CN105808780B - Song recognition method and apparatus - Google Patents
Song recognition method and apparatus Download PDFInfo
- Publication number
- CN105808780B CN105808780B CN201610194530.3A CN201610194530A CN105808780B CN 105808780 B CN105808780 B CN 105808780B CN 201610194530 A CN201610194530 A CN 201610194530A CN 105808780 B CN105808780 B CN 105808780B
- Authority
- CN
- China
- Prior art keywords
- information
- audio
- song
- target
- equipment
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/638—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of song recognition method and apparatus, belong to internet area.The described method includes: when receiving designated character, trigger song recognition instruction, after triggering the song recognition instruction, obtain target audio information, the target audio information is currently playing audio-frequency information, and the equipment of the equipment and the currently playing target audio information for receiving the song recognition instruction is the same equipment, is based on the target audio information, target song is identified by server, the target song is the corresponding song of the target audio information.Equipment in the present invention for receiving equipment and the currently playing target audio information that the song recognition instructs is the same equipment, improves the accuracy rate and efficiency for obtaining the target audio information, and then improves the accuracy rate and efficiency of identification song.
Description
Technical field
The present invention relates to internet area, in particular to a kind of song recognition method and apparatus.
Background technique
With the development of science and technology, mobile phone, the function of apparatus such as computer are more and more, which can play song etc.
Audio-frequency information.By taking the device plays song as an example, during the device plays song, user often can be to currently playing song
It is bent interested, it is desirable to get the relevant information of the song, such as song title, author, the song style, album name of the song
Therefore the information such as title need a kind of song recognition method.
In the related technology, when needing to identify song currently playing in the first equipment, user needs to manually turn on
Related application in two equipment records song currently playing in the first equipment by the application, obtains target audio
The target audio information is sent to server by information.When server receives the target audio information, according to the sound of storage
Frequency information bank identifies the target audio information, and recognition result is sent to the second equipment.
In the implementation of the present invention, the inventor finds that the existing technology has at least the following problems: firstly, user needs
The related application in the second equipment is manually turned on, and is recorded by the second equipment song currently playing to the first equipment
System, complicated for operation, process is cumbersome.Secondly, user, which opens related application, needs the regular hour, therefore, second is opened in user
When related application in equipment, the song played in the first equipment may be missed, to be difficult accurately to work as the first equipment
The song of preceding broadcasting is recorded, and the accuracy rate for recording target audio information is reduced.Finally, when the second equipment works as the first equipment
When the song of preceding broadcasting is recorded, if there are interference informations such as noises in ambient enviroment, may by interference information also into
Row is recorded, and then increases the difficulty of server identification target audio information, reduces recognition efficiency.
Summary of the invention
In order to solve problems in the prior art, the embodiment of the invention provides a kind of song recognition method and apparatus.It is described
Technical solution is as follows:
In a first aspect, providing a kind of song recognition method, which comprises
When receiving designated character, triggering song recognition instruction；
After triggering the song recognition instruction, target audio information is obtained, the target audio information is currently to broadcast
The audio-frequency information put, and the equipment of the equipment and the currently playing target audio information for receiving the song recognition instruction
For the same equipment；
Based on the target audio information, target song is identified by server, the target song is described
The corresponding song of target audio information.
Optionally, described when receiving designated character, triggering song recognition instruction, comprising:
When receiving designated character in target text input frame, the song recognition instruction, the target text are triggered
Word input frame is any text input box in the currently playing target audio information page.
Optionally, described to be based on after the target audio information identifies target song by server, also wrap
It includes:
Displaying target song information, the target song information are based on the target audio information to institute for the server
Target song is stated to be identified to obtain.
Optionally, described to be based on after the target audio information identifies target song by server, also wrap
It includes:
The specific audio frequency of installation is called to play application；
It is played and is applied by the specific audio frequency, play the target song.
Optionally, described after triggering the song recognition instruction, obtain target audio information, comprising:
If currently playing audio-frequency information be it is multiple, from currently playing multiple audio-frequency informations, obtain present bit
In the audio-frequency information that foreground plays；
The audio-frequency information that will acquire is determined as the target audio information.
Optionally, described after triggering the song recognition instruction, obtain target audio information, comprising:
If currently playing audio-frequency information be it is multiple, obtain the program mark where currently playing multiple audio-frequency informations
Know；
Show the program identification where the multiple audio-frequency information；
It is when the program identification based on display receives selection instruction, the selected audio-frequency information of the selection instruction is true
It is set to the target audio information.
Optionally, described after triggering the song recognition instruction, obtain target audio information, comprising:
Obtain currently playing audio-frequency information；
The audio-frequency information is decomposed into background music information and voiceless sound information, the voiceless sound information is the audio-frequency information
In information in addition to background music information；
An information is selected in the background music information and the voiceless sound information, the information of selection is determined as described
Target audio information.
Second aspect, provides a kind of song recognition equipment, and the equipment includes:
Receiving module, for when receiving designated character, triggering song recognition to be instructed；
Module is obtained, for obtaining target audio information, the target audio after triggering the song recognition instruction
Information is currently playing audio-frequency information, and equipment and the currently playing target sound for receiving the song recognition instruction
The equipment of frequency information is the same equipment；
Identification module identifies target song by server, the mesh for being based on the target audio information
Mark song is the corresponding song of the target audio information.
