Content output queue generation | |
| US7792831B2 (en) | Apparatus, system and method for extracting structure of song lyrics using repeated pattern thereof | |
| US20050254366A1 (en) | Method and apparatus for selecting an audio track based upon audio excerpts | |
| US20080022846A1 (en) | Method of and system for browsing of music | |
| CN105279227B (en) | Method and device for processing voice search of homophone | |
| CN111199732B (en) | Emotion-based voice interaction method, storage medium and terminal equipment | |
| CN104123115A (en) | Audio information processing method and electronic device | |
| CN108242238B (en) | Audio file generation method and device and terminal equipment | |
| US20110046955A1 (en) | Speech processing apparatus, speech processing method and program | |
| US20170300291A1 (en) | Apparatus for recording audio information and method for controlling same | |
| CN104867494B (en) | The name sorting technique and system of a kind of recording file | |
| US20180268809A1 (en) | Voice keyword detection apparatus and voice keyword detection method | |
| CN107481735A (en) | A kind of method, server and the computer-readable recording medium of transducing audio sounding | |
| CN106302987A (en) | A kind of audio frequency recommends method and apparatus | |
| JP2003177784A (en) | Method and device for extracting sound turning point, method and device for sound reproducing, sound reproducing system, sound delivery system, information providing device, sound signal editing device, recording medium for sound turning point extraction method program, recording medium for sound reproducing method program, recording medium for sound signal editing method program, sound turning point extraction method program, sound reproducing method program, and sound signal editing method program | |
| CN104900231A (en) | VOICE SEARCH DEVICE and VOICE SEARCH METHOD | |
| CN111354325B (en) | Automatic word and song creation system and method thereof | |
| CN110134825A (en) | Music retrieval method and device | |
| CN110797001B (en) | Method and device for generating voice audio of electronic book and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |