CN110335625A - The prompt and recognition methods of background music, device, equipment and medium - Google Patents
The prompt and recognition methods of background music, device, equipment and medium Download PDFInfo
- Publication number
- CN110335625A CN110335625A CN201910611412.1A CN201910611412A CN110335625A CN 110335625 A CN110335625 A CN 110335625A CN 201910611412 A CN201910611412 A CN 201910611412A CN 110335625 A CN110335625 A CN 110335625A
- Authority
- CN
- China
- Prior art keywords
- music
- video
- background music
- target
- fingerprint
- 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 89
- 238000003860 storage Methods 0.000 claims abstract description 26
- 238000010276 construction Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 19
- 230000002123 temporal effect Effects 0.000 claims description 13
- 239000000284 extract Substances 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 11
- 238000007667 floating Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 101100217298 Mus musculus Aspm gene Proteins 0.000 description 5
- 230000005291 magnetic effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 239000000203 mixture Substances 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/488—Data services, e.g. news ticker
- H04N21/4882—Data services, e.g. news ticker for displaying messages, e.g. warnings, reminders
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses recognition methods, device, equipment and the storage mediums of background music in a kind of prompt of background music and video.The described method includes: playing target video in video playing interface；Obtain with the matched background music information of the target video, include: background music description information in the background music information；In the playing process of the target video, the background music description information is supplied to user.The technical solution of the embodiment of the present invention can be in video display process, the background music information for obtaining in real time and playing video matching, it realizes in video display process, the background music information that will acquire is supplied to user, the process for making user obtain video background music information is more convenient, saves user time.
Description
Technical field
The present embodiments relate to background musics in the prompt of Internet technology more particularly to a kind of background music and video
Recognition methods, device, equipment and storage medium.
Background technique
With the rapid development of Internet technology, network broadband increases therewith, and flow price is gradually reduced, and viewing video is
Through the important component for becoming public recreation life.No matter professional team produce extensively or personal impromptu production, usually all
It will increase background music and carry out rendered atmosphere.Masses are often interested in background music during watching video, generate background
At this moment the identification demand of music would generally request background music by hair barrage, and need further by browser or
Person's music software carries out the secondary release version inquired and can just finally obtain background music, and process is comparatively laborious and takes a long time.
In the prior art, part of the application software has the function of that song is listened to know song, but it is usually required through terminal microphone
Audio being played on is acquired, ambient noise is often acquired with audio to be identified together, not so as to cause recognition result
Accurate or low recognition success rate problem.
Summary of the invention
The embodiment of the invention provides the recognition methods of background music in a kind of prompt of background music and video, device,
Equipment and storage medium, realize in video display process, obtain the background music information in currently playing video in real time,
Keep the process of the background music in user's acquisition video more convenient.
In a first aspect, the embodiment of the invention provides a kind of reminding methods of background music, comprising:
Target video is played in video playing interface；
Obtain with the matched background music information of the target video, include: background music in the background music information
Description information；
In the playing process of the target video, the background music description information is supplied to user.
Second aspect, the embodiment of the invention also provides a kind of recognition methods of background music in video, comprising:
Video to be identified is obtained, and extracts the audio content in the video；
According to the frequency domain character of the audio content, multiple Meier scaled versions corresponding with the audio content are obtained
Frequency domain character point, and according to the comparison music fingerprint of each frequency domain character the point construction and the match audio content of the video；
By the comparison music fingerprint of the video, is matched, obtained with the standard music fingerprint of music each in music libraries
Target music corresponding with the video；
The music description information for obtaining the target music, as with the matched background music information of the target video.
The third aspect, the embodiment of the invention also provides a kind of suggestion devices of background music, comprising:
Target video playing module, for playing target video in video playing interface；
Background music data obtaining module, for obtaining and the matched background music information of the target video, the back
It include: background music description information in scape music information；
Background music nformation alert module, in the playing process of the target video, the background music to be retouched
It states information and is supplied to user.
Fourth aspect, the embodiment of the invention also provides a kind of identification devices of background music in video, comprising:
Audio content extraction module for obtaining video to be identified, and extracts the audio content in the video；
Compare music fingerprint constructing module, for the frequency domain character according to the audio content, obtain in the audio
Hold the frequency domain character point of corresponding multiple Meier scaled versions, and according to the sound of each frequency domain character the point construction and the video
The comparison music fingerprint of frequency content matching；
Target music obtains module, for the standard by the comparison music fingerprint of the video, with music each in music libraries
Music fingerprint is matched, and target music corresponding with the video is obtained；
Description information memory module, for by the music description information of the target music, as with the target video
Matched background music information.
5th aspect the embodiment of the invention also provides a kind of computer equipment, including memory, processor and is stored in
On memory and the computer program that can run on a processor, the processor are realized when executing described program as the present invention is real
The reminding method of any background music in example is applied, or realizes background in the video as described in any in the embodiment of the present invention
The recognition methods of music.
6th aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the reminding method of the background music as described in any in the embodiment of the present invention when program is executed by processor, or
Realize the recognition methods of background music in the video as described in any in the embodiment of the present invention.
The embodiment of the invention provides the recognition methods of background music in a kind of prompt of background music and video, device,
Equipment and storage medium, by obtaining the back to match with currently playing target video in real time in video display process
Scape music information, and above-mentioned background music information is supplied to user, user is realized during watching video, without exiting
The video-see page can obtain the effect of background music in video, and, by the way that the audio content for including in video is converted
To frequency domain, and according to the frequency domain character point of the Meier scaled version of audio construct compare music fingerprint, for in music libraries
Standard music fingerprint is matched, and to identify the corresponding background music of currently playing video, effectively increases music recognition
Success rate and accuracy.
Detailed description of the invention
Fig. 1 a is the flow chart of the reminding method of one of the embodiment of the present invention one background music；
Fig. 1 b is a kind of scene for displaying background music prompt options that the technical solution of the embodiment of the present invention one is applicable in；
Fig. 1 c is that a kind of displaying background music that the technical solution of the embodiment of the present invention one is applicable in describes card and pass
Join the scene of recommendation information；
Fig. 2 is the flow chart of the reminding method of one of the embodiment of the present invention two background music；
Fig. 3 is the flow chart of the recognition methods of background music in one of the embodiment of the present invention three video；
Fig. 4 a is the flow chart of the recognition methods of background music in one of the embodiment of the present invention four video；
Fig. 4 b is a kind of schematic diagram for spectrogram that the technical solution of the embodiment of the present invention four is applicable in；
Fig. 5 a is the flow chart of the recognition methods of background music in one of the embodiment of the present invention five video；
Fig. 5 b is a kind of fingerprint matching schematic diagram that the embodiment of the present invention five provides；
Fig. 6 is the structure chart of the suggestion device of one of the embodiment of the present invention six background music；
Fig. 7 is the structure chart of the identification device of background music in one of the embodiment of the present invention seven video；
Fig. 8 is the structural schematic diagram of one of the embodiment of the present invention eight computer equipment.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
It also should be noted that only the parts related to the present invention are shown for ease of description, in attached drawing rather than
Full content.It should be mentioned that some exemplary embodiments are described before exemplary embodiment is discussed in greater detail
At the processing or method described as flow chart.Although operations (or step) are described as the processing of sequence by flow chart,
It is that many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operations can be by again
It arranges.The processing can be terminated when its operations are completed, it is also possible to have the additional step being not included in attached drawing.
The processing can correspond to method, function, regulation, subroutine, subprogram etc..
Embodiment one
Fig. 1 a is a kind of flow chart of the reminding method for background music that the embodiment of the present invention one provides, and the present embodiment can fit
The case where for including the video of background music by video class client terminal playing, this method can be provided by the embodiment of the present invention
The suggestion device of background music execute, the mode which can be used software and/or hardware is realized, which can be integrated in
In video class client for providing video playing service, it is used cooperatively with video server.As shown in Figure 1a, the present embodiment
Method specifically include:
S110, target video is played in video playing interface.
In the present embodiment, the view that is installed on mobile terminal or PC (Personal Computer, personal computer) end
Frequency class client end response is in the video play operation of user, for example, clicking certain in video (typical, small video) recommendation page
One video then starts to play the video content that user specifies in video playing interface.Illustratively, mobile terminal can be intelligence
Energy mobile phone or tablet computer etc., target video is the video that will be played specified by user.
S120, obtain with the matched background music information of the target video, include: background in the background music information
Music description information.
In the present embodiment, can according to the identification information of target video, to the request of corresponding video server with
The corresponding background music information of the target video, with acquisition and the matched background music information of the target video, alternatively, can also
To directly acquire according to the mapping relations between the identification information of the video locally prestored and corresponding background music information
With the matched background music information of the target video.
Wherein it is possible to request back corresponding with the target video to video server when the target video starts to play
Scape music information, or when can also start to include background music in the currently playing content of the target video, to video
Server requests background music information corresponding with the target video, alternatively, can also be according to user in video playing interface
The setting button of click triggers to video server and requests background music information corresponding with the target video etc., the present embodiment
To this and it is not limited.
Specifically, the background music information be with the associated information of background music that is played in the video, for example, being used for
The background music essential information is described, High-speed clarification is allowed the user to or positions the background music description letter of the background music
Breath.Typically, which can be the music name of background music.It is, of course, understood that a video
In may include being in the whole playing intervals for thering is multistage background music or one section of background music to be not present in video
It can also include that background music be regarded in the target convenient for the background music being accurately positioned in video, in the background music information
Start-stop play position in frequency etc..
It should be noted that the identification information of video and corresponding background can be previously stored in video server
Mapping relations between music information, and then after video server receives the identification information of the target video, can be with
Background music information corresponding with the target video is directly acquired by above-mentioned mapping relations, and feeds back to the video class visitor
Family end；
It further, can be real-time if the not stored identification information for having target video in the video server
The background music for including in the target video is extracted, and (includes each music with the music libraries prestored by the background music
Background music information) it is matched, acquisition background music information corresponding with the matched music of the background music feeds back to described
Video class client.
S130, in the playing process of the target video, the background music description information is supplied to user.
In the present embodiment, on the basis of getting the background music of currently playing video, by way of interface display
Background music description information is supplied to user.Illustratively, video class client is got current during playing video
The background music for including in video is played, currently playing video page vertical screen can be converted to by transverse screen displaying and shown, regarded
Background sound description information is shown below frequency play area, while further being shown and current back below background music description information
The relevant recommendation video data of scape music, user can slide mobile phone screen viewing relevant information according to demand.
Optionally, the process that background music is supplied to user is also possible that in getting currently playing video and includes
Background music after, do not change the broadcast state of current video, in the video playing interface, show one it is new for mentioning
For the function button (background music prompt options) of background music prompt service；According to the user to the music tip option
Selection, the background music description information is supplied to the user.
In this optional embodiment, background music prompt choosing is further provided at video playing interface according to user demand
, when recognizing the corresponding background music of video, the position that user watches video is not only influenced in broadcast interface, shows background
Music tip option can choose above-mentioned background music prompt options, at this time again when user is interested in current background music
Background music related content is shown to user.
Optionally, in the video playing interface, display background music tip option, comprising:
In the video playing interface, the background music prompt options are shown by floating layer.
In this optional embodiment, after recognizing background music information, i.e., the figure layer above the video playing page is outstanding
It is floating to show that background music prompts icon, for prompting user currently to have the background music recognized.Illustratively, such as Fig. 1 b institute
Show, the icon of a circumflex shape is shown on the right side of the video playing page.
Optionally, the selection according to the user to the music tip option, will be with the background music description information
It is supplied to the user, comprising:
Selection according to the user to the music tip option is shown with the associated setting in the video playing interface
In region, with the display format of setting, the background music description information is supplied to the user；
Wherein, the background music description information includes at least one of following: the work of the title of background music, background music
The affiliated album of person, the player of background music or singer and background music.
In this optional embodiment, after user is interested in current background music and has selected music tip option,
The background music description got can be shown in the form of setting in preset information display area in video playback area
Information.Illustratively, when user's vertical screen watches video, setting display area can be the lower section of the video playing page, when with
When family transverse screen watches video, function can be shown by split screen, display area is set on the right side of video playback area, setting is aobvious
Show that form can be card form or pop-up form, is not specifically limited here.
It optionally, will be described with the display format of setting and in the associated setting display area in the video playing interface
Background music description information is supplied to the user, comprising:
In the bottom at the video playing interface, in the form of card, by floating layer by the background music description information
It is supplied to the user.
Video playback area in this optional embodiment, after user selects background music prompt options, in the page
Lower section is shown as shown in first card below video in Fig. 1 c comprising background musics such as background music title, author, albums
The card of description information.Wherein, above-mentioned card is also to be different from video playing figure layer, is shown in the floating layer of display interface.
Optionally, the card is that can click card, the broadcast address pass for clicking card and the background music
Connection.
In this optional embodiment, click card comprising background music broadcast address when above-mentioned card, when user into
When one beans-and bullets shooter hits above-mentioned card, the page can jump directly to background music and play the page, and user can directly play the background sound
It is happy.
Optionally, in the bottom of the card, display and the matched correlation recommendation information of the background music.
In this optional embodiment, also display second card piece below video such as in Fig. 1 c is clicked below card above-mentioned
Shown in other recommendation informations relevant to background music, for example, the corresponding song MV of background music, concert or with the song
The episodes etc. of Qu Zuowei theme song, user can jump to associated recommendation video page by clicking lower section recommendation information
Face.
In the present embodiment, get with after the background music of currently playing video matching, above the video playing page
Figure layer shows background music prompt options, when detecting that user selects the operation of background music prompt options, shows background sound
Happy description information and associated recommendation information realize the effect for obtaining video background music in real time in video display process,
It solves the problems, such as that user's lookup background music process is cumbersome, saves user time.
Embodiment two
Fig. 2 is a kind of flow chart of the reminding method of background music provided by Embodiment 2 of the present invention, more than the present embodiment
It states and optimizes based on embodiment, in the present embodiment, will acquire and the matched background music information of target video, embody
Are as follows: the identification information of the target video is sent to server, and obtains the server feedback, with the target video
Matched background music information；Wherein, the server is previously stored with the mapping relations between video and background music information,
Alternatively, the server according to the audio content for including in the target video, is calculated and the target video in real time
The background music information matched.
Correspondingly, background music description information is supplied to user, is specifically included in the playing process of target video:
According to the start-stop play position, duration section of the background music in the target video is determined；If it is determined that the mesh
The current play position of mark video is located in the duration section, then the background music description information is supplied to the use
Family.
Correspondingly, the method for the embodiment of the present invention includes:
S210, target video is played in video playing interface.
S220, the identification information of the target video is sent to server, and obtains the server feedback, with institute
State the matched background music information of target video；
Wherein, the server is previously stored with the mapping relations between video and background music information, alternatively, the clothes
Device be engaged according to the audio content for including in the target video, is calculated in real time and the matched background of the target video
Music information.
Optionally, in the background music information further include: start-stop of the background music in the target video plays position
It sets.
In the present embodiment, by sending server for the identification information of currently playing video, video is carried out by server
The identification of background music, the final background music information with currently playing video matching for receiving server feedback.Wherein, video
Identification information can be the broadcasting network address of video.
In the present embodiment, the mapping relations of video and background music can be stored in advance in server, wherein a video
At least one background music is corresponded to, includes also the start-stop play position of the music in video in per song information, works as service
After device receives video recognition information, currently playing video is determined by the identification information, to determine according to above-mentioned mapping relations
With the background music information for currently broadcasting video matching, when not including current view to be identified in the pre-stored mapping relations of server
When frequency, the audio content that can include by current video is calculated and the target video by Music Recognition Algorithm
The background music information matched.Illustratively, after server receives video playing address, determination is worked as from mapping relations
Preceding broadcasting video, and further inquire background music corresponding with current video.
S230, according to the start-stop play position, determine duration section of the background music in the target video.
In the present embodiment, position also is played comprising the start-stop of background music in video in the background music information that obtains in real time
It sets, the period that background music survives in video is determined by the start-stop position, for example, video total duration being played on is
10 minutes, when the position of video playing to 30%-50%, background music 1 is played, when the position of video playing to 60%-70%
When setting, background music 2 is played, then can determine that background music 1 is present in video by the start-stop play position of above-mentioned music
3rd minute to the 5th minute, background music 2 was present in the 6th minute to the 7th minute of video.
S240, if it is determined that the current play position of the target video is located in the duration section, then will be described
Background music description information is supplied to user.
In the present embodiment, in video display process, one section of video can correspond to multistage background music, only broadcast in video
It puts in the period survived to a certain specific background music, just the relevant information of the background music can be prompted to user.It is right
It answers, in the citing of step 230, background music 1 can be provided a user when video playing was by the 3rd minute to the 5th minute
Relevant information, and when video playing was by the 6th minute to the 7th minute, provide a user the relevant information of background music 2.