Optionally, the receiving module includes:
Trigger unit refers to for when receiving designated character in target text input frame, triggering the song recognition
It enables, the target text input frame is any text input box in the currently playing target audio information page.
Optionally, the equipment further include:
Display module, is used for displaying target song information, and the target song information is that the server is based on the mesh
Mark audio-frequency information is identified to obtain to the target song.
Optionally, the equipment further include:
Calling module, for calling the specific audio frequency of installation to play application；
Playing module is applied for being played by the specific audio frequency, plays the target song.
Optionally, the acquisition module includes:
First acquisition unit, if for currently playing audio-frequency information be it is multiple, from currently playing multiple audios
In information, the audio-frequency information for being currently located at foreground broadcasting is obtained；
First determination unit, the audio-frequency information for will acquire are determined as the target audio information.
Optionally, the acquisition module includes:
Second acquisition unit, if for currently playing audio-frequency information be it is multiple, obtain currently playing multiple sounds
Program identification where frequency information；
Display unit, for showing the program identification where the multiple audio-frequency information；
Second determination unit, for when the program identification based on display receives selection instruction, by the selection instruction
Selected audio-frequency information is determined as the target audio information.
Optionally, the acquisition module includes:
Third acquiring unit, for obtaining currently playing audio-frequency information；
Decomposition unit, for the audio-frequency information to be decomposed into background music information and voiceless sound information, the voiceless sound information
For the information in the audio-frequency information in addition to background music information；
Third determination unit will be selected for selecting an information in the background music information and the voiceless sound information
The information selected is determined as the target audio information.
Technical solution provided in an embodiment of the present invention has the benefit that in embodiments of the present invention, when the equipment
When receiving designated character, triggering song recognition instruction, i.e. user can be by inputting designated character, touch the equipment quickly
Song recognition instruction is sent out, the speed for responding song recognition instruction is improved, after triggering song recognition instruction, this is set
It is standby to obtain target audio information, due to the equipment and the currently playing target audio information for receiving song recognition instruction
Equipment is the same equipment, therefore, there is no need to obtain the target audio information by other equipment, improves and obtains the target
The accuracy rate and efficiency of audio-frequency information, and then improve the accuracy rate and efficiency of identification song.Obtaining the target audio information
Later, it is based on the target audio information, target song is identified by server, further improves and identifies target song
Bent efficiency.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of song recognition method flow diagram provided in an embodiment of the present invention；
Fig. 2 is another song recognition method flow diagram provided in an embodiment of the present invention；
Fig. 3 is a kind of page schematic diagram for playing audio-frequency information provided in an embodiment of the present invention；
Fig. 4 is another page schematic diagram for playing audio-frequency information provided in an embodiment of the present invention；
Fig. 5 is a kind of song recognition device structure schematic diagram provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Before carrying out detailed explanation to the embodiment of the present invention, first the application scenarios of the embodiment of the present invention are given
It introduces.When user plays song using mobile phone, apparatus such as computer, user often can be interested in currently playing song, it is desirable to
Get the relevant information of the song.In the related technology, when needing to identify song currently playing in the first equipment, Yong Huxu
The related application in the second equipment is manually turned on, song currently playing in the first equipment is recorded by the application
System, obtains target audio information, the target audio information is then sent to server, is believed by server according to the audio of storage
Breath library identifies the target audio information.But user needs to manually turn on the related application in the second equipment, and passes through
The second equipment song currently playing to the first equipment is recorded, and not only complicated for operation, process is cumbersome, it is also difficult to accurately record
The currently playing song of the first equipment is made, and during the first equipment of recording currently playing song, it is easy to will do
It disturbs information also to be recorded, and then causes to identify that the accuracy rate of target audio information is very low.Therefore, the embodiment of the present invention provides
A kind of song recognition method can be improved the accuracy rate of identification target audio information.
Fig. 1 is a kind of song recognition method flow diagram provided in an embodiment of the present invention, referring to Fig. 1, the interaction master of this method
Body be equipment and server, this method comprises:
Step 101: when receiving designated character, triggering song recognition instruction.
Step 102: after triggering song recognition instruction, obtaining target audio information, which is to work as
The audio-frequency information of preceding broadcasting, and the equipment of the equipment and the currently playing target audio information for receiving song recognition instruction
For the same equipment.
Step 102: being based on the target audio information, target song is identified by server, which is
The corresponding song of target audio information.
In embodiments of the present invention, when the equipment receives designated character, triggering song recognition instruction, i.e. user can be with
By inputting designated character, to make the equipment quickly trigger song recognition instruction, improves and respond song recognition instruction
Speed, after triggering song recognition instruction, which obtains target audio information, due to referring to for receiving the song recognition
The equipment of the equipment of order and the currently playing target audio information be the same equipment, therefore, there is no need to by other equipment come
The target audio information is obtained, improves the accuracy rate and efficiency for obtaining the target audio information, and then improve identification song
Accuracy rate and efficiency.After obtaining the target audio information, it is based on the target audio information, target is sung by server
Qu Jinhang identification, further improves the efficiency for identifying the target song.
Optionally, when receiving designated character, triggering song recognition instruction, comprising:
When receiving designated character in target text input frame, song recognition instruction is triggered, the target text is defeated
Entering frame is any text input box in the currently playing target audio information page.
Optionally, after being identified based on the target audio information to target song by server, further includes:
Displaying target song information, the target song information are that the server is based on the target audio information to target song
Qu Jinhang identifies to obtain.
Optionally, after being identified based on the target audio information to target song by server, further includes:
The specific audio frequency of installation is called to play application；
It is played and is applied by the specific audio frequency, play the target song.
Optionally, after triggering song recognition instruction, target audio information is obtained, comprising:
If currently playing audio-frequency information be it is multiple, from currently playing multiple audio-frequency informations, obtain present bit
In the audio-frequency information that foreground plays；
The audio-frequency information that will acquire is determined as the target audio information.
Optionally, after triggering song recognition instruction, target audio information is obtained, comprising:
If currently playing audio-frequency information be it is multiple, obtain the program mark where currently playing multiple audio-frequency informations
Know；
Show the program identification where multiple audio-frequency information；
When the program identification based on display receives selection instruction, the selected audio-frequency information of the selection instruction is determined
For the target audio information.
Optionally, after triggering song recognition instruction, target audio information is obtained, comprising:
Obtain currently playing audio-frequency information；
The audio-frequency information is decomposed into background music information and voiceless sound information, which is in the audio-frequency information except back
Information other than scape music information；
An information is selected in the background music information and the voiceless sound information, and the information of selection is determined as the target sound
Frequency information.
All the above alternatives, can form alternative embodiment of the invention according to any combination, and the present invention is real
It applies example and this is no longer repeated one by one.
Fig. 2 is a kind of song recognition method flow diagram provided in an embodiment of the present invention, referring to fig. 2, the interaction master of this method
Body be equipment and server, this method comprises:
Step 201: when the equipment receives designated character, triggering song recognition instruction.
Since when user plays song using mobile phone, apparatus such as computer, user often can be emerging to currently playing song sense
Interest, it is desirable to get the relevant information of the song, therefore, which can trigger the song when receiving the instruction character
Identification instruction, and then the song currently playing to the equipment identifies.
Wherein, which can be the equipment that mobile phone, computer etc. can play the audio-frequency informations such as song, which can
To be to play MP3 (Moving Picture Experts Group Audio Layer III, dynamic image expert's compression standard
Audio level 3), the audio file of formats such as WMA (Windows Media Audio) when audio-frequency information, be also possible to play
AVI (Audio Video Interleaved, Audio Video Interleaved format), MP4 (Moving Picture Experts
Group Audio Layer IV, dynamic image expert's compression standard audio level 4) etc. the video file of formats when audio letter
Breath, certainly, in practical applications, which can also be audio-frequency information when the other types of file of the device plays,
For example, station broadcast etc., the embodiment of the present invention is not specifically limited in this embodiment.
It should be noted that the designated character can be a character, it is also possible to a character string, for example, when this refers to
When to determine character be a character, which can be " s ", " f " etc.；When the designated character is a character string, the character string
It can be "@shibie ", " ctrl "+" alt "+" s " etc., the present invention is not especially limit this.
It should also be noted that, the designated character can also be based on specified operation input for the equipment, and do not broadcast currently
It puts in the audio-frequency information page and is shown, for example, the specified operation can be first by " enter " when the equipment is computer
Then key inputs the designated character, at this point, the equipment can receive the designated character and trigger song recognition instruction, and work as
The designated character will not be shown in preceding broadcasting audio-frequency information page.Certainly, in practical applications, which can also be
The operation of other way, the embodiment of the present invention are not specifically limited in this embodiment.
In addition, song recognition instruction other than it can trigger through the above way, can also be executed default behaviour by user
It triggers, which can be the operation such as clicking operation, slide, and the embodiment of the present invention is not specifically limited in this embodiment.
It should be noted that it is default that the speed that user inputs designated character will be faster than user's execution due under normal conditions
Therefore the speed of operation when i.e. triggering song recognition instructs when the equipment receives designated character, can be improved response identification
The speed of song instruction.
Further, if user is triggered the song recognition by input designated character and instructed, when the equipment is in target
When receiving designated character in text input box, song recognition instruction is triggered, which is currently playing be somebody's turn to do
Any text input box in target audio information page.
It wherein, usually can also include one or more text input box since the equipment is when playing audio-frequency information,
For example, text input box can be used for searching for audio file when the audio-frequency information of the device plays audio file；When the equipment
When the audio-frequency information of playing video file, text input box can be used for inputting barrage.Therefore, user can be somebody's turn to do currently playing
In multiple text input boxes in the audio-frequency information page, selection target input frame, and designated character is inputted, and then when the equipment exists
When receiving the designated character in target text input frame, triggering song recognition instruction.
For example, as shown in figure 3, further including a use in the page of currently playing film when the device plays film
In the text input box of input barrage, user can input " shibie " in the text input box, and then the equipment can be
When receiving " shibie " in the text input box, triggering song recognition instruction.
Step 202: after triggering song recognition instruction, which obtains target audio information, and the target is believed
Breath is sent to server, which is currently playing audio-frequency information, and for receiving song recognition instruction
The equipment of equipment and the currently playing target audio information is the same equipment.
Since the audio-frequency information of different songs is also different, it can be different to identify by different audio-frequency informations
Song, so, after triggering song recognition instruction, which can be determined as target sound for currently playing audio-frequency information
Frequency information.In addition, due to the limited storage space of equipment local, the audio-frequency information that may store is also limited, therefore, in order to mention
The target audio information can be sent to service when obtaining the target audio information by the efficiency of height identification song, the equipment
Device, and then the target is identified by the server.
Wherein, when the device plays audio-frequency information, the audio that is typically sent to the audio-frequency information in the equipment
Output module, and then the audio-frequency information is played by the audio output module, therefore, when the equipment needs to obtain target audio letter
When breath, the audio-frequency information can be determined as the mesh in the audio output module audio-frequency information being sent in the equipment
Mark audio-frequency information.Due in embodiments of the present invention, for receiving the equipment and the currently playing target of song recognition instruction
The equipment of audio-frequency information can be the same equipment, do not need to play the audio-frequency information in the audio output module and then lead to
It crosses other equipment and records the audio-frequency information, therefore, user does not need to obtain the target audio information manually, and obtains the target
When audio-frequency information the accuracy rate for obtaining the target audio information will not be improved by the interference of the interference informations such as ambient noise
And efficiency, and then improve the accuracy rate and efficiency of identification song.
Further, due to the equipment may currently playing multiple audio-frequency informations, for example, playing film and song simultaneously
Song therefore, can be in multiple sound when the currently playing multiple audio-frequency informations of the equipment and when needing to obtain the target audio information
An audio-frequency information is selected in frequency information, and then the audio-frequency information of selection is determined as the target audio information, specifically can wrap
Include following two ways.
First way, if currently playing audio-frequency information be it is multiple, from currently playing multiple audio-frequency informations,
The audio-frequency information for being currently located at foreground broadcasting is obtained, the audio-frequency information that will acquire is determined as the target audio information.
Wherein, when the equipment plays multiple audio-frequency informations simultaneously, being currently located at the audio-frequency information of foreground broadcasting, have very much can
It can be that user wishes the target audio information obtained, for example, the audio for being currently located at foreground broadcasting may be that the user currently sees
The audio-frequency information in film seen, therefore, the available audio-frequency information for being currently located at foreground broadcasting of the equipment, the sound that will acquire
Frequency information is determined as the target audio information.
It should be noted that the audio-frequency information that the foreground plays, which refers to, works as when the equipment can show multiple pages simultaneously
When multiple page is arranged with overlapped way, the audio-frequency information currently playing positioned at the page of the top of multiple page；When
When the equipment is only able to display a page simultaneously, the audio-frequency information which plays refers to be played in the page that the equipment is currently shown
Audio-frequency information.
For example, being shown when the equipment can show multiple pages simultaneously as shown in figure 4, the equipment is laminated simultaneously
" " news hookup " ", " " Harry Potter " " and " " the Sound of Music " " three pages, and " " news hookup " " page is located at this three
Page top, therefore, the currently playing audio 1 of available " " the news hookup " " page of the equipment, and the sound that will be will acquire
Frequently 1 is determined as the target audio information.
The second way, if currently playing audio-frequency information be it is multiple, obtain currently playing multiple audio-frequency informations
The program identification at place shows the program identification where multiple audio-frequency information, when the program identification based on display receives choosing
When selecting instruction, the selected audio-frequency information of the selection instruction is determined as the target audio information.
Wherein, each in multiple audio-frequency information since currently playing multiple audio-frequency informations play simultaneously
A audio-frequency information all may be that user wishes the target audio information obtained, therefore, obtain the target audio information to improve
Accuracy rate, the program identification where the available currently playing multiple audio-frequency informations of the equipment shows multiple audio letter
Program identification where ceasing, and when receiving selection instruction, the selected audio-frequency information of the selection instruction is determined as the mesh
Mark audio-frequency information.
For example, when the equipment obtain the program identification where currently playing multiple audio-frequency informations be " " news hookup " ",
When " " Harry Potter " " and " " the Sound of Music " ", show the program identification where multiple audio-frequency information be " " news hookup " ",
" " Harry Potter " " and " " the Sound of Music " ", when receiving selection instruction 1, program identification which selects for
" " news hookup " " corresponding audio-frequency information " audio 1 " is determined as the target audio and believed by " " news hookup " ", therefore, the equipment
Breath.
It should be noted that the various ways such as the equipment can be shown by window, pop-up is shown show multiple audio
Program identification where information, the embodiment of the present invention are not specifically limited in this embodiment.
It should also be noted that, the program identification can be the Page Name for playing the audio-frequency information page, it is also possible to broadcast
The page properties of playback frequency information page, certainly, in practical applications, which can also be other and can identify respectively
The mark of multiple audio-frequency information, the embodiment of the present invention are not specifically limited in this embodiment.
Wherein, which can be the corresponding programm name of currently playing audio-frequency information, such as song title, electricity
Shadow title etc.；The page properties can be the Apply Names of currently playing audio-frequency information, for example, music player, video playing
Device etc..Certainly, in practical applications, the Page Name and page properties can also have other meanings, and the embodiment of the present invention is to this
It is not specifically limited.
For example, as shown in figure 4, the equipment plays three audio-frequency informations simultaneously, wherein the page properties of the page 1 are network
Radio station, Page Name are " news hookup ", and the audio-frequency information of broadcasting is audio 1；The page properties of the page 2 are video player,
Page Name is " Harry Potter ", and the audio-frequency information of broadcasting is audio 2；The page properties of the page 3 are music player, page name
Referred to as " the Sound of Music ", the audio-frequency information of broadcasting are audio 3.When the program identification is the Page Name for playing the audio-frequency information page
When, the program identification where which obtains currently playing multiple audio-frequency informations is " " news hookup " ", " " Harry Potter " "
" " the Sound of Music " "；When the program identification is to play the page properties of the audio-frequency information page, which obtains currently playing
Multiple audio-frequency informations where program identification be " network radio station ", " video player " and " music player ".
In addition, in practical applications, which can also select one in multiple audio-frequency information otherwise
Audio-frequency information, and then the audio-frequency information of selection is determined as the target audio information, the embodiment of the present invention does not do specific limit to this
It is fixed.
Further, in the second way, which not only can be directly by the selected audio-frequency information of selection instruction
It is determined as the target audio information, it is of course also possible to which the selected audio-frequency information of the selection instruction is decomposed, obtains background
Music information and information of singing opera arias, and then an information is selected from background music information and voiceless sound information, the information of selection is true
It is set to the target audio information, the embodiment of the present invention is not specifically limited in this embodiment.
Further, when the equipment obtains target audio information, which can not only be obtained by the above method
It takes, can also be obtained in the following way, specifically: currently playing audio-frequency information is obtained, which is decomposed
For background music information and voiceless sound information, which is the information in the audio-frequency information in addition to background music information, In
An information is selected in the background music information and the voiceless sound information, and the information of selection is determined as the target audio information.
Wherein, since the audio-frequency information in song generally comprises two parts, a part is the instrument playings such as piano, flute
Background music information, another part is the voiceless sound information that singer sings, and the user may be only interested in background music, obtains
Take sung by other singers and background music information be the background music song；Or the voiceless sound that only singer is sung
Information is interested, obtains the song of singer performance, therefore, in order to further increase the accuracy rate and effect of identification song
Rate, the available currently playing audio-frequency information of the equipment, is decomposed into background music information and voiceless sound information for the audio-frequency information,
An information is selected in the background music information and the voiceless sound information, and the information of selection is determined as the target audio information,
And then only background music information or voiceless sound information are identified.
It should be noted that background music information and voiceless sound information respectively correspond different tracks in song, therefore,
When the audio-frequency information is decomposed into background music information and voiceless sound information, background music can be determined by different tracks
The audio-frequency information in practical applications, is decomposed into background music information and voiceless sound information may be used also by information and voiceless sound information certainly
To refer to the prior art, the embodiment of the present invention no longer repeats one by one.
Step 203: the server is based on the target audio information, identifies to target song, will when identifying successfully
Target song information is sent to the equipment, which is the corresponding song of target audio information.
It specifically, can be according to the audio of storage when the server receives the target audio information of equipment transmission
Information bank identifies the target audio information, and then identifies to the target song.When identifying successfully, by target
Song information is sent to the equipment.
Wherein, it when the server is according to the audio-frequency information library of storage, when being identified to the target audio information, can incite somebody to action
The audio-frequency information stored in the target audio information and the audio-frequency information library is matched, when in the audio-frequency information library exist and this
When the audio-frequency information of target audio information matches, determination is identified successfully.
It should be noted that the audio-frequency information stored in the target audio information and the audio-frequency information library is carried out matched
Method, can refer to the prior art, and the embodiment of the present invention no longer repeats one by one.
It wherein, may include audio-frequency information song information corresponding with the audio-frequency information, the service in the audio-frequency information library
Device can be based on the target audio information, before identifying to the target song, audio-frequency information is corresponding with the audio
Song information is stored in the audio-frequency information library, as described in Table 1.
Table 1
It should be noted that the embodiment of the present invention only carries out for audio-frequency information and song information shown in the above-mentioned table 1
Illustrate, above-mentioned table 1 does not constitute the embodiment of the present invention and limits.
It should also be noted that, the song information may include song title, singer, album name, title, age, wind
The information such as lattice, chained address, certainly in practical applications, the song information can also include other information, the embodiment of the present invention
It is not specifically limited in this embodiment.
In addition, when, there is no when the audio-frequency information with the target audio information matches, determining identification in the audio-frequency information library
Failure sends recognition failures prompt information to the equipment, and the failure prompt information is for prompting the ownership goal song recognition to lose
It loses.