In the present embodiment, background music is determined by the start-stop position of the background music that gets in currently playing video
The period survived in video provides a user the background when in video playing to specific background music duration section
The relevant information of music, the technical solution of the present embodiment can provide corresponding description letter in background music play time section
Breath, so that user is bright to be compareed while hearing background music and read associated description information.
Embodiment three
The flow chart of the recognition methods of background music, this implementation in a kind of video that Fig. 3 provides for the embodiment of the present invention three
Example is applicable to the case where carrying out background music identification using the frequency domain character of audio, and this method can be mentioned by the embodiment of the present invention
The identification device of background music executes in the video of confession, and the mode which can be used software and/or hardware is realized, the device
It can be in integrating server.As shown in Figure 1, the method for the present embodiment specifically includes:
S310, video to be identified is obtained, and extracts the audio content in the video.
In embodiment itself, in video display process, server obtains the view for needing to carry out background music identification first
Frequently, and from video file extract respective audio content.It wherein, include background music in audio content.
S320, according to the frequency domain character of the audio content, obtain multiple Meier scales corresponding with the audio content
The frequency domain character point of form, and according to the comparison music of each frequency domain character the point construction and the match audio content of the video
Fingerprint.
Wherein, the original audio got in the step 310 is the loudness data in timing, and is generally comprised various each
The noise of sample is easy if extracting the feature of original audio directly from timing by the noise being superimposed upon on original audio
Influence reduced so as to cause the accuracy rate of music recognition so that data distribution varies widely.Also, even if same sound
Happy different Cover Version sheets, also there are larger differences with master music in time series data distribution, therefore, extract in timing
The feature of original audio, which carries out background music, which knows method for distinguishing, has the lower defect of robustness.
In the present embodiment, to solve the above-mentioned problems, the audio in time domain that will acquire first is transformed on frequency domain, from
And the frequency domain character of audio content is obtained, for example, frequency domain character may include the corresponding frequency of audio and energy of certain time length
Magnitude.But since perception of the human ear for frequency is not linear, it is therefore desirable to further be converted to frequency values, by frequency
It is converted into Meier scale, obtains the frequency domain character point of multiple Meier scaled versions, finally according to the frequency domain character point structure in audio
The music fingerprint for making video sound intermediate frequency content, the identification for background music.Specifically, firstly, by the audio content in video
Multiple windows are divided into, and are transformed on frequency domain respectively, to obtain frequency and its corresponding energy value, and further will frequency
Rate is converted into Meier scale, then in global search energy extreme point, and using the corresponding Meier scale of energy extreme point as frequency
These frequency domain character points are finally grouped processing according to setting means by characteristic of field point, and every group obtains comparison music
Fingerprint, and all the set composition ratio of music sub fingerprint is compared to music fingerprint.Illustratively, the comparison music sub fingerprint can
Frequency domain character point to be continuous, specified quantity corresponds to cryptographic Hash, is also possible to above-mentioned cryptographic Hash and first frequency domain character
The combination that the position of point is constituted, alternatively, by above-mentioned cryptographic Hash, the position of first frequency domain character point and first and last frequency domain character point
Time difference constitute combination.
S330, the comparison music fingerprint by the video, are matched with the standard music fingerprint of music each in music libraries,
Obtain target music corresponding with the video.
Wherein, standard music fingerprint is made as made of the frequency domain character point construction of the standard music stored in music libraries
For the comparison standard in background music identification.
In the present embodiment, the standard music fingerprint in music libraries is extracted, then refers to comparison music obtained in step 320
Line is matched with the standard music fingerprint in music libraries, is needed in matching process by the comparison music fingerprint of current audio content
Matched with the whole standard music fingerprints stored in music libraries, finally will with the matched standard music of present video as with
The corresponding target music of the video.
S340, the music description information for obtaining the target music, as with the matched background music of the target video
Information.
In the present embodiment, on the basis of step 330 has determined target music corresponding with currently playing video, determine with
The corresponding music description information (for example, the information such as musical designation, author or singer) of above-mentioned target music, and further will
The music description information of above-mentioned target music is as the background music information with currently playing video matching, to watch in user
In journey it should be understood that when background music details, it is supplied to user in time.
In the present embodiment, by will be transformed on frequency domain from the audio content extracted in video, so that it is determined that audio
The frequency domain character point of Meier scaled version, and music fingerprint further is compared according to frequency domain character point construction is corresponding with audio,
It is matched eventually by the standard music fingerprint for including in music fingerprint and music libraries will be compared, determines mesh corresponding to video
Mark with phonetic symbols is happy.On the one hand, the music fingerprint of the frequency domain character point construction of Meier scaled version effectively increases the success of music recognition
Rate and accuracy, on the other hand, using the target music description information of acquisition as the background music with currently playing video matching
Information can effectively meet the background music identification demand of user, save the time of user.
Example IV
The flow chart of the recognition methods of background music, this implementation in a kind of video that Fig. 4 a provides for the embodiment of the present invention four
Example optimized based on above-described embodiment, in the present embodiment, according to the frequency domain character of the audio content, will obtain with
The frequency domain character point of the corresponding multiple Meier scaled versions of the audio content, and according to each frequency domain character point construction and institute
The comparison music fingerprint for stating the match audio content of video, is embodied as: the spectrogram with the match audio content is obtained, and
Each Frequency point in the spectrogram is converted into corresponding Meier scale；Whole energy extreme values are searched in the spectrogram
Point, and obtain Meier scale corresponding with each energy extreme point and be used as frequency domain character point, constructs and the video
The comparison music fingerprint of match audio content.
Correspondingly, the method for the embodiment of the present invention includes:
S410, video to be identified is obtained, and extracts the audio content in the video.
S420, obtain with the spectrogram of the match audio content, and each Frequency point in the spectrogram is converted
For corresponding Meier scale.
Wherein, spectrogram is that the audio in timing is transformed on frequency domain, obtained expression signal time, frequency and energy
The map of relationship between amount, Meier scale are the scale based on audience equally spaced from each other to the perception judgement of high pitch, this scale
It is the tone that the high pitch of 1000 Meiers is appointed as to 100Hz that reference point between normal frequency, which defines,.
In the present embodiment, the audio in timing is transformed into the time for obtaining indicating present video on frequency domain, frequency first
And between energy relationship map, but due to human ear be not for the perception of frequency it is linear, by above-mentioned spectrogram
In audio frequency be converted to the appreciable Meier scale of human ear, finally obtained spectrogram is as shown in Figure 4 b, audio frequency
Conversion relational expression between Meier scale is as follows:
Wherein, f is the frequency of audio.
Optionally, the spectrogram with the match audio content is obtained, comprising:
According to setting time window, and setting sliding step, frequency-region signal processing is carried out to the audio content, is obtained
Spectrogram corresponding with the audio content；
Wherein, the spectrogram defines the energy value under assigned frequency point and specified time point.
In this optional embodiment, audio signal is carried out according to the time window of setting and setting sliding step first
It divides, the multistage audio signal as unit of setting time window is obtained, for example, each window may include 5 seconds audios.So
Carrying out discrete Fourier transform (Discrete Fourier Transform, DFT) respectively to the audio in each window afterwards will
Audio is transformed into frequency domain from time domain, the frequency of audio and its corresponding energy value in specific time is obtained, finally by each window
Frequency, energy value and its corresponding time of sound intermediate frequency constitute spectrogram, and in the spectrogram, horizontal axis indicates time, longitudinal axis table
Show that the frequency of audio, color indicate the corresponding energy value under specific time and frequency.
S430, whole energy extreme points are searched in the spectrogram, and acquisition is right respectively with each energy extreme point
The Meier scale answered is as frequency domain character point, the comparison music fingerprint of construction and the match audio content of the video.
In the present embodiment, whole energy extreme points in audio are obtained first in spectrogram, wherein energy extreme point table
Showing in spectrogram, energy value is greater than left and right Frequency point adjacent thereto, the i.e. maximum point in certain time range self-energy value,
Then on the basis of each Frequency point being converted to corresponding Meier scale at step 420, whole energy extreme point pair is determined
The Meier scale answered is as frequency domain character point, and further, in the way of setting, the processing of above-mentioned frequency domain character point generates
The music fingerprint of present video.
Optionally, described that whole energy extreme points are searched in the spectrogram, and obtain and each energy extreme point
Corresponding Meier scale constructs the comparison music fingerprint with the match audio content of the video as frequency domain character point,
Include:
Will frequency domain character point corresponding with each energy extreme point, be ranked up according to chronological order；
In ranking results, obtains continuous, setting quantity the frequency domain character point and constitute at least one extreme value point set
Close, and according in the extreme value point set each frequency domain character point and the extreme value point set in first frequency domain character point
Corresponding time point calculates cryptographic Hash；
The cryptographic Hash corresponding with each extreme value point set and with feature extreme value first in extreme value point set
At point corresponding time point, construction is corresponding with each extreme value point set to compare music sub fingerprint；
By the set for comparing music sub fingerprint corresponding with each extreme value point set, as in the audio of the video
Hold matched comparison music fingerprint.