Wherein, since the audio-frequency information that the server can store also is limited, it may in the audio-frequency information library
And the target audio information is not present, so, when the target audio information is not present in the audio-frequency information library, determine that identification is lost
It loses, and sends recognition failures prompt information to the equipment.
For example, working as the target audio information that the server receives for audio 1, in the audio-frequency information library of server storage
There are the audios 1, and therefore, server determination identifies successfully, and the corresponding song information 1 of audio 1 is sent to the equipment.
When the target audio information that the server receives be audio 4, the server storage audio-frequency information library in be not present the audio
4, therefore, which determines recognition failures, and sends recognition failures prompt information to the equipment.
Step 204: when the equipment receives the target song information of server transmission, displaying target song information should
Target song information is that the server is identified to obtain based on the target audio information to the target song.
When the equipment receives the target song information, the target song information can be shown, and then user can root
According to the target song information, information related with the target song is quickly understood.
It should be noted that the various ways such as the equipment can be shown by window, pop-up is shown show the target song
Information, the embodiment of the present invention are not specifically limited in this embodiment.
In addition, from the foregoing it will be appreciated that including the information such as song title, chained address in the target song information, therefore, when this
When equipment receives the target song information, the specific audio frequency of installation according to the target song information, can be called to play application,
It is played and is applied by the specific audio frequency, play the target song.
Wherein, when the equipment receives the target song information, and plays the target song, user knows intuitively root
According to the target song of broadcasting, determine whether the song that the equipment is identified is correct song, to further increase identification song
Accuracy rate.
It should be noted that can be sung according to the target when playing the application plays target song by the specific audio frequency
The chained address for including in bent information obtains the corresponding Internet resources of the target song, and then corresponding according to the target song
Internet resources play the target song；Alternatively, playing the song service of application from the specific audio frequency according to the target song information
In device, obtains and play the target song.Certainly, in practical applications, which broadcasts by specific audio frequency broadcasting application
When putting the target song, the target song can also be played according to other information, the embodiment of the present invention is not specifically limited in this embodiment.
Further, from the foregoing it will be appreciated that when the server determines recognition failures, recognition failures can be sent to the equipment and mentioned
Show information, therefore, when the equipment receives the recognition failures prompt information, can also show the recognition failures prompt information.
It should be noted that the various ways such as the equipment can be shown by window, pop-up is shown show the recognition failures
When prompt information, the embodiment of the present invention is not specifically limited in this embodiment.
In embodiments of the present invention, user can be defeated in any text input box in the currently playing audio-frequency information page
Enter designated character, and then when the equipment receives designated character, can quickly trigger song recognition instruction, improves response and know
The speed of other song instruction.In addition, the equipment obtains target audio information, and should after triggering song recognition instruction
Target information is sent to server, since the target audio information is currently playing audio-frequency information, receives the song recognition and refers to
The equipment of order and the equipment of the currently playing audio-frequency information are the same equipment, and the target audio information that obtains of the equipment be
It is acquired when by audio output module that the audio-frequency information is sent in the equipment, rather than by recording the audio output mould
The audio-frequency information that block plays acquires, and this improves the accuracys rate and efficiency that obtain the target audio information, and then improves
The accuracy rate and efficiency of identification song.Furthermore when server is according to the target audio information, successfully identify the target song it
Afterwards, which can be with displaying target song information, or plays target song, it is ensured that user can rapidly get target song
Bent information, or intuitively according to the target song of broadcasting, determine whether the song that the equipment is identified is correct song, with
Further increase the accuracy rate of identification song.
Fig. 5 is a kind of song recognition equipment provided in an embodiment of the present invention, and referring to Fig. 5, which includes: receiving module
501, module 502 and identification module 503 are obtained.
Receiving module 501, for when receiving designated character, triggering song recognition to be instructed.
Module 502 is obtained, for obtaining target audio information, the target audio after triggering song recognition instruction
Information is currently playing audio-frequency information, and equipment and currently playing target audio letter for receiving song recognition instruction
The equipment of breath is the same equipment.
Identification module 503 identifies target song by server, the mesh for being based on the target audio information
Mark song is the corresponding song of target audio information.
Optionally, which includes:
Trigger unit, for when receiving designated character in target text input frame, triggering song recognition instruction,
The target text input frame is any text input box in the currently playing target audio information page.
Optionally, the equipment further include:
Display module, is used for displaying target song information, which is that the server is based on the target audio
Information is identified to obtain to the target song.
Optionally, the equipment further include:
Calling module, for calling the specific audio frequency of installation to play application；
Playing module plays the target song for playing application by the specific audio frequency.
Optionally, which includes:
First acquisition unit, if for currently playing audio-frequency information be it is multiple, from currently playing multiple audios
In information, the audio-frequency information for being currently located at foreground broadcasting is obtained；
First determination unit, the audio-frequency information for will acquire are determined as the target audio information.
Optionally, which includes:
Second acquisition unit, if for currently playing audio-frequency information be it is multiple, obtain currently playing multiple sounds
Program identification where frequency information；
Display unit, for showing the program identification where multiple audio-frequency information；
Second determination unit, for when the program identification based on display receives selection instruction, by the selection instruction institute
The audio-frequency information of selection is determined as the target audio information.
Optionally, which includes:
Third acquiring unit, for obtaining currently playing audio-frequency information；
Decomposition unit, for the audio-frequency information to be decomposed into background music information and voiceless sound information, which is should
Information in audio-frequency information in addition to background music information；
Third determination unit, for selecting an information in the background music information and the voiceless sound information, by selection
Information is determined as the target audio information.
In conclusion in embodiments of the present invention, when the equipment receives designated character, triggering song recognition instruction,
I.e. user, to make the equipment quickly trigger song recognition instruction, can improve by inputting designated character and respond the song
The speed for identifying instruction, after triggering song recognition instruction, which obtains target audio information, due to for receiving this
The equipment of song recognition instruction and the equipment of the currently playing target audio information are the same equipment, therefore, there is no need to pass through
Other equipment obtain the target audio information, improve the accuracy rate and efficiency for obtaining the target audio information, and then improve
The accuracy rate and efficiency of identification song.After obtaining the target audio information, it is based on the target audio information, passes through service
Device identifies target song, further improves the efficiency for identifying the target song.
About the equipment in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of song recognition method, which is characterized in that the described method includes:
When receiving designated character, triggering song recognition instruction；
After triggering the song recognition instruction, target audio information is obtained, the target audio information is currently playing
Audio-frequency information, and the equipment of the equipment and the currently playing target audio information for receiving the song recognition instruction is same
One equipment；
Based on the target audio information, target song is identified by server, the target song is the target
The corresponding song of audio-frequency information；
Wherein, described when receiving designated character, triggering song recognition instruction, comprising:
When receiving the designated character in target text input frame, the song recognition instruction, the target text are triggered
Word input frame is any text input box in the currently playing target audio information page；
Wherein, described after triggering the song recognition instruction, obtain target audio information, comprising:
Obtain the currently playing audio-frequency information；
The audio-frequency information is decomposed into background music information and voiceless sound information, the voiceless sound information is to remove in the audio-frequency information
Information other than the background music information；
An information is selected in the background music information and the voiceless sound information, and the information of selection is determined as the target
Audio-frequency information.
2. the method as described in claim 1, which is characterized in that described to be based on the target audio information to mesh by server
After mark song is identified, further includes:
Displaying target song information, the target song information are that the server is based on the target audio information to the mesh
Mark song is identified to obtain.
3. the method as described in claim 1, which is characterized in that described to be based on the target audio information to mesh by server
After mark song is identified, further includes:
The specific audio frequency of installation is called to play application；
It is played and is applied by the specific audio frequency, play the target song.
4. the method as described in claim 1, which is characterized in that it is described after triggering the song recognition instruction, obtain mesh
Mark audio-frequency information, comprising:
If the currently playing audio-frequency information be it is multiple, from currently playing multiple audio-frequency informations, obtain present bit
In the audio-frequency information that foreground plays；
The audio-frequency information that will acquire is determined as the target audio information.
5. the method as described in claim 1, which is characterized in that it is described after triggering the song recognition instruction, obtain mesh
Mark audio-frequency information, comprising:
If the currently playing audio-frequency information be it is multiple, obtain the program mark where currently playing multiple audio-frequency informations
Know；
Show the program identification where the multiple audio-frequency information；
When the program identification based on display receives selection instruction, the selected audio-frequency information of the selection instruction is determined as
The target audio information.
6. a kind of song recognition equipment, which is characterized in that the equipment includes:
Receiving module, for when receiving designated character, triggering song recognition to be instructed；
Module is obtained, for obtaining target audio information, the target audio information after triggering the song recognition instruction
Equipment and the currently playing target audio letter for currently playing audio-frequency information, and for receiving the song recognition instruction
The equipment of breath is the same equipment；
Identification module identifies target song by server, the target song for being based on the target audio information
Song is the corresponding song of the target audio information；
Wherein, the receiving module includes:
Trigger unit refers to for when receiving the designated character in target text input frame, triggering the song recognition
It enables, the target text input frame is any text input box in the currently playing target audio information page；
The acquisition module includes:
Third acquiring unit, for obtaining the currently playing audio-frequency information；
Decomposition unit, for the audio-frequency information to be decomposed into background music information and voiceless sound information, the voiceless sound information is institute
State the information in audio-frequency information in addition to the background music information；
Third determination unit, for selecting an information in the background music information and the voiceless sound information, by selection
Information is determined as the target audio information.
7. equipment as claimed in claim 6, which is characterized in that the equipment further include:
Display module, is used for displaying target song information, and the target song information is that the server is based on the target sound
Frequency information is identified to obtain to the target song.
8. equipment as claimed in claim 6, which is characterized in that the equipment further include:
Calling module, for calling the specific audio frequency of installation to play application；
Playing module is applied for being played by the specific audio frequency, plays the target song.
9. equipment as claimed in claim 6, which is characterized in that the acquisition module includes:
First acquisition unit, if for the currently playing audio-frequency information be it is multiple, from currently playing multiple audios
In information, the audio-frequency information for being currently located at foreground broadcasting is obtained；
First determination unit, the audio-frequency information for will acquire are determined as the target audio information.