In this optional embodiment, the specific side for specifically constructing according to frequency domain character point and comparing music fingerprint is provided
Formula, in a specific example: firstly, by the corresponding frequency domain character point of the whole extreme points arrived in global search when
It is ranked up on domain, obtains frequency domain character point 1 according to time sequence, 2,3,4,5,6, it, will then in obtained ranking results
Three continuous frequency domain character points constitute an extreme value point set, can further obtain four extreme value point sets (1,2,3),
(2,3,4), (3,4,5), (4,5,6).Secondly, by frequency domain character point each in extreme value point set and first frequency domain character point pair
The time point answered, which connects, calculates cryptographic Hash SHA1, finally, by the corresponding cryptographic Hash of extreme value point set, Yi Jiji
It is worth the corresponding time point combination composition ratio of first feature extreme point in point set to music sub fingerprint, i.e., each extreme value point set pair
Answer a comparison music sub fingerprint, that is to say, that (every height refers to available multiple comparison music sub fingerprints in a segment of audio
Line is all by SHA1 value, initial position and background music information composition), finally by the corresponding comparison music of each extreme value point set
The set that sub fingerprint is constituted becomes as the music fingerprint of this section audio and compares music fingerprint.
S440, the comparison music fingerprint by the video, are matched with the standard music fingerprint of music each in music libraries,
Obtain target music corresponding with the video.
Optionally, it by the comparison music fingerprint of the video, is carried out with the standard music fingerprint of music each in music libraries
Matching, before obtaining target music corresponding with the video, further includes:
A music in music libraries is successively obtained as currently processed music；
Obtain spectrogram corresponding with the currently processed music；
Each Frequency point in the spectrogram is converted into corresponding Meier scale；
Whole energy extreme points are searched in the spectrogram, and obtain plum corresponding with each energy extreme point
That scale is as frequency domain character point, construction and the currently processed matched standard music fingerprint of music；
It returns to the music for executing and successively obtaining in music libraries to operate as currently processed music, until completing to described
The processing of whole music in music libraries.
In this optional embodiment, the building of music fingerprint is carried out to all music in music libraries according to certain sequence, directly
Whole music fingerprints that whole music include into acquisition music libraries.Wherein, specific music fingerprint construction method is auspicious sees step
The description of 420~step 430, details are not described herein again.
S450, the music description information for obtaining the target music, as with the matched background music of the target video
Information.
In the present embodiment, when including assigned frequency point and be specified by handling to obtain to audio content progress frequency-region signal
Between put the spectrogram of lower energy value, and using the corresponding Meier scale of energy extreme point in spectrogram as frequency domain character point, and most
It is constructed eventually according to above-mentioned frequency domain character point and compares music fingerprint, the identification for background music, wherein according to energy extreme point
The method that Meier scale construction compares music fingerprint effectively increases background music identification recall rate.
Embodiment five
The flow chart of the recognition methods of background music, this implementation in a kind of video that Fig. 5 a provides for the embodiment of the present invention five
Example is optimized based on above-described embodiment, in the present embodiment, by the comparison music fingerprint of the video, in music libraries
The standard music fingerprint of each music is matched, and is obtained target music corresponding with the video, is embodied as: respectively will be with institute
State the corresponding multiple comparison music sub fingerprints of video, multiple standard music corresponding with each music in the music libraries
Sub fingerprint is matched, and screening obtains described comparing corresponding at least one standard of music sub fingerprint with each of the video
Music sub fingerprint is as object matching music sub fingerprint；Each temporal information for comparing music sub fingerprint is calculated, and it is corresponding
At least one target criteria music sub fingerprint temporal information between time difference；According to affiliated music, to each mesh
Mark matching music sub fingerprint is sorted out, and counts the maximum number of repetitions for the same time difference for including in each classification；It obtains
The maximum target category of maximum number of repetitions value is taken, and is more than setting threshold in the maximum number of repetitions value for determining the target category
When value, will music corresponding with the target category as the target music.
Correspondingly, the method for the embodiment of the present invention includes:
S510, video to be identified is obtained, and extracts the audio content in the video.
S520, according to the frequency domain character of the audio content, obtain multiple Meier scales corresponding with the audio content
The frequency domain character point of form, and according to the comparison music of each frequency domain character the point construction and the match audio content of the video
Fingerprint.
S530, respectively will multiple comparison music sub fingerprints corresponding with the video, with each sound in the music libraries
Happy corresponding multiple standard pronunciation fun fingerprints are matched, and screening obtains referring to each music that compares of the video
At least one corresponding standard pronunciation fun fingerprint of line is as object matching music sub fingerprint.
In the present embodiment, the standard pronunciation fun fingerprint that sort according to chronological order is extracted from music libraries, for
The corresponding comparison music sub fingerprint of the audio content for including in video is matched, and the SHA1 of music sub fingerprint is filtered out and compare
It is worth identical standard pronunciation fun fingerprint.
S540, each temporal information for comparing music sub fingerprint is calculated, at least one corresponding target criteria sound
Time difference between the temporal information of fun fingerprint.
In the present embodiment, according to music preceding, video is rear, as shown in Figure 5 b, for the identical sub fingerprint of SHA1 value, meter
Each temporal information for comparing music sub fingerprint is calculated, with the time between the temporal information of corresponding target criteria music sub fingerprint
Difference.Illustratively, in figure 5b, the sub fingerprint a, b, d in standard music are corresponding with the sub fingerprint 1,2,3 in Video Music respectively
(i.e. SHA1 value is identical) then determines sub fingerprint a respectively, and the time and sub fingerprint 1,2,3 of b, d in standard music are in video
Time in music, and calculate the time difference of the sub fingerprint to match one by one, the time difference that finally will acquire, video identifier letter
The location information of breath, the identification information of standard music and comparison music sub fingerprint (i.e. the sub fingerprint of music in video) is corresponding to be protected
It deposits.
S550, according to affiliated music, each object matching music sub fingerprint is sorted out, and count each class
The maximum number of repetitions for the same time difference for including in not.
In the present embodiment, since the sub fingerprint in Video Music may match with the sub fingerprint of multiple standard music, because
This sorts out object matching sub fingerprint according to its affiliated music.Illustratively, refer in video comprising 10 comparison music
Line, respectively with include in the quasi- music of three heads in song library standard pronunciation fun fingerprint matching success, then need to determine respectively this three
(correspondence saves in corresponding step 540 with the time difference corresponding to the matched sub fingerprint of music sub fingerprint is compared in the quasi- music of head
Time difference), and further count the maximum number of repetitions of same time difference.
S560, the maximum target category of maximum number of repetitions value is obtained, and in the maximum repetition for determining the target category
Secondary numerical value be more than given threshold when, will music corresponding with the target category as the target music.
In the present embodiment, according to the maximum for the same time difference that per song includes in the music libraries counted in step 550
Number of repetition, and using the most music of number of repetition as candidate music, it is then that the same time for including in candidate music is poor
Number of repetition compared with preset confidence threshold value, when the number be more than given threshold when, using the candidate music as mesh
Mark with phonetic symbols is happy.
Optionally, it is worth maximum target category in the acquisition maximum number of repetitions, and is determining the target category
Maximum number of repetitions value be more than given threshold when, will music corresponding with the target category as the target music after,
Further include:
Sequentially in time, it obtains in the video, the first place with the standard pronunciation fun fingerprint matching of the target music
It compares music sub fingerprint and last bit compares music sub fingerprint；
Music sub fingerprint and the corresponding time letter of last bit comparison music sub fingerprint are compared according to the first place
Breath, determines start-stop play position of the background music in the video.
In this optional embodiment, in order to determine the start-stop play position of background music in video, need to find timing
The first place of upper and target music standard pronunciation fun fingerprint matching compares music sub fingerprint and last bit compares music sub fingerprint, and really
Its fixed corresponding temporal information.Illustratively, as shown in Figure 5 b, it is corresponding with target music in video for comparing music sub fingerprint 1
It is the first compare music sub fingerprint, comparing music sub fingerprint 3 is that last bit corresponding with target music compares music and refers in video
Line, since the comparison music sub fingerprint in above-mentioned video is arranged according to chronological order, then above-mentioned the first and last bit
Comparison music sub fingerprint corresponding to the start-stop play time of the background music that as currently recognizes of time point in video.
S570, the music description information for obtaining the target music, as with the matched background music of the target video
Information.
Optionally, the start-stop of the music description information and background music of the target music in the video is broadcast
Position is put, it is described to be added to the background music information storage corresponding with the target video of the target video.
In this optional embodiment, by what is determined in timing, background music start-stop play position in video and
The music description information of target music is corresponding with target video to be saved, so that being played to the start bit of background music in target video
When setting, background music prompt is carried out to user.
In the present embodiment, include by comparing video in the standard music fingerprint stored in music fingerprint and music libraries
Sub fingerprint is matched, and obtains and compare the matched whole standard pronunciation fun fingerprints of music sub fingerprint as object matching music
Fingerprint, then by calculate and count compare music sub fingerprint and the time difference between corresponding object matching music sub fingerprint it is true
Candidate music is made, when the sub fingerprint identical with the music sub fingerprint time difference is compared for including in candidate music is more than preset sets
When confidence threshold, it can confirm that current candidate music is standard music corresponding with background music, which effectively improves
The efficiency of music recognition realizes the effect of quickly identification background music.
Embodiment six
Fig. 6 is a kind of structural schematic diagram of the suggestion device for background music that the embodiment of the present invention six provides, such as Fig. 6 institute
Show, described device includes: target video playing module 610, background music data obtaining module 620 and background music information
Cue module 630.Wherein:
Target video playing module 610, for playing target video in video playing interface；
Background music data obtaining module 620, it is described for acquisition and the matched background music information of the target video
It include: background music description information in background music information；
Background music nformation alert module 630, in the playing process of the target video, by the background music
Description information is supplied to user.
The embodiment of the invention provides a kind of suggestion devices of background music, by being obtained in video display process in real time
The background music information to match with currently playing target video is taken, and above-mentioned background music information is supplied to user, it is real
User is showed during watching video, the effect of background music in video can be obtained without exiting the video-see page.
On the basis of the various embodiments described above, in the background music information further include: background music is regarded in the target
Start-stop play position in frequency；
Background music nformation alert module 630, comprising:
Period determination unit, for determining background music in the target video according to the start-stop play position
Duration section；
Period prompt unit, for if it is determined that the current play position of the target video is located at the duration
In section, then the background music description information is supplied to the user.
On the basis of the various embodiments described above, background music nformation alert module 630, further includes:
Prompt options display unit is used for the display background music tip option in the video playing interface；
Background music information alert unit will be described for the selection according to the user to the music tip option
Background music description information is supplied to the user.
On the basis of the various embodiments described above, prompt options display unit can be specifically used for:
In the video playing interface, the background music prompt options are shown by floating layer.
On the basis of the various embodiments described above, background music information alert unit, comprising:
Information alert subelement is broadcast for the selection according to the user to the music tip option with the video
It puts in the associated setting display area in interface, with the display format of setting, the background music description information is supplied to described
User；
Wherein, the background music description information includes at least one of following: the work of the title of background music, background music
The affiliated album of person, the player of background music or singer and background music.
On the basis of the various embodiments described above, information alert subelement, comprising:
Card prompts subelement, in the bottom at the video playing interface, in the form of card, by floating layer by the back
Scape music description information is supplied to the user.
On the basis of the various embodiments described above, the card is that can click card, described to click card and the background
The broadcast address of music is associated with.
On the basis of the various embodiments described above, card prompts subelement, can be specifically used for:
In the bottom of the card, display and the matched correlation recommendation information of the background music.
On the basis of the various embodiments described above, background music data obtaining module 620 can be specifically used for:
The identification information of the target video is sent to server, and obtains the server feedback, with the mesh
Mark the background music information of video matching；
Wherein, the server is previously stored with the mapping relations between video and background music information, alternatively, the clothes
Device be engaged according to the audio content for including in the target video, is calculated in real time and the matched background of the target video
Music information.
The prompt side of background music provided by any embodiment of the invention can be performed in the suggestion device of above-mentioned background music
Method has the corresponding functional module and beneficial effect of the reminding method for executing background music.
Embodiment seven
The structural schematic diagram of the identification device of background music in a kind of video that Fig. 7 provides for the embodiment of the present invention seven, such as
Shown in Fig. 7, described device includes: audio content extraction module 710, compares music fingerprint constructing module 720, and target music obtains
Module 730 and description information memory module 740.Wherein:
Audio content extraction module 710 for obtaining video to be identified, and extracts the audio content in the video；
Music fingerprint constructing module 720 is compared to obtain and the audio for the frequency domain character according to the audio content
The frequency domain character point of the corresponding multiple Meier scaled versions of content, and according to each frequency domain character point construction and the video
The comparison music fingerprint of match audio content；
Target music obtains module 730, for the mark by the comparison music fingerprint of the video, with music each in music libraries
Quasi- music fingerprint is matched, and target music corresponding with the video is obtained；
Description information memory module 740, for obtaining the music description information of the target music, as with the target
The background music information of video matching.
In the present embodiment, by will be transformed on frequency domain from the audio content extracted in video, so that it is determined that audio
The frequency domain character point of Meier scale frequency form, and further compare music according to frequency domain character point construction is corresponding with audio and refer to
Line is matched eventually by will compare the standard music fingerprint for including in music fingerprint and music libraries, and determination is corresponding with video
Target music.On the one hand, the music fingerprint of the frequency domain character point construction of Meier scaled version effectively increases music recognition
Success rate and accuracy, on the other hand, using the target music description information of acquisition as the background with currently playing video matching
Music information can effectively meet the background music identification demand of user, save the time of user.
On the basis of the various embodiments described above, the comparison music fingerprint constructing module 720, comprising:
Spectrogram acquiring unit, for obtain with the spectrogram of the match audio content, and will be in the spectrogram
Each Frequency point is converted to corresponding Meier scale；
Compare music fingerprint structural unit, for searching for whole energy extreme points in the spectrogram, and obtain with it is each
The corresponding Meier scale of the energy extreme point is as frequency domain character point, construction and the match audio content of the video
Compare music fingerprint.
On the basis of the various embodiments described above, the spectrogram acquiring unit can be specifically used for:
According to setting time window, and setting sliding step, frequency-region signal processing is carried out to the audio content, is obtained
Spectrogram corresponding with the audio content；
Wherein, the spectrogram defines the energy value under assigned frequency point and specified time point.
On the basis of the various embodiments described above, the comparison music fingerprint structural unit can be specifically used for:
Will frequency domain character point corresponding with each energy extreme point, be ranked up according to chronological order；
In ranking results, obtains continuous, setting quantity the frequency domain character point and constitute at least one extreme value point set
Close, and according in the extreme value point set each frequency domain character point and the extreme value point set in first frequency domain character point
Corresponding time point calculates cryptographic Hash；
The cryptographic Hash corresponding with each extreme value point set and with feature extreme value first in extreme value point set
At point corresponding time point, construction is corresponding with each extreme value point set to compare music sub fingerprint；
By the set for comparing music sub fingerprint corresponding with each extreme value point set, as in the audio of the video
Hold matched comparison music fingerprint.
On the basis of the various embodiments described above, the target music obtains module 730, comprising:
Match music sub fingerprint acquiring unit, for respectively will multiple comparison music sub fingerprints corresponding with the video,
Multiple standard pronunciation fun fingerprints corresponding with each music in the music libraries are matched, and screening obtains and the view
At least one corresponding standard pronunciation fun fingerprint of each comparison music sub fingerprint of frequency refers to as object matching music
Line；
Time difference calculating unit, for calculate it is each it is described compare music sub fingerprint temporal information, with it is corresponding at least
Time difference between the temporal information of one target criteria music sub fingerprint；
Time difference statistic unit, for sorting out to each object matching music sub fingerprint according to affiliated music,
And count the maximum number of repetitions for the same time difference for including in each classification；
Target music determination unit for obtaining the maximum target category of maximum number of repetitions value, and is determining the mesh
Mark classification maximum number of repetitions value be more than given threshold when, will music corresponding with the target category as the target sound
It is happy.
On the basis of the various embodiments described above, the identification device of background music in the video, further includes:
First and last compares music sub fingerprint and obtains module, for being worth maximum target class in the acquisition maximum number of repetitions
It not, will be corresponding with the target category and when the maximum number of repetitions value for determining the target category is more than given threshold
It after music is as the target music, sequentially in time, obtains in the video, the standard music with the target music
The matched the first comparison music sub fingerprint of sub fingerprint and last bit compare music sub fingerprint；
Play position determining module, for comparing music sub fingerprint and last bit comparison music according to the first place
The corresponding temporal information of fingerprint determines start-stop play position of the background music in the video.
The description information memory module 740, can be specifically used for:
By the start-stop play position of the music description information and background music of the target music in the video,
It is described to be added to the background music information storage corresponding with the target video of the target video.
On the basis of the various embodiments described above, the identification device of background music in the video, further includes:
Currently processed music obtains module, and each in music libraries in the comparison music fingerprint by the video
The standard music fingerprint of music is matched, and before obtaining target music corresponding with the video, is successively obtained in music libraries
A music as currently processed music；
Currently processed music frequency spectrum figure obtains module, for obtaining spectrogram corresponding with the currently processed music；
Meier scales transforming module, for each Frequency point in the spectrogram to be converted to corresponding Meier scale；
Standard music fingerprint constructing module searches for whole energy extreme points in the spectrogram, and obtain with it is each described
The corresponding Meier scale of energy extreme point is as frequency domain character point, construction and the currently processed matched standard pronunciation of music
Happy fingerprint；
Music circulation processing module, for returning to the music executed successively obtain in music libraries as currently processed sound
Happy operation, until completing the processing to music whole in the music libraries.
Background in video provided by any embodiment of the invention can be performed in the identification device of background music in above-mentioned video
The recognition methods of music has the corresponding function module and beneficial effect for executing the recognition methods of background music in video.
Embodiment eight
Fig. 8 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention eight provides.Fig. 8, which is shown, to be suitable for being used to
Realize the block diagram of the exemplary computer device 12 of embodiment of the present invention.The computer equipment 12 that Fig. 8 is shown is only one
Example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 8, computer equipment 12 is showed in the form of universal computing device.The component of computer equipment 12 can be with
Including but not limited to: one or more processor or processing unit 16, system storage 28 connect different system components
The bus 18 of (including system storage 28 and processing unit 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by
The usable medium that computer equipment 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Computer equipment 12 may further include it is other it is removable/can not
Mobile, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing not
Movably, non-volatile magnetic media (Fig. 8 do not show, commonly referred to as " hard disk drive ").It, can be with although being not shown in Fig. 8
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") is provided, and non-volatile to moving
The CD drive of CD (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driving
Device can be connected by one or more data media interfaces with bus 18.Memory 28 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform of the invention each
The function of embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.Program mould
Block 42 usually executes function and/or method in embodiment described in the invention.
Computer equipment 12 can also be with one or more external equipments 14 (such as keyboard, sensing equipment, display 24
Deng) communication, can also be enabled a user to one or more equipment interact with the computer equipment 12 communicate, and/or with make
The computer equipment 12 any equipment (such as network interface card, the modulatedemodulate that can be communicated with one or more of the other calculating equipment
Adjust device etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, computer equipment 12 may be used also
To pass through network adapter 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network
Network, such as internet) communication.As shown, network adapter 20 is logical by other modules of bus 18 and computer equipment 12
Letter.It should be understood that other hardware and/or software module, packet can be used in conjunction with computer equipment 12 although being not shown in Fig. 8
It includes but is not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, magnetic tape drive
Device and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the reminding method of background music provided by the embodiment of the present invention.
Namely: the processing unit is realized when executing described program: playing target video in video playing interface；
Obtain with the matched background music information of the target video, include: background music in the background music information
Description information；
In the playing process of the target video, the background music description information is supplied to the user.
Alternatively, realize the recognition methods of background music in video provided by the embodiment of the present invention, namely:
Video to be identified is obtained, and extracts the audio content in the video；
According to the frequency domain character of the audio content, multiple Meier scaled versions corresponding with the audio content are obtained
Frequency domain character point, and according to the comparison music fingerprint of each frequency domain character the point construction and the match audio content of the video；
By the comparison music fingerprint of the video, is matched, obtained with the standard music fingerprint of music each in music libraries
Target music corresponding with the video；
The music description information for obtaining the target music, as with the matched background music information of the target video.
Embodiment nine
The embodiment of the present invention nine provides a kind of computer readable storage medium, is stored thereon with computer program, the journey
The reminding method of the background music provided such as all inventive embodiments of the application is provided when sequence is executed by processor.
That is, realization when the program is executed by processor: playing target video in video playing interface；
Obtain with the matched background music information of the target video, include: background music in the background music information
Description information；
In the playing process of the target video, the background music description information is supplied to the user,
Alternatively, realizing that all inventive embodiments of the application such as provide background music in video when the program is executed by processor
Recognition methods.
That is, realization when the program is executed by processor: obtaining video to be identified, and extract the audio in the video
Content；
According to the frequency domain character of the audio content, multiple Meier scaled versions corresponding with the audio content are obtained
Frequency domain character point, and according to the comparison music fingerprint of each frequency domain character the point construction and the match audio content of the video；
By the comparison music fingerprint of the video, is matched, obtained with the standard music fingerprint of music each in music libraries
Target music corresponding with the video；
The music description information for obtaining the target music, as with the matched background music information of the target video.
It can be using any combination of one or more computer-readable media.Computer-readable medium can be calculating
Machine readable signal medium or computer readable storage medium.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example (non exhaustive list) of machine readable storage medium storing program for executing includes: electrical connection with one or more conducting wires, just
Taking formula computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In this document, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (20)
1. a kind of reminding method of background music characterized by comprising
Target video is played in video playing interface；
Obtain with the matched background music information of the target video, include: background music description in the background music information
Information；
In the playing process of the target video, the background music description information is supplied to user.
2. the method according to claim 1, wherein in the background music information further include: background music exists
Start-stop play position in the target video；
It is described in the playing process of the target video, the background music description information is supplied to user, comprising:
According to the start-stop play position, duration section of the background music in the target video is determined；
If it is determined that the current play position of the target video is located in the duration section, then the background music is retouched
It states information and is supplied to the user.
3. method according to claim 1 or 2, which is characterized in that described to be supplied to the background music description information
User, comprising:
In the video playing interface, display background music tip option；
The background music description information is supplied to the use by the selection according to the user to the music tip option
Family.
4. according to the method described in claim 3, it is characterized in that, described in the video playing interface, display background sound
Happy prompt options, comprising:
In the video playing interface, the background music prompt options are shown by floating layer.
5. according to the method described in claim 3, it is characterized in that, it is described according to the user to the music tip option
Selection, will be supplied to the user with the background music description information, comprising:
Selection according to the user to the music tip option, with the associated setting display area in the video playing interface
It is interior, the background music description information is supplied to by the user with the display format of setting；
Wherein, the background music description information includes at least one of following: the title of background music, background music author,
The player or singer of background music and the affiliated album of background music.
6. according to the method described in claim 5, it is characterized in that, with the associated setting display area in the video playing interface
It is interior, the background music description information is supplied to by the user with the display format of setting, comprising:
In the bottom at the video playing interface, in the form of card, the background music description information is provided by floating layer
To the user.
7. according to the method described in claim 6, it is characterized in that, the card be can click card, it is described to click card
It is associated with the broadcast address of the background music.
8. according to the method described in claim 6, it is characterized in that, in the bottom at the video playing interface, with the shape of card
Formula, while the background music description information is supplied to the user by floating layer, further includes:
In the bottom of the card, display and the matched correlation recommendation information of the background music.
9. the method according to claim 1, wherein the acquisition and the matched background music of the target video
Information, comprising:
The identification information of the target video is sent to server, and obtains the server feedback, is regarded with the target
Frequently matched background music information；
Wherein, the server is previously stored with the mapping relations between video and background music information, alternatively, the server
According to the audio content for including in the target video, it is calculated in real time and the matched background music of the target video
Information.
10. the recognition methods of background music in a kind of video characterized by comprising
Video to be identified is obtained, and extracts the audio content in the video；
According to the frequency domain character of the audio content, the frequency domain of multiple Meier scaled versions corresponding with the audio content is obtained
Characteristic point, and according to the comparison music fingerprint of each frequency domain character the point construction and the match audio content of the video；
It by the comparison music fingerprint of the video, is matched, is obtained and institute with the standard music fingerprint of music each in music libraries
State the corresponding target music of video；
The music description information for obtaining the target music, as with the matched background music information of the target video.
11. according to the method described in claim 10, it is characterized in that, the frequency domain character according to the audio content, obtains
It is constructed to the frequency domain character point of multiple Meier scaled versions corresponding with the audio content, and according to each frequency domain character point
With the comparison music fingerprint of the match audio content of the video, comprising:
The spectrogram with the match audio content is obtained, and each Frequency point in the spectrogram is converted into corresponding plum
That scale；
Whole energy extreme points are searched in the spectrogram, and obtain Meier mark corresponding with each energy extreme point
Degree is used as frequency domain character point, the comparison music fingerprint of construction and the match audio content of the video.
12. according to the method for claim 11, which is characterized in that obtain the spectrogram with the match audio content, packet
It includes:
According to setting time window, and setting sliding step, frequency-region signal processing is carried out to the audio content, is obtained and institute
State the corresponding spectrogram of audio content；
Wherein, the spectrogram defines the energy value under assigned frequency point and specified time point.
13. according to the method for claim 11, which is characterized in that described to search for whole energy extreme values in the spectrogram
Point, and obtain Meier scale corresponding with each energy extreme point and be used as frequency domain character point, constructs and the video
The comparison music fingerprint of match audio content, comprising:
Will frequency domain character point corresponding with each energy extreme point, be ranked up according to chronological order；
In ranking results, obtains continuous, setting quantity the frequency domain character point and constitute at least one extreme value point set, and
According in the extreme value point set each frequency domain character point and the extreme value point set in it is corresponding with first frequency domain character point
Time point calculates cryptographic Hash；
The cryptographic Hash corresponding with each extreme value point set and with feature extreme point pair first in extreme value point set
At the time point answered, construction is corresponding with each extreme value point set to compare music sub fingerprint；
By the set for comparing music sub fingerprint corresponding with each extreme value point set, as the audio content with the video
The comparison music fingerprint matched.
14. according to the method described in claim 10, it is characterized in that, the comparison music fingerprint by the video, with sound
The standard music fingerprint of each music is matched in music storehouse, obtains target music corresponding with the video, comprising:
Respectively will multiple comparison music sub fingerprints corresponding with the video, respectively corresponded with each music in the music libraries
Multiple standard pronunciation fun fingerprints matched, screening obtain respectively corresponding with each music sub fingerprint that compares of the video
At least one standard pronunciation fun fingerprint as object matching music sub fingerprint；
Each temporal information for comparing music sub fingerprint is calculated, at least one corresponding target criteria music sub fingerprint
Time difference between temporal information；
According to affiliated music, each object matching music sub fingerprint is sorted out, and counts in each classification and includes
Same time difference maximum number of repetitions；
It obtains maximum number of repetitions and is worth maximum target category, and be more than in the maximum number of repetitions value for determining the target category
When given threshold, will music corresponding with the target category as the target music.
15. according to the method for claim 14, which is characterized in that be worth maximum target in the acquisition maximum number of repetitions
Classification, and when the maximum number of repetitions value for determining the target category is more than given threshold, it will be corresponding with the target category
Music as the target music after, further includes:
Sequentially in time, it obtains in the video, is compared with the first place of the standard pronunciation fun fingerprint matching of the target music
Music sub fingerprint and last bit compare music sub fingerprint；
Music sub fingerprint and the corresponding temporal information of last bit comparison music sub fingerprint are compared according to the first place, really
Determine start-stop play position of the background music in the video；
The music description information by the target music is added to the background music information of the target video and the mesh
Mark the corresponding storage of video, comprising:
By the start-stop play position of the music description information and background music of the target music in the video, it is added
To the background music information storage corresponding with the target video of the target video.
16. according to the method described in claim 10, it is characterized in that, in the comparison music fingerprint by the video, with
The standard music fingerprint of each music is matched in music libraries, before obtaining target music corresponding with the video, further includes:
A music in music libraries is successively obtained as currently processed music；
Obtain spectrogram corresponding with the currently processed music；
Each Frequency point in the spectrogram is converted into corresponding Meier scale；
Whole energy extreme points are searched in the spectrogram, and obtain Meier mark corresponding with each energy extreme point
Degree is used as frequency domain character point, construction and the currently processed matched standard music fingerprint of music；
It returns to the music for executing and successively obtaining in music libraries to operate as currently processed music, until completing to the music
The processing of whole music in library.
17. a kind of suggestion device of background music characterized by comprising
Target video playing module, for playing target video in video playing interface；
Background music data obtaining module, for obtaining and the matched background music information of the target video, the background sound
It include: background music description information in happy information；
Background music nformation alert module, in the playing process of the target video, the background music being described to believe
Breath is supplied to user.
18. the identification device of background music in a kind of video characterized by comprising
Audio content extraction module for obtaining video to be identified, and extracts the audio content in the video；
Music fingerprint constructing module is compared to obtain and the audio content pair for the frequency domain character according to the audio content
The frequency domain character point for the multiple Meier scaled versions answered, and according in the audio of each frequency domain character point construction and the video
Hold matched comparison music fingerprint；
Target music obtains module, for the standard music by the comparison music fingerprint of the video, with music each in music libraries
Fingerprint is matched, and target music corresponding with the video is obtained；
Description information memory module, for obtaining the music description information of the target music, as with the target video
The background music information matched.
19. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes the background as described in any in claim 1-9 when executing described program
The reminding method of music, or realize the recognition methods of background music in the video as described in any in claim 10-16.
20. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The reminding method of the background music as described in any in claim 1-9 is realized when execution, or is realized as in claim 10-16
The recognition methods of background music in any video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611412.1A CN110335625A (en) | 2019-07-08 | 2019-07-08 | The prompt and recognition methods of background music, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611412.1A CN110335625A (en) | 2019-07-08 | 2019-07-08 | The prompt and recognition methods of background music, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110335625A true CN110335625A (en) | 2019-10-15 |
Family
ID=68143255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910611412.1A Pending CN110335625A (en) | 2019-07-08 | 2019-07-08 | The prompt and recognition methods of background music, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110335625A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110958386A (en) * | 2019-11-12 | 2020-04-03 | 北京达佳互联信息技术有限公司 | Video synthesis method and device, electronic equipment and computer-readable storage medium |
| CN110992983A (en) * | 2019-11-26 | 2020-04-10 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device, terminal and storage medium for identifying audio fingerprint |
| CN111161758A (en) * | 2019-12-04 | 2020-05-15 | 厦门快商通科技股份有限公司 | Song listening and song recognition method and system based on audio fingerprint and audio equipment |
| CN111309935A (en) * | 2020-03-17 | 2020-06-19 | 广州酷狗计算机科技有限公司 | Song recommendation method and device and computer storage medium |
| CN112269898A (en) * | 2020-10-30 | 2021-01-26 | 维沃移动通信有限公司 | Background music obtaining method and device, electronic equipment and readable storage medium |
| CN112788376A (en) * | 2019-11-04 | 2021-05-11 | 海信视像科技股份有限公司 | Display device and music recommendation method |
| CN112911331A (en) * | 2020-04-15 | 2021-06-04 | 腾讯科技（深圳）有限公司 | Music identification method, device and equipment for short video and storage medium |
| CN112965686A (en) * | 2021-02-23 | 2021-06-15 | 北京字跳网络技术有限公司 | Music playing method and equipment |
| CN113810762A (en) * | 2021-09-17 | 2021-12-17 | 长沙理工大学 | Monitoring method for background music infringement behavior in live video |
| CN114495916A (en) * | 2022-04-15 | 2022-05-13 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining insertion time point of background music |
| CN114845145A (en) * | 2021-01-30 | 2022-08-02 | 华为技术有限公司 | Action prompt icon sequence generation method, electronic equipment and readable storage medium |
| CN115103232A (en) * | 2022-07-07 | 2022-09-23 | 北京字跳网络技术有限公司 | Video playing method, device, equipment and storage medium |
| CN117037837A (en) * | 2023-10-09 | 2023-11-10 | 广州伏羲智能科技有限公司 | Noise separation method and device based on audio track separation technology |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093761A (en) * | 2011-11-01 | 2013-05-08 | 腾讯科技（深圳）有限公司 | Audio fingerprint retrieval method and retrieval device |
| CN103442251A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for providing video program music information |
| CN103686452A (en) * | 2013-12-06 | 2014-03-26 | 北京普瑞众合国际科技有限公司 | Addition processing method for video associated information |
| CN104113785A (en) * | 2014-06-26 | 2014-10-22 | 小米科技有限责任公司 | Information acquisition method and device |
| CN104598502A (en) * | 2014-04-22 | 2015-05-06 | 腾讯科技（北京）有限公司 | Method, device and system for obtaining background music information in played video |
| CN106375782A (en) * | 2016-08-31 | 2017-02-01 | 北京小米移动软件有限公司 | Video playing method and device |
| CN106940996A (en) * | 2017-04-24 | 2017-07-11 | 维沃移动通信有限公司 | The recognition methods of background music and mobile terminal in a kind of video |
| CN107124623A (en) * | 2017-05-12 | 2017-09-01 | 腾讯科技（深圳）有限公司 | The transmission method and device of music file information |
| US20180097838A1 (en) * | 2016-10-03 | 2018-04-05 | Telepathy Labs, Inc. | System and method for audio fingerprinting for attack detection |
| CN109509472A (en) * | 2018-12-29 | 2019-03-22 | 苏州思必驰信息科技有限公司 | Method, apparatus and system based on voice platform identification background music |
-
2019
- 2019-07-08 CN CN201910611412.1A patent/CN110335625A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093761A (en) * | 2011-11-01 | 2013-05-08 | 腾讯科技（深圳）有限公司 | Audio fingerprint retrieval method and retrieval device |
| CN103442251A (en) * | 2013-08-15 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for providing video program music information |
| CN103686452A (en) * | 2013-12-06 | 2014-03-26 | 北京普瑞众合国际科技有限公司 | Addition processing method for video associated information |
| CN104598502A (en) * | 2014-04-22 | 2015-05-06 | 腾讯科技（北京）有限公司 | Method, device and system for obtaining background music information in played video |
| CN104113785A (en) * | 2014-06-26 | 2014-10-22 | 小米科技有限责任公司 | Information acquisition method and device |
| CN106375782A (en) * | 2016-08-31 | 2017-02-01 | 北京小米移动软件有限公司 | Video playing method and device |
| US20180097838A1 (en) * | 2016-10-03 | 2018-04-05 | Telepathy Labs, Inc. | System and method for audio fingerprinting for attack detection |
| CN106940996A (en) * | 2017-04-24 | 2017-07-11 | 维沃移动通信有限公司 | The recognition methods of background music and mobile terminal in a kind of video |
| CN107124623A (en) * | 2017-05-12 | 2017-09-01 | 腾讯科技（深圳）有限公司 | The transmission method and device of music file information |
| CN109509472A (en) * | 2018-12-29 | 2019-03-22 | 苏州思必驰信息科技有限公司 | Method, apparatus and system based on voice platform identification background music |
Non-Patent Citations (5)
| Title |
|---|
| 严勤: "《语音信号处理与识别》", 30 December 2015 * |
| 张永: ""基于音频指纹的分片音乐检索算法的研究"", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 朱步裔: ""基于指纹匹配的音乐检索系统的设计与实现"", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 蒋刚 等: "《工业机器人》", 31 January 2011 * |
| 韩志艳: "《语音识别及语音可视化技术研究》", 31 January 2017 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112788376A (en) * | 2019-11-04 | 2021-05-11 | 海信视像科技股份有限公司 | Display device and music recommendation method |
| CN110958386A (en) * | 2019-11-12 | 2020-04-03 | 北京达佳互联信息技术有限公司 | Video synthesis method and device, electronic equipment and computer-readable storage medium |
| CN110992983A (en) * | 2019-11-26 | 2020-04-10 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device, terminal and storage medium for identifying audio fingerprint |
| CN110992983B (en) * | 2019-11-26 | 2023-04-18 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, device, terminal and storage medium for identifying audio fingerprint |
| CN111161758A (en) * | 2019-12-04 | 2020-05-15 | 厦门快商通科技股份有限公司 | Song listening and song recognition method and system based on audio fingerprint and audio equipment |
| CN111309935A (en) * | 2020-03-17 | 2020-06-19 | 广州酷狗计算机科技有限公司 | Song recommendation method and device and computer storage medium |
| CN111309935B (en) * | 2020-03-17 | 2024-01-30 | 广州酷狗计算机科技有限公司 | Song recommendation method and device and computer storage medium |
| CN112911331A (en) * | 2020-04-15 | 2021-06-04 | 腾讯科技（深圳）有限公司 | Music identification method, device and equipment for short video and storage medium |
| CN112911331B (en) * | 2020-04-15 | 2024-09-10 | 深圳市雅阅科技有限公司 | Music identification method, device, equipment and storage medium for short video |
| CN112269898A (en) * | 2020-10-30 | 2021-01-26 | 维沃移动通信有限公司 | Background music obtaining method and device, electronic equipment and readable storage medium |
| CN114845145B (en) * | 2021-01-30 | 2024-04-12 | 华为技术有限公司 | Action prompt icon sequence generation method, electronic device and readable storage medium |
| CN114845145A (en) * | 2021-01-30 | 2022-08-02 | 华为技术有限公司 | Action prompt icon sequence generation method, electronic equipment and readable storage medium |
| CN112965686A (en) * | 2021-02-23 | 2021-06-15 | 北京字跳网络技术有限公司 | Music playing method and equipment |
| US11941047B2 (en) | 2021-02-23 | 2024-03-26 | Beijing Zitiao Network Technology Co., Ltd. | Music playing method and device |
| CN113810762A (en) * | 2021-09-17 | 2021-12-17 | 长沙理工大学 | Monitoring method for background music infringement behavior in live video |
| CN113810762B (en) * | 2021-09-17 | 2023-10-13 | 长沙理工大学 | Monitoring method for background music infringement behavior in video live broadcast |
| CN114495916B (en) * | 2022-04-15 | 2022-07-12 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining insertion time point of background music |
| CN114495916A (en) * | 2022-04-15 | 2022-05-13 | 腾讯科技（深圳）有限公司 | Method, device, equipment and storage medium for determining insertion time point of background music |
| WO2024007833A1 (en) * | 2022-07-07 | 2024-01-11 | 北京字跳网络技术有限公司 | Video playing method and apparatus, and device and storage medium |
| CN115103232B (en) * | 2022-07-07 | 2023-12-08 | 北京字跳网络技术有限公司 | Video playing method, device, equipment and storage medium |
| CN115103232A (en) * | 2022-07-07 | 2022-09-23 | 北京字跳网络技术有限公司 | Video playing method, device, equipment and storage medium |
| CN117037837B (en) * | 2023-10-09 | 2023-12-12 | 广州伏羲智能科技有限公司 | Noise separation method and device based on audio track separation technology |
| CN117037837A (en) * | 2023-10-09 | 2023-11-10 | 广州伏羲智能科技有限公司 | Noise separation method and device based on audio track separation technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335625A (en) | The prompt and recognition methods of background music, device, equipment and medium | |
| US20060224260A1 (en) | Scan shuffle for building playlists | |
| EP2096626A1 (en) | Method for visualizing audio data | |
| US20080235018A1 (en) | Method and System for Determing the Topic of a Conversation and Locating and Presenting Related Content | |
| US8892565B2 (en) | Method and apparatus for accessing an audio file from a collection of audio files using tonal matching | |
| US10885107B2 (en) | Music recommendation method and apparatus | |
| US9576050B1 (en) | Generating a playlist based on input acoustic information | |
| US11271993B2 (en) | Streaming music categorization using rhythm, texture and pitch | |
| US20240061899A1 (en) | Conference information query method and apparatus, storage medium, terminal device, and server | |
| CN113691909B (en) | Digital audio workstation with audio processing recommendations | |
| CN107679196A (en) | A kind of multimedia recognition methods, electronic equipment and storage medium | |
| CN111142993A (en) | Information acquisition method, terminal and computer storage medium | |
| US20050160449A1 (en) | Apparatus and method for automatic dissection of segmented audio signals | |
| CN111859008A (en) | Music recommending method and terminal | |
| JP5344756B2 (en) | Information processing apparatus, information processing method, and program | |
| CN109635151A (en) | Establish the method, apparatus and computer equipment of audio retrieval index | |
| US7680654B2 (en) | Apparatus and method for segmentation of audio data into meta patterns | |
| CN113707128B (en) | Test method and system for full duplex voice interaction system | |
| US11410706B2 (en) | Content pushing method for display device, pushing device and display device | |
| JP2004145161A (en) | Speech database registration processing method, speech generation source recognizing method, speech generation section retrieving method, speech database registration processing device, speech generation source recognizing device, speech generation section retrieving device, program therefor, and recording medium for same program | |
| CN111046218A (en) | Audio acquisition method, device and system based on screen locking state | |
| Chourdakis et al. | Tagging and retrieval of room impulse responses using semantic word vectors and perceptual measures of reverberation | |
| EP4443421A1 (en) | Method for generating a sound effect | |
| JP7243447B2 (en) | VOICE ACTOR EVALUATION PROGRAM, VOICE ACTOR EVALUATION METHOD, AND VOICE ACTOR EVALUATION SYSTEM | |
| CN116456164B (en) | Teaching course input editing system and method |
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 |