10. equipment as claimed in claim 6, which is characterized in that the acquisition module includes:
Second acquisition unit, if for the currently playing audio-frequency information be it is multiple, obtain currently playing multiple sounds
Program identification where frequency information；
Display unit, for showing the program identification where the multiple audio-frequency information；
Second determination unit will be selected by the selection instruction for when the program identification based on display receives selection instruction
The audio-frequency information selected is determined as the target audio information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610194530.3A CN105808780B (en) | 2016-03-31 | 2016-03-31 | Song recognition method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610194530.3A CN105808780B (en) | 2016-03-31 | 2016-03-31 | Song recognition method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105808780A CN105808780A (en) | 2016-07-27 |
| CN105808780B true CN105808780B (en) | 2019-11-22 |
Family
ID=56460541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610194530.3A Active CN105808780B (en) | 2016-03-31 | 2016-03-31 | Song recognition method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105808780B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106599274A (en) * | 2016-12-23 | 2017-04-26 | 珠海市魅族科技有限公司 | Played sound source identification apparatus and method |
| CN107040587A (en) * | 2017-03-02 | 2017-08-11 | 广州小鹏汽车科技有限公司 | A kind of vehicle radio station music content acquisition methods and device |
| CN108334272B (en) * | 2018-01-23 | 2020-08-21 | 维沃移动通信有限公司 | Control method and mobile terminal |
| CN108509620A (en) * | 2018-04-04 | 2018-09-07 | 广州酷狗计算机科技有限公司 | Song recognition method and device, storage medium |
| CN109947979B (en) * | 2018-08-22 | 2021-09-21 | Oppo广东移动通信有限公司 | Song identification method, device, terminal and storage medium |
| CN113517010A (en) * | 2021-08-03 | 2021-10-19 | 广州酷狗计算机科技有限公司 | Calling method and device of music playing function, electronic equipment and storage medium |
| CN114666653B (en) * | 2022-03-23 | 2024-07-19 | 腾讯音乐娱乐科技（深圳）有限公司 | Subtitle display method and equipment for music fragments and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110068749A (en) * | 2009-12-14 | 2011-06-22 | 한국과학기술연구원 | Apparatus and method for searching similar music artist and music/music artist recommendation service system |
| CN103685520A (en) * | 2013-12-13 | 2014-03-26 | 深圳Tcl新技术有限公司 | Method and device for pushing songs on basis of voice recognition |
| 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 |
-
2016
- 2016-03-31 CN CN201610194530.3A patent/CN105808780B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105808780A (en) | 2016-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105808780B (en) | Song recognition method and apparatus | |
| KR101397433B1 (en) | Method and apparatus for configuring equalizer of media file player | |
| CN102959544B (en) | For the method and system of synchronized multimedia | |
| US20090307594A1 (en) | Adaptive User Interface | |
| EP1855216A2 (en) | System, device, method, and program for segmenting radio broadcast audio data | |
| US20050147256A1 (en) | Automated presentation of entertainment content in response to received ambient audio | |
| CN1636240A (en) | System for selling a product utilizing audio content identification | |
| US20080154962A1 (en) | Apparatus and method for automatically composing album and managing cover image of album | |
| KR20080024137A (en) | Playlist structure for large playlists | |
| CN110324718A (en) | Audio-video generation method, device, electronic equipment and readable medium | |
| WO2023040520A1 (en) | Method and apparatus for performing music matching of video, and computer device and storage medium | |
| WO2022160603A1 (en) | Song recommendation method and apparatus, electronic device, and storage medium | |
| JP2007012013A (en) | Video data management device and method, and program | |
| EP1403852B1 (en) | Voice activated music playback system | |
| CN111046226A (en) | Music tuning method and device | |
| JP2000207415A (en) | Information providing method, information recording medium, information management method and recording and reproducing device | |
| CN113781989A (en) | Audio animation playing and rhythm stuck point identification method and related device | |
| JP2000298978A (en) | Playing music related information display device, display processing method for playing music related information, and recording medium for playing music related information display program | |
| JP2004152174A (en) | Content reproducing device, content providing system, content retrieving method, and program | |
| KR101551968B1 (en) | Music source information provide method by media of vehicle | |
| CN103680561A (en) | System and method for synchronizing human voice signal and text description data of human voice signal | |
| CN111046218A (en) | Audio acquisition method, device and system based on screen locking state | |
| JP7166373B2 (en) | METHOD, SYSTEM, AND COMPUTER-READABLE RECORDING MEDIUM FOR MANAGING TEXT TRANSFORMATION RECORD AND MEMO TO VOICE FILE | |
| KR20180034718A (en) | Method of providing music based on mindmap and server performing the same | |
| EP4443421A1 (en) | Method for generating a sound effect |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 510660 Guangzhou City, Guangzhou, Guangdong, Whampoa Avenue, No. 315, self - made 1-17 Applicant after: Guangzhou KuGou Networks Co., Ltd. Address before: 510000 B1, building, No. 16, rhyme Road, Guangzhou, Guangdong, China 13F Applicant before: Guangzhou KuGou Networks Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |