WO2018045988A1 - 歌曲的数字乐谱文件的生成方法、装置和存储介质 - Google Patents

歌曲的数字乐谱文件的生成方法、装置和存储介质 Download PDF

Info

Publication number
WO2018045988A1
WO2018045988A1 PCT/CN2017/101008 CN2017101008W WO2018045988A1 WO 2018045988 A1 WO2018045988 A1 WO 2018045988A1 CN 2017101008 W CN2017101008 W CN 2017101008W WO 2018045988 A1 WO2018045988 A1 WO 2018045988A1
Authority
WO
WIPO (PCT)
Prior art keywords
triplet
audio
file
note
valid
Prior art date
Application number
PCT/CN2017/101008
Other languages
English (en)
French (fr)
Inventor
赵伟锋
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Publication of WO2018045988A1 publication Critical patent/WO2018045988A1/zh
Priority to US16/059,109 priority Critical patent/US10923089B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00—Details of electrophonic musical instruments
    • G10H1/0008—Associated control or indicating means
    • G10H1/0025—Automatic or semi-automatic music composition, e.g. producing random music, applying rules from music theory or modifying a musical piece
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10G—REPRESENTATION OF MUSIC; RECORDING MUSIC IN NOTATION FORM; ACCESSORIES FOR MUSIC OR MUSICAL INSTRUMENTS NOT OTHERWISE PROVIDED FOR, e.g. SUPPORTS
    • G10G3/00—Recording music in notation form, e.g. recording the mechanical operation of a musical instrument
    • G10G3/04—Recording music in notation form, e.g. recording the mechanical operation of a musical instrument using electrical means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/432—Query formulation
    • G06F16/433—Query formulation using audio data
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H1/00—Details of electrophonic musical instruments
    • G10H1/36—Accompaniment arrangements
    • G10H1/361—Recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H3/00—Instruments in which the tones are generated by electromechanical means
    • G10H3/12—Instruments in which the tones are generated by electromechanical means using mechanical resonant generators, e.g. strings or percussive instruments, the tones of which are picked up by electromechanical transducers, the electrical signals being further manipulated or amplified and subsequently converted to sound by a loudspeaker or equivalent instrument
    • G10H3/125—Extracting or recognising the pitch or fundamental frequency of the picked up signal
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/061—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction of musical phrases, isolation of musically relevant segments, e.g. musical thumbnail generation, or for temporal structure analysis of a musical piece, e.g. determination of the movement sequence of a musical work
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/066—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for pitch analysis as part of wider processing for musical purposes, e.g. transcription, musical performance evaluation; Pitch recognition, e.g. in polyphonic sounds; Estimation or use of missing fundamental
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/071—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for rhythm pattern analysis or rhythm style recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
    • G10H2210/031—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/086—Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for transcription of raw audio or music data to a displayed or printed staff representation or to displayable MIDI-like note-oriented data, e.g. in pianoroll format
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2220/00—Input/output interfacing specifically adapted for electrophonic musical tools or instruments
    • G10H2220/005—Non-interactive screen display of musical or status data
    • G10H2220/011—Lyrics displays, e.g. for karaoke applications
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2220/00—Input/output interfacing specifically adapted for electrophonic musical tools or instruments
    • G10H2220/005—Non-interactive screen display of musical or status data
    • G10H2220/015—Musical staff, tablature or score displays, e.g. for score reading during a performance.
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2220/00—Input/output interfacing specifically adapted for electrophonic musical tools or instruments
    • G10H2220/155—User input interfaces for electrophonic musical instruments
    • G10H2220/441—Image sensing, i.e. capturing images or optical patterns for musical purposes or musical control purposes
    • G10H2220/451—Scanner input, e.g. scanning a paper document such as a musical score for automated conversion into a musical file format
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2230/00—General physical, ergonomic or hardware implementation of electrophonic musical tools or instruments, e.g. shape or architecture
    • G10H2230/005—Device type or category
    • G10H2230/015—PDA [personal digital assistant] or palmtop computing devices used for musical purposes, e.g. portable music players, tablet computers, e-readers or smart phones in which mobile telephony functions need not be used
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
    • G10H2240/00—Data organisation or data communication aspects, specifically adapted for electrophonic musical tools or instruments
    • G10H2240/011—Files or data streams containing coded musical information, e.g. for transmission
    • G10H2240/016—File editing, i.e. modifying musical data files or streams as such

Definitions

  • the embodiments of the present application relate to the field of computers, and in particular, to a method, an apparatus, and a storage medium for generating a digital score file of a song.
  • MIDI Musical Instrument Digital Instrument
  • participant causes the production cost of digital music score files to be large, and on the other hand, there is no effective way to detect the quality of the digital score files produced, which results in the production efficiency of digital music score files is relatively low.
  • the embodiment of the present application provides a method, an apparatus, and a storage medium for generating a digital music score file of a song, so as to at least solve the technical problem of low production efficiency of the digital music score file in the related art.
  • a method of generating a digital score file of a song includes: obtaining an utterance audio file that satisfies a first condition from an accompaniment audio file corresponding to the song, wherein the sing-along audio file includes the sing-song data that the user sings the song; and according to the time information of the song Candidate clearing audio file Dividing a plurality of valid audio segments; extracting note information of each valid audio segment, wherein the note information includes one or more triplets, each triple including a start time of a note having a mapping relationship, and the duration of the note Time, the note value of the note; and generating a digital score file based on the note information of each valid audio segment, wherein the digital score file includes some or all of the triples.
  • a device for generating a digital musical score file of a song includes: an obtaining unit configured to acquire a candidate presenting audio file satisfying the first condition from the clearing audio file corresponding to the song, wherein the clearing audio file includes the clearing data of the user singing the song a dividing unit configured to divide a plurality of valid audio segments from the candidate captivating audio file according to the time information of the song; the extracting unit configured to extract note information of each valid audio segment, wherein the note information includes one or more a triplet, each triple including a start time of a note having a mapping relationship, a duration of a note, a note value of a note; and a generating unit configured to generate a digital score based on note information of each valid audio segment A file in which the digital score file includes some or all of the triples.
  • a terminal configured to execute a program code for performing the steps in the method of generating a digital musical score file of the song of the embodiment of the present application.
  • a storage medium configured to store program code for performing steps in a method of generating a digital music score file of a song of an embodiment of the present application .
  • the candidate clearing audio file that satisfies the first condition is obtained from the clearing audio file corresponding to the song, wherein the clearing audio file includes the clearing data of the user singing the song; and the candidate clearing audio is selected according to the time information of the song.
  • Deriving a plurality of valid audio segments in the file extracting note information of each valid audio segment, the note information includes one or more triplets, each triple including a start time of a note having a mapping relationship, and the duration of the note Time, the note value of the note; generating a digital score file based on the note information of each valid audio segment, The digital score file includes part or all of the triplet, and the digital music score file is generated by the song sing data of the song corresponding to the user candidate to clear the audio file, thereby achieving the purpose of automatically generating the digital score file, thereby improving the clearing audio.
  • the technical effect of the production efficiency of the document further solves the technical problem of low efficiency in the production of digital music score files in the related art.
  • FIG. 1 is a schematic diagram of a hardware environment of a method for generating a digital music score file of a song according to an embodiment of the present application
  • FIG. 2 is a flowchart of a method of generating a digital score file of a song according to an embodiment of the present application
  • FIG. 3 is a flowchart of a method for dividing a plurality of valid audio segments from a candidate utterance audio file according to time information of a song according to an embodiment of the present application;
  • FIG. 4 is a flowchart of a method of extracting note information of each valid audio segment, according to an embodiment of the present application
  • FIG. 5 is a flow chart of a method of performing processing on each valid audio segment, in accordance with an embodiment of the present application
  • FIG. 6 is a flowchart of a method of generating a digital score file of another song according to an embodiment of the present application
  • FIG. 7 is a flowchart of a method of generating a digital music score file of another song according to an embodiment of the present application.
  • FIG. 8 is a flowchart of a method of merging note values according to an embodiment of the present application.
  • FIG. 9 is a diagram of generating a triple corresponding to a plurality of valid audio segments according to an embodiment of the present application. Flow chart of the method;
  • FIG. 10 is a flowchart of a method of generating a digital score file based on note information of each valid audio segment, in accordance with an embodiment of the present application
  • FIG. 11 is a flowchart of a method for acquiring a candidate clearing audio file according to an embodiment of the present application
  • FIG. 12 is a flowchart of a method of generating a digital score file of another song according to an embodiment of the present application
  • FIG. 13 is a schematic diagram of a visualization format for generating a digital score file according to note information of each valid audio segment, according to an embodiment of the present application
  • FIG. 14 is a schematic diagram of a device for generating a digital musical score file of a song according to an embodiment of the present application
  • 15 is a schematic diagram of a device for generating a digital musical score file of another song according to an embodiment of the present application.
  • 16 is a schematic diagram of a device for generating a digital musical score file of another song according to an embodiment of the present application
  • 17 is a schematic diagram of a device for generating a digital musical score file of another song according to an embodiment of the present application.
  • FIG. 18 is a structural block diagram of a terminal according to an embodiment of the present application.
  • an embodiment of a method for generating a digital music score file of a song is provided.
  • the method of generating the digital score file of the above song can be applied to the hardware environment constituted by the server 102 and the terminal 104 as shown in FIG. 1.
  • FIG. 1 is a schematic diagram of a hardware environment of a method for generating a digital musical score file of a song according to an embodiment of the present application.
  • the server 102 is connected to the terminal 104 through a network.
  • the network includes but is not limited to a wide area network, a metropolitan area network, or a local area network.
  • the terminal 104 is not limited to a PC, a mobile phone, a tablet, or the like.
  • the method for generating the digital score file of the song of the embodiment of the present application may be executed by the server 102, may be executed by the terminal 104, or may be jointly executed by the server 102 and the terminal 104.
  • the method for generating the digital score file of the song of the terminal of the embodiment of the present application may also be performed by a client installed thereon.
  • FIG. 2 is a flow chart of a method of generating a digital score file of a song according to an embodiment of the present application. As shown in FIG. 2, the method may include the following steps:
  • Step S202 Acquire a candidate clearing audio file that satisfies the first condition from the clearing audio file corresponding to the song.
  • the sing-along audio file includes the sing-along data that the user sings the song.
  • the candidate clearing audio file is a clearing audio file that satisfies the first condition, wherein the first condition is a screening condition for screening out the candidate clearing audio file in the clearing audio file corresponding to the song, that is, determining whether the clearing audio file reaches the candidate.
  • Standards for example, a large number of other users' uploaded audio files
  • each of the plurality of clearing audio files obtains a corresponding score, and the first condition is set to a condition that the score is higher than the predetermined score threshold, for example, the clearing audio file is performed between 0 and 10 minutes.
  • the score is set to a condition that the score is higher than 8 points, and the captivating audio file having a score higher than the predetermined score threshold is determined as the candidate singer audio file.
  • a large number of other users can also evaluate the uploaded clearing audio files, such as "satisfaction”, “unsatisfactory”, “bad review”, “general”, “excellent”, “like”, etc.
  • a condition is set as a condition that the evaluation result reaches a predetermined evaluation threshold. For example, if the first condition is set as the evaluation result reaches 10 "satisfactory", 20 excellent, and 30 praise conditions, the evaluation result reaches the predetermined threshold of the clearing audio.
  • the file is determined to be a candidate clearing audio file.
  • the first condition further includes a condition of manual screening in addition to the screening condition, that is, the screening condition is a preliminary screening condition in the first condition.
  • the screening condition is a preliminary screening condition in the first condition.
  • the specific producer makes an audition of the clearing audio file that reaches the initial screening condition, and determines whether the singing pitch of the clearing audio file that reaches the initial screening condition is accurate, that is, It is determined whether the singing pitch of the user who sings the clearing audio file that reaches the initial screening condition reaches the available standard. If it is determined that the singing pitch of the clearing audio file that reaches the preliminary screening condition is accurate, it is determined that the uploaded clearing audio file is the candidate clearing audio file.
  • the above-described clearing audio file includes the clearing data of the user singing the song, and the clearing data includes sound data of the user collected by the user when singing the song, the sound data including a tone for indicating the voice of the user.
  • the data is data for indicating the timbre of the user's voice, data for indicating the loudness of the user's voice, data for indicating the tone of the user's voice, and the like.
  • the captivating audio file may further include pitch data of the user singing a hand song, the pitch data being used to instruct the user to sing the pitch of the hand song so that the specific producer judges whether the user sings the song accurately.
  • an upload request for requesting uploading the clearing audio file is sent.
  • Filter the objects that receive the upload request before sending the upload request. Can get the number According to the history of the songs sung by the user stored in the library, the data is sung. Determining the level data for indicating the level of the user's singing according to the historical singing data, determining the user whose level data reaches the predetermined level threshold as the target user, and preferably determining the clearing audio file generated by the target user singing the song as the candidate clearing audio file. , the terminal that records the target user's clearing audio file, that is, the object that receives the upload request.
  • the evaluation data for evaluating the song sung by the user and the scoring data for scoring the song may also be obtained from the database, for example, the evaluation data includes indicating “satisfactory” and “ If you are dissatisfied, "bad”, “general”, “excellent”, “like”, etc., the scoring data can be used to indicate scoring data between 0 and 10 points. Determining the level data for indicating the level of the user's singing according to the evaluation data and the scoring data, and determining the user whose level data reaches the preset level threshold as the target user, and acquiring the clearing audio file generated by the target user singing the song.
  • the song to be generated by the digital music score file is a new song, and no user sings it for a while, and the prize invites the high-level user to sing the new song to obtain the clearing audio file corresponding to the new song.
  • Step S204 dividing a plurality of valid audio segments from the candidate clearing audio files according to the time information of the song.
  • a song corresponds to a lyric file
  • the lyric file includes time information corresponding to each lyric.
  • Each sentence in the lyrics file corresponds to an audio segment.
  • an audio segment having lyrics and no unwanted noise is determined as a valid audio segment of the candidate utterance audio file.
  • the plurality of valid audio segments are divided from the candidate clearing audio file, and optionally, the duration information of each sentence in the lyric file corresponding to the candidate clearing audio file is obtained, according to the duration of each lyric file.
  • the information divides the candidate clearing audio file to obtain the division result, and detects whether the division result has extra noise, thereby removing the portion without the lyrics, and ensuring that the effective audio segment has no unnecessary noise.
  • Step S206 extracting note information of each valid audio segment.
  • the note information includes one or more triples from which triads can be extracted.
  • Each valid audio segment can be processed, for example, filtering processing is performed on each valid audio segment to obtain a baseband, and the fundamental frequency value in the baseband is subjected to note processing to obtain a note value of the fundamental frequency value, and then the note is obtained.
  • the values are merged to join the points of the same note value in the note value and generate a triple corresponding to each valid audio segment, and the triple of each valid audio segment includes the start time of the triple. , the triplet's note value, the duration of the triple.
  • Each triple includes the start time of the note with the mapping relationship, the duration of the note, and the note value of the note.
  • the start time of the note is also the start time of the triplet.
  • the unit of the start time can be milliseconds
  • the duration of the note is the duration of the triplet.
  • the unit of the duration can be milliseconds.
  • the note value of the note is also the note value of the triplet.
  • Step S208 generating a digital score file according to the note information of each valid audio segment.
  • the digital score file includes some or all of the triples. After extracting the note information of each valid audio segment, a digital score file is generated based on the start time of the note, the duration of the note, and the note value of the note. Optionally, the plurality of triplets in the note information are combined into a triple sequence, and the triplet sequence is normalized to obtain a digital score file.
  • the digital score file is output in a preset format.
  • the quality of the digital score file is detected, for example, the digital score file with the quality test is retained, and the digital score file with the unqualified quality test is deleted, thereby reducing the artificial production cost of the digital score file and improving the digital score file. Production efficiency.
  • the digital score file is a MIDI file, thereby effectively reducing the labor cost of making the MIDI file by the above steps, improving the quality of the MIDI file, and improving the production efficiency of the MIDI file.
  • the candidate clearing audio file obtained by the embodiment from the clearing audio file corresponding to the song may be one or more.
  • each candidate clearing audio file is divided according to the time information of the song, and a plurality of valid audio segments of each candidate clearing audio file are obtained, corresponding to each candidate clearing audio file.
  • the note information of the plurality of valid audio segments generates a digital score file corresponding to each candidate captivating audio file, and the digital score file corresponding to each candidate captivating audio file may be a MIDI file.
  • the digital score file corresponding to each candidate clearing audio file may be selected by the user, and the digital score file corresponding to the selected candidate clearing audio file is determined as the final digital score file of the song, and may also be used for each candidate.
  • the digital score file corresponding to the audio file is cleared for quality detection, and the quality detection result is obtained, and the digital score file with the highest quality detection result is determined as The final digital score file for the song.
  • the clearing audio file satisfying the first condition is obtained from the clearing audio file corresponding to the song; and the plurality of valid audio segments are divided from the candidate clearing audio file according to the time information of the song; extracting each valid
  • the note information of the audio segment includes one or more triplets, each triplet including the start time of the note having the mapping relationship, the duration of the note, the note value of the note; and according to each valid audio segment
  • the note information generates a digital score file, and the digital score file includes part or all of the triplet, and the digital score file is generated by the song sing data of the song corresponding to the user candidate to clear the audio file, thereby achieving the purpose of automatically generating the digital score file.
  • the high cost of artificially making a digital music score file is avoided, thereby realizing the technical effect of improving the production efficiency of the digital music score file, thereby solving the technical problem of low production efficiency of the digital music score file in the related art.
  • step S204 a plurality of valid audio segments are segmented from the candidate clearing audio file according to the time information of the song, and the candidate clearing audio file is to be selected according to the time information corresponding to each lyrics in the lyric file. Multiple valid audio segments are divided for implementation.
  • FIG. 3 is a flow diagram of a method of dividing a plurality of valid audio segments from a candidate utterance audio file based on time information of a song, in accordance with an embodiment of the present application. As shown in FIG. 3, the method includes the following steps:
  • Step S301 acquiring a lyric file corresponding to the song.
  • a song corresponds to a lyric file, and a lyric file corresponding to the song is obtained, and the lyric file includes time information corresponding to each lyric.
  • the candidate sing-along audio file has a lyric file, and the playing time of each audio segment in the candidate sing-along audio file is obtained according to the lyric file provided by the candidate sing-along audio file, and the lyric file includes indication information for indicating the playing duration, that is, The indication information can determine the duration of play of each audio segment in the lyric file during playback.
  • Step S302 the candidate clearing sound is based on the time information corresponding to each lyrics in the lyric file.
  • the frequency file divides a number of valid audio segments.
  • the time information corresponding to each lyric is the playing duration of each audio segment in the candidate sing-along file.
  • lyrics file corresponding to the song is obtained, a plurality of audio segments in the candidate sing-along file are determined from the time information corresponding to each lyric in the lyric file, and each audio segment corresponds to each lyric in the lyric file.
  • the time information corresponding to the first sentence of the lyric file is 1 to 8 seconds
  • the time information corresponding to the second sentence is 1 to 10 seconds
  • the time information corresponding to the third sentence is 1 to 6 seconds.
  • acquiring original audio data in the candidate clearing audio file dividing the original audio data according to time information corresponding to each lyric, obtaining a plurality of audio segments, removing portions of each audio segment without lyrics, and removing The portion with excess noise is extracted, thereby extracting a plurality of valid audio segments from the plurality of valid audio segments, thereby achieving the purpose of dividing the candidate clearing audio files into multiple effective audio segments according to the time information corresponding to each lyrics in the lyric file.
  • the candidate lyrics audio file is divided into a plurality of valid audio segments according to the time information corresponding to each lyrics in the lyric file by acquiring the lyric file corresponding to the song, thereby realizing the division according to the time information of the song from the candidate singer audio file.
  • step S206 extracting note information of each valid audio segment includes: in a plurality of valid audio segments, a sum of play durations of audio segments having a non-zero baseband value exceeding a preset time Next, processing is performed on each valid audio segment to obtain a baseband, and the note values obtained by performing the note processing on the baseband value in the baseband are combined to implement the extraction of the note information of the effective audio segment.
  • FIG. 4 is a diagram of extracting note information of each valid audio segment according to an embodiment of the present application. Flow chart of the method. As shown in FIG. 4, the method includes the following steps:
  • Step S401 extracting the fundamental frequency information of each valid audio segment.
  • the baseband information includes the fundamental frequency value of the audio segment. After dividing a plurality of valid audio segments from the candidate clear audio file, extracting the baseband information of each valid audio segment, the baseband information may be a baseband with a frame shift of 10 milliseconds and a frame length of 30 milliseconds.
  • the frequency information includes the fundamental frequency value of the audio segment. Since the frequency generated by the vibration when the sound is transmitted through the channel is filtered, a large amount of overtones are generated. In order to facilitate the subsequent processing of the candidate clearing audio file, it is necessary to extract the pitch directly expressing the vibration frequency of the soundtrack from the audio information, and the pitch is also determined. The pitch of the entire note, that is, the fundamental frequency value.
  • Step S402 Acquire a sum of playing durations of audio segments whose baseband values are non-zero among the plurality of valid audio segments.
  • the audio segment 1, the audio segment 2, the audio segment 3, and the audio segment 4 are included, wherein the audio segment 1 and the audio segment 2 are audio segments having an audio value of non-zero, and the audio segment 3 and the audio segment 4 are audio having an audio value of zero.
  • the clip extracts the audio clip 1 and the audio clip 2 from the audio clip 1, the audio clip 2, the audio clip 3, and the audio clip 4.
  • the playback duration of the audio segment whose baseband value is non-zero is obtained, and the playback duration of the audio segment whose baseband value is non-zero is calculated.
  • obtaining a sum of playing durations of the audio clips whose baseband value is non-zero for example, after extracting the audio clip 1 and the audio clip 2 from the audio clip 1, the audio clip 2, the audio clip 3, and the audio clip 4, respectively Obtain the playing duration of the audio segment 1 and the audio segment 2, for example, the playing time of the audio segment 1 is 2 seconds, the playing time of the audio segment 2 is 3 seconds, and the playing time of the audio segment 1 is 2 seconds and the playing of the audio segment 2 is performed.
  • the summation calculation is performed for 3 seconds, and the playback duration of the audio clip whose baseband value is non-zero is obtained for 5 seconds.
  • the base frequency value of the adjacent valid audio segments of the plurality of valid audio segments may be acquired, adjacent to
  • the difference between the fundamental frequency values of the effect audio segments satisfies a certain condition, for example, the difference between the fundamental frequency values of the adjacent valid audio segments is less than the predetermined difference
  • the fundamental frequency value of the adjacent valid audio segment is set to zero, That is, the singular base frequency point is detected according to the difference of the fundamental frequency values of the front and rear fundamental frequency points in the effective audio segment, and the singular base frequency point is set to zero, so that the adjacent valid audio segment is an audio segment with a fundamental frequency value of zero.
  • step S403 it is determined whether the sum of the playing durations exceeds a preset time.
  • the playback duration does not exceed the preset time that is, the sum of the playback durations of the audio segments whose baseband values are non-zero is relatively short, it is determined that the effective audio segment is not Passing through, can not be used to obtain the baseband; or, re-extracting the fundamental frequency information of each valid audio segment, obtaining the sum of the playing durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments, and judging the playing time again
  • the preset time is exceeded, if the playing time has not exceeded the preset time, it is directly determined that the valid audio segment has not passed the pass and cannot be used to obtain the base band; or, the valid audio segment is not processed.
  • Step S404 performing processing on each valid audio segment to obtain a base frequency band.
  • processing is performed on each valid audio segment to obtain a baseband, that is, performing processing on the plurality of valid audio segments respectively. , get the base band.
  • filtering processing is performed on each valid audio segment to obtain a baseband.
  • the note value of the fundamental frequency value can well divide the triplet including the start time, the note value and the duration, so that the note information of the effective audio segment can be accurately obtained, and the note information of each valid audio segment can be extracted. Purpose, and then generate a digital score file according to the note information of each valid audio segment, thereby improving The effect of clearing the production efficiency of audio files.
  • Step S405 obtaining a fundamental frequency value in the base frequency band.
  • the fundamental frequency value in the base band is obtained.
  • the value of the zero-base frequency band in the base frequency band that is less than the preset number of frames is set to the base frequency value of the last frame of the base frequency band, for example, the base frequency value of the zero-based frequency band less than 15 frames behind the base frequency band is set as a base.
  • the baseband value of the last frame of the band is set to the base frequency value of the last frame of the base frequency band.
  • Step S406 performing a note processing on the fundamental frequency value to obtain a note value of the fundamental frequency value.
  • a note value f(x) of the fundamental frequency value is calculated, where x is the fundamental frequency value of the base band.
  • x is the fundamental frequency value of the base band.
  • all the fundamental frequency values in the base frequency band are tokenized to obtain a note value.
  • Step S407 the note values are combined to obtain note information of the valid audio segment.
  • the embodiment extracts the baseband information of each valid audio segment, wherein the baseband information includes a baseband value of the audio segment; and obtains a sum of play durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments; If the sum of the playback durations exceeds the preset time, performing processing on each valid audio segment to obtain a baseband; obtaining a baseband value in the baseband; performing a tokenization process on the baseband value to obtain a note value of the baseband value; Combining the note values to obtain the note information of the valid audio segment realizes the purpose of extracting the note information of each valid audio segment, thereby achieving the effect of improving the production efficiency of the clearing audio file.
  • performing processing on each valid audio segment includes performing filtering processing on the audio segment according to the length corresponding to the audio segment, obtaining a filtered segment, and acquiring a fundamental frequency value of the filtered segment.
  • FIG. 5 is a flow diagram of a method of performing processing on each valid audio segment in accordance with an embodiment of the present application. As shown in FIG. 5, the method includes the following steps:
  • Step S501 obtaining a length corresponding to each valid audio segment.
  • the length corresponding to the audio segment in this embodiment is in frames. If it is determined that the sum of the play durations exceeds the preset time, the length corresponding to each valid audio segment is obtained.
  • Step S502 performing a first filtering process on the valid audio segment whose length is smaller than the first preset value, to obtain a first filtering segment.
  • the filtering segment for example, the first preset value is 35 frames, and the median filtering of the length of the base band is directly performed on the effective audio segment whose baseband length is less than 35 frames, to obtain the first filtering segment.
  • Step S503 performing a second filtering process on the valid audio segment whose length is greater than or equal to the first preset value, to obtain a second filtering segment.
  • the filter segment for example, the first preset value is 35 frames, and the audio segment with the base band length greater than or equal to 35 frames is subjected to median filtering of 10 points per frame to obtain a second filter segment.
  • median filtering is used to filter out the noise signal in the active audio segment and to protect the signal edges of the active audio segment from blurring while filtering out the noise signal.
  • median filtering of valid audio clips set the window length to the audio in the window length
  • the data of the segment is set to the signal sample value of the median filter, and the signal sample values are arranged in ascending order, so that the median value of the sorted data is the output value of the median filter.
  • the window length is set to 10 points, that is, the length is greater than or equal to the first preset value.
  • 10 data in each audio segment of the effective audio segment is median filtered
  • 10 data in the window length is set as the median filtered signal sample value
  • the signal sample values are arranged in ascending order, so that The median value of the sorted data is the output value of the median filter, thereby obtaining a second filter segment.
  • acquiring the base frequency value in the base frequency band includes: acquiring a base frequency value of the first filtered segment and a base frequency value of the second filtered segment.
  • the embodiment obtains a length corresponding to each valid audio segment, performs a first filtering process on the effective audio segment whose length is less than the first preset value, to obtain a first filtering segment, and obtains an audio segment whose length is greater than or equal to the first preset value.
  • Performing the second filtering process to obtain the second filtering segment achieves the purpose of performing processing on each valid audio segment, thereby achieving the purpose of improving the efficiency of the digital music score file.
  • the zero audio segment exists in the effective audio segment whose length is less than the second preset value, and the base frequency value of the zero audio segment is set to pre Set the base frequency value.
  • FIG. 6 is a flow chart of a method of generating a digital score file of another song according to an embodiment of the present application. As shown in FIG. 6, the method further includes the following steps:
  • Step S601 Determine whether a zero-tone segment exists in the valid audio segment whose length is less than the second preset value.
  • the zero-tone segment is an audio segment with a baseband value of zero, and the second preset value can be 15 frames. Whether there is a zero-audio clip in an audio clip whose length is less than 15 frames.
  • Step S602 setting a fundamental frequency value of the zero audio segment to a preset fundamental frequency value.
  • the base frequency value of the zero-audio segment is set to The preset baseband value, optionally, the preset baseband value is the baseband value of the last frame of the baseband, and the baseband value of the zero fundamental frequency segment less than 15 frames behind the baseband may be set to the last frame of the baseband. Base frequency value.
  • acquiring the base frequency value in the base frequency band includes: acquiring a base frequency value of the first filtered segment, a base frequency value of the second filtered segment, and a preset base frequency value.
  • the base frequency value of the zero-audio segment is set to a preset baseband value; and the fundamental frequency value of the first filtered segment and the second filtered segment are obtained.
  • the base frequency value and the preset base frequency value achieve the purpose of performing processing on each valid audio segment, thereby achieving the purpose of improving the production efficiency of the clearing audio file.
  • the second condition is satisfied by the difference between the fundamental frequency values of the adjacent audio segments.
  • the fundamental frequency value of the adjacent audio segment is set to zero.
  • FIG. 7 is a flow chart of a method of generating a digital score file of another song according to an embodiment of the present application. As shown in FIG. 7, the method further includes the following steps:
  • Step S701 Acquire a base frequency value of a neighboring audio segment among the plurality of valid audio segments.
  • the base frequency value of the adjacent audio segments of the plurality of valid audio segments is obtained before acquiring the sum of the durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments.
  • Step S702 calculating a difference value of a fundamental frequency value of the adjacent audio segment.
  • the fundamental frequency values of the adjacent audio segments are calculated to obtain a difference between the fundamental frequency values of the adjacent audio segments.
  • Step S703 determining whether the difference satisfies the second condition.
  • the second condition may be a condition that the difference is less than the predetermined difference, which is a condition for detecting the singular base frequency point.
  • the singular base frequency points are detected according to the difference between the fundamental frequency values of the base frequency points before and after.
  • Step S704 the base frequency value of the adjacent audio segment is set to zero.
  • the singular fundamental frequency point is determined according to the difference between the fundamental frequency values of the base frequency points before and after, and the fundamental frequency value of the adjacent audio segment is set to zero.
  • the base frequency value of the adjacent audio segments in the plurality of valid audio segments is obtained before acquiring the sum of the durations of the audio segments whose baseband values are non-zero in the plurality of valid audio segments; calculating the basis of the adjacent audio segments The difference of the frequency values; determining whether the difference satisfies the condition; if it is determined that the difference satisfies the second condition, the base frequency value of the adjacent audio segment is set to zero, thereby realizing the operation of zeroing the audio segment, thereby improving the The efficiency of the production of audio files.
  • step S407 combining the note values to obtain the note information of the valid audio segment includes: generating a triplet corresponding to the plurality of valid audio segments according to the same note value in the note value, and using the effective audio The triples corresponding to the segments are combined into a first triplet sequence for representing note information.
  • FIG. 8 is a flow chart of a method of merging note values in accordance with an embodiment of the present application. As shown in FIG. 8, the method includes the following steps:
  • Step S801 combining the same note values in the note values, and generating a triplet corresponding to the plurality of valid audio segments.
  • the triplet corresponding to the plurality of valid audio segments includes the start time of the triplet , the triplet's note value, the duration of the triple.
  • Step S802 combining the triples corresponding to the plurality of valid audio segments into a first triplet sequence for representing note information.
  • This embodiment combines the same note values in the note values and generates a triplet corresponding to the plurality of valid audio segments; and combines the triples corresponding to the plurality of valid audio segments into the first for representing the note information
  • the triplet sequence realizes the purpose of combining the note values to obtain the note information of the valid audio segment.
  • step S801 generating a triplet corresponding to the plurality of valid audio segments includes: starting time of the triplet corresponding to the plurality of valid audio segments according to the same note value, and multiple valid audio segments The duration of the corresponding triples generates a triple of corresponding valid audio segments.
  • FIG. 9 is a flow chart of a method of generating triples corresponding to a plurality of valid audio segments, in accordance with an embodiment of the present application. As shown in FIG. 9, the method includes the following steps:
  • Step S901 Acquire the same note value, the start time of the triplet corresponding to the plurality of valid audio segments, and the duration of the triplet corresponding to the plurality of valid audio segments.
  • Step S902 generating a triplet corresponding to the plurality of valid audio segments according to the same note value, the start time of the triplet corresponding to the plurality of valid audio segments, and the duration of the triplet corresponding to the plurality of valid audio segments.
  • the start time of the triplet corresponding to the plurality of valid audio segments, and the duration of the triplet corresponding to the plurality of valid audio segments, the ternary corresponding to the plurality of valid audio segments according to the same note value The start time of the group, the triple of the corresponding valid audio segment The duration generates a triple of corresponding valid audio segments.
  • the embodiment obtains the same note value, the start time of the triplet corresponding to the plurality of valid audio segments, and the duration of the triplet corresponding to the plurality of valid audio segments; corresponding to the plurality of valid audio segments according to the same note value
  • the start time of the triplet and the duration of the triplet corresponding to the plurality of valid audio segments generate a triplet corresponding to the plurality of valid audio segments, thereby achieving the purpose of generating a triplet corresponding to the plurality of valid audio segments, and further Improve the efficiency of the production of clearing audio files.
  • the first triplet sequence includes a first triplet and a second triplet
  • step S208 generating a digital musical score file according to note information of each valid audio segment includes obtaining under different conditions.
  • the second triad sequence outputs the triad in the second triad sequence according to a preset format to obtain a digital score file.
  • FIG. 10 is a flow chart of a method of generating a digital score file based on note information of each valid audio segment, in accordance with an embodiment of the present application. As shown in FIG. 10, the method includes the following steps:
  • Step S1001 combining the first triplet and the second triplet to obtain a third triplet, and deleting the first triplet from the first triplet sequence to obtain a second triplet sequence.
  • Step S1002 combining the fourth triplet and the first triplet to obtain a fifth triplet, and deleting the first triplet from the first triplet sequence to obtain a second triplet sequence.
  • the start time of the fourth triplet when the start time of the first triplet is not equal to the sum of the start time of the second triplet and the duration of the second triplet, when the fourth ternary
  • the start time of the group is equal to the sum of the start time of the first triplet and the duration of the first triplet
  • the fourth triplet and the first triplet are merged to obtain the fifth triplet
  • the first triad is deleted from the first triad sequence to obtain a second triad sequence.
  • Step S1003 deleting the first triplet from the first triplet sequence to obtain the second triplet sequence.
  • the start time of the first triplet is not equal to the sum of the start time of the second triplet and the duration of the second triplet, and when the start time of the fourth triplet is not equal to the first three
  • the start time of the tuple is equal to the duration of the first triplet, the first triplet is deleted from the first triplet sequence to obtain a second triplet sequence.
  • step S1004 the triplet in the second triplet sequence is output according to a preset format to obtain a digital score file.
  • the triplet in the second triplet sequence is output according to a preset format to obtain a digital musical score file.
  • step S202 acquiring the candidate clearing audio file from the clearing audio file corresponding to the song includes: obtaining reply information for the plurality of original clearing audio files, and the quality level indicated by the reply information reaches a predetermined level.
  • the original captivating audio file it is determined as a candidate captivating audio file.
  • FIG. 11 is a flow chart of a method of acquiring a candidate utterance audio file in accordance with an embodiment of the present application. As shown in FIG. 11, the method for obtaining a candidate clearing audio file includes the following steps:
  • Step S1101 Acquire a plurality of original clearing audio files uploaded.
  • the original clearing audio file can be used for the user to sing the song-song audio file uploaded by the song, and obtain the uploaded original clearing audio files.
  • Step S1102 Acquire reply information for a plurality of original clearing audio files.
  • the reply information is used to indicate the quality level of the original clearing audio file, and the user can sing the song after the uploading, and other users are
  • the work is scored and/or evaluated, and the quality level is determined by scoring and/or evaluation.
  • step S1103 it is judged whether the quality level indicated by the reply information reaches a predetermined level.
  • step S1104 the original captivating audio file is determined as a candidate clearing audio file.
  • the original captivating audio file is determined as the candidate capsizing audio file. Alternatively, if it is determined that the quality level indicated by the reply information does not reach the predetermined level, the original captivating audio file is not determined as the candidate captivating audio file.
  • the user evaluation reaches a certain threshold, for example, when 32 "likes" are obtained, the user is considered to sing the song to the candidate standard, and the original singer audio file is determined as the candidate singer audio file.
  • the embodiment obtains the plurality of original clearing audio files uploaded; obtains reply information for the plurality of original clearing audio files, the reply information is used to indicate the quality level of the original clearing audio file; and determines whether the quality level indicated by the reply information reaches the predetermined level. The level; and if it is determined that the quality level indicated by the reply message reaches a predetermined level, the original captivating audio file is determined as the candidate singer audio file, and the purpose of acquiring the candidate singer audio file is achieved.
  • determining the original clearing audio file as the candidate clearing audio file includes: acquiring the pitch data of the original clearing audio file if it is determined that the evaluation index meets the preset evaluation index; determining whether the pitch data conforms to the pre-preparation The pitch is set; and if it is determined that the pitch data conforms to the preset pitch, the original clearing audio file is determined to be a candidate clearing audio file, and the acquisition of the candidate candidate clearing audio file is realized.
  • the format of the candidate clearing audio file is adjusted to a preset format, for example, the format of the candidate clearing audio file is adjusted to a 16k16 bit pcm format to obtain an adjusted clearing audio file, according to the song.
  • the time information is divided into a plurality of valid audio segments from the adjusted clear audio file; the note information of each valid audio segment is extracted; and the digital score file is generated according to the note information of each valid audio segment, thereby achieving the purpose of automatically generating the digital score file .
  • the candidate sing-along audio file includes the sing-song data of the song corresponding to the user candidate sing-along audio file; the plurality of valid audio segments are divided from the candidate sing-along audio file; and each valid audio segment is extracted.
  • the note information includes one or more triples, each triple including a start time of a note having a mapping relationship, a duration of the note, a note value of the note; a note according to each valid audio segment
  • the information generates a digital score file, wherein the digital score file includes part or all of the triplet, and the digital score file is generated by the song sing data of the song corresponding to the user candidate to clear the audio file, thereby achieving the purpose of automatically generating the digital score file.
  • FIG. 12 is a flowchart of a method of generating a digital score file of another song according to an embodiment of the present application. As shown in Figure 12, this includes the following steps:
  • step S1201 the candidate user sings the song based on the user evaluation.
  • step S1202 After uploading the sing-along audio file of the song sung by the user, a large number of other users will score and/or evaluate the uploaded sing-along audio file, and when the score and/or evaluation reaches a certain threshold y, the song sung by the user is considered After the candidate criteria are met, the producer will perform an audition to determine whether the user's singing pitch has reached the available standard, and if the available criteria are met, step S1202 is performed.
  • the song to be generated for the clearing audio file is a new song, no one is singing at the moment. Then there is a prize to invite senior and high-level users to sing, then you can generate clearing audio files.
  • Step S1202 extracting a valid data segment according to the lyric file.
  • the lyrics file that comes with the song contains the duration information of each song.
  • the original audio data is cut according to the time of each sentence, and the part without lyrics is removed, so that there is no extra noise in the invalid part, so that A series of audio segments ⁇ x 1 , x 2 ... x n ⁇ , where n is the number of sentences in the lyrics file.
  • the pitch of the vibration frequency the pitch also determines the pitch of the entire note.
  • the singular fundamental frequency points are detected according to the difference between the fundamental frequency values of the fundamental frequency points before and after, and are set to zero. It is judged whether the sum of the passage times whose base frequency values are non-zero exceeds 10 seconds, and if it is less than 10 seconds, it is directly judged as not passing.
  • the median filtering with the window length being the length of the base band is directly performed to obtain the base band; when the effective audio segment is obtained When the length is greater than or equal to 35 frames, 10 median filtering is performed for each frame to obtain the base band.
  • the fundamental frequency value of the zero-base frequency band less than 15 frames behind the baseband is set to the baseband value of the last frame of the baseband, thereby achieving zero-based frequency point filling.
  • a note value f(x) of the fundamental frequency value is calculated, where x is the fundamental frequency value of the base band.
  • x is the fundamental frequency value of the base band.
  • all the fundamental frequency values in the base frequency band are tokenized to obtain a note value.
  • step S1204 the back end is regular.
  • the triplet O i is specially processed (where m i is the ith triplet)
  • m i-1 is the note value of the i-1th triplet
  • m i+1 is the note value of the i+1th triplet
  • the embodiment of the present application generates a digital music score file by using a candidate clearing audio file, wherein the candidate clearing audio file includes the music clearing data that the user sings the song corresponding to the candidate clearing audio file, so that the user's voice automatically generates the digital musical score file without Manual production reduces the cost of digital score file production and improves the efficiency of digital score file production.
  • the application environment of the embodiment of the present application may be, but is not limited to, the reference to the application environment in the foregoing embodiments.
  • An embodiment of the present application provides an optional specific application for implementing the foregoing information acquisition and transmission method.
  • FIG. 13 is a schematic diagram of a visualization format for generating a digital score file based on note information of each valid audio segment, in accordance with an embodiment of the present application.
  • the visual format of the digital score file is such that the triplet sequence represents a triplet for each row (eg, 36000 150 55), and the first column (eg, 36000 36150 36200 36330 36960) is a note.
  • the second column for example, 150 50 130 630 30
  • the note duration in ms
  • the third column for example, 55 56 57 56 55
  • each song that can be sung will have a corresponding MIDI file, which describes the pitch of the song performed by the original singer.
  • This file is a MIDI file that can be used. It has many functions, such as providing the user with a visual pitch reference curve, repairing the user's inadequacies, and evaluating the user's singing.
  • the previous MIDI files are manually created. In this way, on the one hand, the labor cost is large, and on the other hand, the finished MIDI file has no effective method for quality detection, and the candidate clearing audio file is obtained through the embodiment of the present application; and multiple candidates are selected from the candidate clearing audio file.
  • a valid audio segment extracting note information of each valid audio segment, wherein the note information includes one or more triples, each triple including a start time of a note having a mapping relationship, a duration of the note, and a note a note value; and generating a digital score file according to the note information of each valid audio segment, wherein the digital score file includes part or all of the triplet, and the digital score is generated by the sing data of the song corresponding to the song corresponding to the user candidate clearing the audio file File, the purpose of automatically generating digital score files, from Increase production efficiency to achieve a cappella audio files technical effect, and then solve the low efficiency of production technologies in digital music files technical issues.
  • the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware, but in many cases, the former is A better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present application.
  • FIG. 14 is a schematic diagram of a device for generating a digital musical score file of a song according to an embodiment of the present application.
  • the apparatus may include an acquisition unit 10, a division unit 20, an extraction unit 30, and a generation unit 40.
  • the obtaining unit 10 is configured to acquire an accompaniment audio file that satisfies the first condition from the vocal audio file corresponding to the song, wherein the sing-along audio file includes the sing-along data that the user sings the song.
  • the dividing unit 20 is arranged to divide a plurality of valid audio segments from the candidate captivating audio files according to the time information of the song.
  • the extracting unit 30 is configured to extract note information of each valid audio segment, wherein the note information includes one or more triplets, each triplet including a start time of the note having the mapping relationship, the duration of the note , the note value of the note.
  • the generating unit 40 is configured to generate digital music according to note information of each valid audio segment A spectral file in which a digital score file includes some or all of the triples.
  • the foregoing obtaining unit 10, the dividing unit 20, the extracting unit 30, and the generating unit 40 may be operated in the terminal as a part of the device, and the functions implemented by the above module may be executed by the processor in the terminal, and the terminal also It can be a smart phone (such as Android phone, iOS phone, etc.), tablet computer, applause computer, and mobile Internet devices (MID), PAD and other terminal devices.
  • the apparatus may include an acquisition unit 10, a division unit 20, an extraction unit 30, and a generation unit 40.
  • the dividing unit 20 includes: a first acquiring module 21 and a dividing module 22.
  • the obtaining unit 10, the dividing unit 20, the extracting unit 30, and the generating unit 40 of this embodiment have the same functions as those of the generating apparatus of the digital musical score file of the song of the embodiment shown in FIG. 14, and details are not described herein again. .
  • the first obtaining module 21 is configured to acquire a lyric file corresponding to the song, and the lyric file includes time information corresponding to each lyric.
  • the dividing module 22 is configured to divide the candidate cappuccino audio file into a plurality of valid audio segments according to time information corresponding to each lyrics in the lyric file.
  • the foregoing first obtaining module 21 and the dividing module 22 may be run in the terminal as part of the device, and the function implemented by the foregoing module may be performed by a processor in the terminal, and the terminal may also be a smart phone (eg, Terminal devices such as Android phones, iOS phones, etc., tablets, applause computers, and mobile Internet devices (MID), PAD, etc.
  • Terminal devices such as Android phones, iOS phones, etc., tablets, applause computers, and mobile Internet devices (MID), PAD, etc.
  • the apparatus may include: an obtaining unit 10, a dividing unit 20, an extracting unit 30, and a generating unit 40.
  • the extracting unit 30 includes: an extracting module 31, a second obtaining module 32, a judging module 33, and a first processing module. 34.
  • the third obtaining module 35 and the second processing module Block 36 and merge module 37.
  • the obtaining unit 10, the dividing unit 20, the extracting unit 30, and the generating unit 40 have the same functions as those of the generating apparatus of the digital musical score file of the song of the embodiment shown in FIG. 14, and details are not described herein again.
  • the extraction module 31 is arranged to extract the baseband information of each valid audio segment, wherein the baseband information comprises a fundamental frequency value of the audio segment.
  • the second obtaining module 32 is configured to obtain a sum of playing durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments.
  • the determining module 33 is configured to determine whether the sum of the playing durations exceeds a preset time.
  • the first processing module 34 is configured to perform processing on each valid audio segment to obtain a base frequency band when it is determined that the sum of the playback durations exceeds the preset time.
  • the playing duration does not exceed the preset time that is, the sum of the playing durations of the audio segments whose non-zero baseband values are non-zero is relatively short
  • determining The valid audio segment does not pass, and cannot be used to obtain the baseband; or, the fundamental frequency information of each valid audio segment is re-extracted, and the sum of the playback durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments is obtained again. It is determined whether the sum of the playback durations exceeds the preset time. If the playback duration has not exceeded the preset time, it is directly determined that the valid audio segment is not cleared, and cannot be used to obtain the baseband; or, the effective audio segment is not processed.
  • the third obtaining module 35 is configured to acquire a base frequency value in the base frequency band.
  • the second processing module 36 is configured to perform a note processing on the baseband value to obtain a note value of the baseband value.
  • the merging module 37 is set to merge the note values to obtain note information of the valid audio segment.
  • the above extraction module 31, second acquisition module 32, determination module 33, first processing module 34, third acquisition module 35, second processing module 36 and merge module 37 may operate as part of the device.
  • the terminal it can be executed by a processor in the terminal.
  • the functions implemented by the module may also be terminal devices such as smart phones (such as Android phones, iOS phones, etc.), tablet computers, applause computers, and mobile Internet devices (MID), PAD, and the like.
  • the generating device of the digital musical score file of the song further comprises: a calculating unit, a first determining unit, and a zeroing unit.
  • the obtaining unit 10 is configured to acquire a base frequency value of a neighboring audio segment of the plurality of valid audio segments before acquiring a sum of durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments;
  • the calculating unit is Set to calculate a difference value of the fundamental frequency values of the adjacent audio segments;
  • the first determining unit is set to determine whether the difference satisfies the condition;
  • the zeroing unit is set to set the adjacent audio when it is determined that the difference satisfies the second condition
  • the base frequency value of the segment is set to zero.
  • the foregoing computing unit, the first determining unit, and the zeroing unit may be operated in the terminal as part of the device, and the functions implemented by the foregoing unit may be performed by a processor in the terminal, and the terminal may also be a smart phone. (such as Android phones, iOS phones, etc.), tablets, applause computers and mobile Internet devices (Mobile Internet Devices, MID), PAD and other terminal devices.
  • the merging module 37 includes a generating module and a combining module.
  • the generating module is configured to combine the same note values in the note values and generate a triplet corresponding to the plurality of valid audio segments;
  • the combining module is configured to combine the triples corresponding to the plurality of valid audio segments into The first triplet sequence is set to represent note information.
  • the foregoing generating module and the combining module may be run in the terminal as part of the device, and the function implemented by the above module may be performed by a processor in the terminal, and the terminal may also be a smart phone (such as an Android mobile phone, iOS). Mobile phones, etc., tablet computers, applause computers, and mobile Internet devices (MID), PAD and other terminal devices.
  • a smart phone such as an Android mobile phone, iOS
  • MID mobile Internet devices
  • the generating module is configured to acquire the same note value, a start time of the triplet corresponding to the plurality of valid audio segments, a duration of the triplet corresponding to the plurality of valid audio segments, and according to the same note value, The start time of the triples corresponding to the valid audio segments and the duration of the triples corresponding to the plurality of valid audio segments generate triplets corresponding to the plurality of valid audio segments.
  • the first triplet sequence includes a first triplet and a second triplet
  • the generating unit 40 is configured to when the starting time of the first triplet is equal to the starting time of the second triplet and When the sum of the durations of the second triad is combined, the first triad and the second triad are combined to obtain a third triad, and the first triad is deleted from the first triad sequence to obtain the first a two-tuple sequence; when the start time of the first triplet is not equal to the sum of the start time of the second triplet and the duration of the second triplet, when the start time of the fourth triplet When the sum of the start time of the first triplet and the duration of the first triplet is merged, the fourth triplet and the first triplet are merged to obtain a fifth triplet, and from the first triplet Deleting the first triplet in the sequence to obtain a second triplet sequence; when the start time of the first triplet is not equal to the sum of the start time of the second triplet and the duration
  • the starting time, l i+1 is the duration of the fourth
  • the apparatus may include an acquisition unit 10, a division unit 20, an extraction unit 30, and a generation unit 40.
  • the extracting unit 30 includes: an extracting module 31, a second obtaining module 32, a determining module 33, a first processing module 34, a third obtaining module 35, a second processing module 36, and a merging module 37, wherein the first processing module 34
  • the method includes an acquisition submodule 341, a first processing submodule 342, and a second processing submodule 343.
  • the module 34, the third obtaining module 35, the second processing module 36, and the merging module 37 have the same functions as those of the digital musical score file generating apparatus of the song of the embodiment shown in FIG. 16, and are not described herein again.
  • the acquisition sub-module 341 is arranged to acquire the length corresponding to each valid audio segment.
  • the first processing sub-module 342 is configured to perform a first filtering process on the valid audio segment whose length is less than the first preset value, to obtain the first filtering segment.
  • the second processing sub-module 343 is configured to perform a second filtering process on the audio segment whose length is greater than or equal to the first preset value, to obtain a second filtering segment.
  • the third obtaining module 35 is configured to acquire a base frequency value of the first filtered segment and a base frequency value of the second filtered segment.
  • the foregoing obtaining submodule 341, the first processing submodule 342, and the second processing submodule 343 may be run in the terminal as part of the device, and the functions implemented by the foregoing module may be performed by a processor in the terminal.
  • the terminal can also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, an applause computer, and a mobile Internet device (MID), a PAD, and the like.
  • the generating device of the digital music score file of the song further includes: a second determining unit and a setting unit.
  • the second determining unit is configured to determine whether a zero audio segment exists in the valid audio segment whose length is less than the second preset value after acquiring the length corresponding to each valid audio segment, where the zero audio segment is a base frequency value.
  • An audio segment of zero a setting unit configured to: present a zero-tone segment in a valid audio segment whose length is less than a second preset value, and set a baseband value of the zero-tone segment to a preset baseband value;
  • the obtaining module 35 is configured to acquire a fundamental frequency value of the first filtered segment, a fundamental frequency value of the second filtered segment, and a preset fundamental frequency value.
  • the foregoing second determining unit and the setting unit may be run in the terminal as part of the device, and the function implemented by the above module may be performed by a processor in the terminal, and the terminal may also be a smart phone (such as an Android mobile phone). , iOS phones, etc.), tablet computers, applause computers, and mobile Internet devices (MID), PAD and other terminal devices.
  • a smart phone such as an Android mobile phone. , iOS phones, etc.
  • tablet computers tablet computers, applause computers, and mobile Internet devices (MID), PAD and other terminal devices.
  • MID mobile Internet devices
  • the obtaining unit 10 includes a fourth acquiring module, a fifth acquiring module, and a determining module.
  • the fourth obtaining module is configured to obtain the uploaded plurality of original clearing audio files;
  • the fifth obtaining module is configured to obtain reply information for the plurality of original clearing audio files, wherein the reply information is set to represent the original clearing audio a quality level of the file;
  • the determining module is configured to determine whether the quality level indicated by the reply information reaches a predetermined level, and when determining that the quality level indicated by the reply information reaches a predetermined level, determining the original clearing audio file as the candidate clearing audio file.
  • the fourth acquiring module, the fifth obtaining module, and the determining module may be run in the terminal as part of the device, and the function implemented by the foregoing module may be performed by a processor in the terminal, and the terminal may also be intelligent.
  • Mobile devices such as Android phones, iOS phones, etc.
  • tablets such as tablets, applause computers, and mobile Internet devices (MID), PAD and other terminal devices.
  • MID mobile Internet devices
  • the obtaining unit 10 in this embodiment may be configured to perform step S202 in Embodiment 1 of the present application
  • the dividing unit 20 in this embodiment may be configured to perform step S204 in Embodiment 1 of the present application.
  • the extracting unit 30 in this embodiment may be configured to perform step S206 in Embodiment 1 of the present application
  • the generating unit 40 in this embodiment may be configured to perform step S208 in Embodiment 1 of the present application.
  • the clearing audio file satisfying the first condition is acquired from the clearing audio file corresponding to the song by the obtaining unit 10, and the plurality of valid audio segments are divided from the candidate clearing audio file according to the time information of the song by the dividing unit 20.
  • the note information of each valid audio segment is extracted by the extracting unit 30, wherein the note information includes one or more triplets, each triplet including the start time of the note having the mapping relationship, the duration of the note, the note
  • the note value is generated by the generating unit 40 according to the note information of each valid audio segment, wherein the digital score file includes part or all of the triplet, and the song is sung by the user candidate to clear the song corresponding to the audio file.
  • the data generates a digital music score file, which achieves the purpose of automatically generating a digital music score file, thereby realizing the technical effect of improving the production efficiency of the clearing audio file, and solving the technical problem of low production efficiency of the digital music score file in the related art. question.
  • the above-mentioned units and modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited to the contents disclosed in the above embodiment 1. It should be noted that the foregoing module may be implemented in a hardware environment as shown in FIG. 1 as part of the device, and may be implemented by software or by hardware, where the hardware environment includes a network environment.
  • the various functional modules provided by the embodiments of the present application may be run in a mobile terminal, a computer terminal, or the like, or may be stored as part of a storage medium.
  • an embodiment of the present application may provide a terminal, which may be any computer terminal device in a group of computer terminals.
  • the foregoing terminal may also be replaced with a terminal device such as a mobile terminal.
  • the foregoing terminal may be located in at least one of the plurality of network devices of the computer network.
  • a terminal for implementing a method for generating a digital score file of the above song, wherein the terminal may be a computer terminal, and the computer terminal may be any one of the computer terminal groups.
  • the foregoing computer terminal may also be replaced with a terminal device such as a mobile terminal.
  • the computer terminal may be located in at least one network device of the plurality of network devices of the computer network.
  • FIG. 18 is a structural block diagram of a terminal according to an embodiment of the present application.
  • the terminal may include one or more (only one shown in the figure) processor 181, memory 183, and transmission device 185.
  • the terminal may further include an input/output device 187. .
  • the memory 183 can be used to store a software program and a module, such as a method for generating a digital music score file of a song in the embodiment of the present application, and a program instruction/module corresponding to the device, and the processor 181 runs the software program stored in the memory 183 and The module, thereby performing various functional applications and data processing, that is, a method of generating a digital score file of the above-described song.
  • the memory 183 may include a high speed random access memory, and may also include a nonvolatile memory such as one or Multiple magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 183 can further include memory remotely located relative to processor 181, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission device 185 described above is for receiving or transmitting data via a network, and can also be used for data transmission between the processor and the memory.
  • Specific examples of the above network may include a wired network and a wireless network.
  • the transmission device 185 includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network.
  • the transmission device 185 is a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the memory 183 is used to store an application.
  • the program code that the processor 181 can call the application stored in the memory 183 by the transmission device 185 to execute the method steps of the various optional or preferred embodiments of the foregoing method embodiments includes:
  • Extracting note information of each valid audio segment wherein the note information includes one or more triplets, each triplet including a start time of a note having a mapping relationship, a duration of the note, and a note value of the note;
  • a digital score file is generated based on note information for each valid audio segment, wherein the digital score file includes some or all of the triples.
  • the processor 181 is further configured to: obtain a lyric file corresponding to the song, the lyric file includes time information corresponding to each lyric; and the candidate singer audio file is divided into multiple valid according to the time information corresponding to each lyric in the lyric file. Audio clip.
  • the processor 181 is further configured to: extract the baseband information of each valid audio segment, where the baseband information includes a baseband value of the audio segment; and acquire audio with a non-zero baseband value in the plurality of valid audio segments.
  • the processor 181 is further configured to: obtain a length corresponding to each valid audio segment; perform a first filtering process on the valid audio segment whose length is less than the first preset value, to obtain a first filtering segment; and the length is greater than or equal to
  • the audio segment of a preset value performs a second filtering process to obtain a second filtering segment; and acquires a fundamental frequency value of the first filtering segment and a fundamental frequency value of the second filtering segment.
  • the processor 181 is further configured to perform the following steps: after acquiring the length corresponding to each valid audio segment, if the zero-audio segment exists in the valid audio segment whose length is less than the second preset value, setting the base frequency value of the zero-audio segment And a preset baseband value, wherein the zero-audio segment is an audio segment with a baseband value of zero; and acquiring a baseband value of the first filter segment, a baseband value of the second filter segment, and a preset baseband value.
  • the processor 181 is further configured to: obtain a base frequency value of the adjacent audio segments of the plurality of valid audio segments before acquiring a sum of durations of the audio segments whose baseband values are non-zero among the plurality of valid audio segments; Calculating the difference of the fundamental frequency values of the adjacent audio segments; if the difference satisfies the second condition, the base frequency value of the adjacent audio segments is set to zero.
  • the processor 181 is further configured to: combine the same note values in the note values, and generate a triplet corresponding to the plurality of valid audio segments; and combine the triples corresponding to the plurality of valid audio segments into The first triple sequence representing the note information.
  • the processor 181 is further configured to: acquire the same note value, a start time of the triplet corresponding to the plurality of valid audio segments, a duration of the triplet corresponding to the plurality of valid audio segments; and according to the same note value
  • the start time of the triplet corresponding to the plurality of valid audio segments and the duration of the triplet corresponding to the plurality of valid audio segments generate a triplet corresponding to the plurality of valid audio segments.
  • the processor 181 is further configured to perform the following steps: the first triplet sequence includes a first triplet and a second triplet, when the start time of the first triplet is equal to the start time of the second triplet When the sum of the durations of the second triad is combined, the first triad and the second triad are combined to obtain a third triad, and the first triad is deleted from the first triad sequence to obtain a second triad sequence; when the start time of the first triad is not equal to the sum of the start time of the second triad and the duration of the second triad, when the start of the fourth triad When the time is equal to the sum of the start time of the first triplet and the duration of the first triplet, the fourth triplet and the first triplet are merged to obtain the fifth triplet, and from the first three yuan
  • the first triplet is deleted from the group sequence to obtain a second triplet sequence; when the start time of the first triplet is not equal to the sum of the start time of
  • the processor 181 is further configured to: obtain the uploaded plurality of original clearing audio files; and obtain reply information for the plurality of original clearing audio files, wherein the reply information is used to indicate the quality level of the original clearing audio file; When the quality level indicated by the information reaches a predetermined level, the original captivating audio file is determined as a candidate clearing audio file.
  • the candidate clearing audio file is obtained; the plurality of valid audio segments are divided from the candidate clearing audio file; the note information of each valid audio segment is extracted, and the note information includes one or more triplets, each The triplet includes the start time of the note with the mapping relationship, The duration of the note, the note value of the note; a digital score file is generated based on the note information of each valid audio segment, wherein the digital score file includes some or all of the triplet, and the user corresponds to the song corresponding to the audio file of the candidate to sing
  • the clearing data generates a digital music score file, and achieves the purpose of automatically generating a digital music score file, thereby realizing the technical effect of improving the production efficiency of the clearing audio file, thereby solving the technical problem of low production efficiency of the digital music score file in the related art.
  • FIG. 18 is only schematic, and the terminal can be a smart phone (such as an Android mobile phone, an iOS mobile phone, etc.), a tablet computer, a palm computer, and a mobile Internet device (MID). Terminal equipment such as PAD.
  • FIG. 18 does not limit the structure of the above electronic device.
  • the terminal may also include more or less components (such as a network interface, display device, etc.) than shown in FIG. 18, or have a different configuration than that shown in FIG.
  • Embodiments of the present application also provide a storage medium.
  • the foregoing storage medium may store program code, where the program code is used to perform the steps in the method for generating a digital music score file of the song provided by the foregoing method embodiment.
  • the foregoing storage medium may be located in any one of the computer terminal groups in the computer network, or in any one of the mobile terminal groups.
  • the storage medium is set to be stored for performing the following steps. code:
  • Extracting note information of each valid audio segment wherein the note information includes one or more triplets, each triplet including a start time of a note having a mapping relationship, a duration of the note, and a note value of the note;
  • a digital score file is generated based on note information for each valid audio segment, wherein the digital score file includes some or all of the triples.
  • the storage medium is further configured to store program code for performing the following steps: acquiring a lyric file corresponding to the song, the lyric file including time information corresponding to each lyric; and time information corresponding to each lyric in the lyric file
  • the candidate chorus audio file divides a plurality of valid audio segments.
  • the storage medium is further configured to store program code for performing the steps of: extracting baseband information for each valid audio segment, wherein the baseband information includes a baseband value of the audio segment; and obtaining a baseband value of the plurality of valid audio segments The sum of the playback durations of the non-zero audio clips; if the sum of the playback durations exceeds the preset time, perform processing on each valid audio segment to obtain the baseband; obtain the baseband value in the baseband; perform notes on the baseband value Processing, obtaining the note value of the fundamental frequency value; and combining the note values to obtain note information of the valid audio segment.
  • the storage medium is further configured to store program code for performing the following steps: obtaining a length corresponding to each valid audio segment; performing a first filtering process on the valid audio segment having a length smaller than the first preset value, to obtain a first filtered segment; Performing a second filtering process on the audio segment whose length is greater than or equal to the first preset value, to obtain a second filtering segment; acquiring a fundamental frequency value of the first filtering segment and a fundamental frequency value of the second filtering segment.
  • the storage medium is also arranged to store program code for performing the following steps: After the length corresponding to the valid audio segment, if there is a zero audio segment in the effective audio segment whose length is less than the second preset value, the base frequency value of the zero audio segment is set to a preset baseband value, wherein the zero audio segment is the fundamental frequency An audio segment having a value of zero; obtaining a fundamental frequency value of the first filtered segment, a fundamental frequency value of the second filtered segment, and a preset fundamental frequency value.
  • the storage medium is further configured to store program code for performing the following steps: acquiring adjacent audio segments of the plurality of valid audio segments before acquiring a sum of durations of the audio segments having a non-zero fundamental frequency value in the plurality of valid audio segments The base frequency value; the difference of the fundamental frequency values of the adjacent audio segments is calculated; if the difference satisfies the second condition, the fundamental frequency value of the adjacent audio segments is set to zero.
  • the storage medium is further configured to store program code for performing the steps of: combining the same note values in the note values and generating a triplet corresponding to the plurality of valid audio segments; and three corresponding to the plurality of valid audio segments The tuples are combined into a first triplet sequence for representing note information.
  • the storage medium is further configured to store program code for performing the following steps: obtaining the same note value, a start time of the triplet corresponding to the plurality of valid audio segments, and a duration of the triplet corresponding to the plurality of valid audio segments; And generating a triple of the plurality of valid audio segments according to the same note value, the start time of the triple corresponding to the plurality of valid audio segments, and the duration of the triple corresponding to the plurality of valid audio segments.
  • the storage medium is also arranged to store program code for performing the steps of: the first triplet sequence comprising a first triplet and a second triplet, when the start time of the first triplet is equal to the second triplet When the start time of the group is the sum of the duration of the second triplet, the first triplet and the second triplet are combined to obtain a third triplet, and the first sequence is deleted from the first triplet sequence.
  • the triplet obtains the second triple sequence; when the start time of the first triple is not equal to the sum of the start time of the second triple and the duration of the second triple, when the fourth three
  • the fourth triplet and the first triplet are merged to obtain the fifth triplet, and Deleting the first triad from the first triad sequence to obtain a second triad sequence; when the starting time of the first triad is not equal to the starting time of the second triad and the second triad
  • the sum of the durations, and when the start time of the fourth triple is not equal to the first three When the start time of the tuple is equal to the duration of the first triplet, the first triplet is deleted from the first triplet sequence to obtain a second triplet sequence; and the second triplet sequence is obtained
  • the triplet in the output is output in a preset format to obtain a digital score file.
  • the storage medium is further configured to store program code for performing the steps of: acquiring the plurality of original clearing audio files uploaded; obtaining reply information for the plurality of original clearing audio files, wherein the reply information is used to represent the original clearing audio file. Quality level; if the quality level indicated by the reply message reaches a predetermined level, the original captivating audio file is determined as a candidate caps audio file.
  • the foregoing storage medium may include, but not limited to, a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, and a magnetic
  • ROM read-only memory
  • RAM random access memory
  • mobile hard disk a magnetic
  • magnetic A variety of media that can store program code, such as a disc or a disc.
  • the integrated unit in the above embodiment if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in the above-described computer readable storage medium.
  • the technical solution of the present application in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product, which is stored in a storage medium.
  • a number of instructions are included to cause one or more computer devices (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the disclosed client may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the candidate presenting audio file that satisfies the first condition is obtained from the clearing audio file corresponding to the song, wherein the candidate clearing audio file includes the clearing data of the user singing the song corresponding to the candidate clearing audio file;
  • the time information is divided into a plurality of valid audio segments from the candidate captivating audio file; the note information of each valid audio segment is extracted, the note information includes one or more triplets, and each triplet includes a note having a mapping relationship.

Abstract

一种歌曲的数字乐谱文件的生成方法、装置和存储介质。其中，该方法包括：从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件（S202），其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段（S204）；提取每个有效音频片段的音符信息（S206），其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及根据每个有效音频片段的音符信息生成数字乐谱文件（S208），其中，数字乐谱文件包括三元组中的部分或全部。解决了相关技术中数字乐谱文件的制作效率低的技术问题。

Description

歌曲的数字乐谱文件的生成方法、装置和存储介质
本申请要求于2016年09月09日提交中国专利局、优先权号为2016108161119、发明名称为“歌曲的数字乐谱文件的生成方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及计算机领域，具体而言，涉及一种歌曲的数字乐谱文件的生成方法、装置和存储介质。
背景技术
目前，数字乐谱文件的制作主要采用人工制作的方式，比如，音乐数字设备接口文件(Musical Instrument Digital Instrument，简称为MIDI)文件均采用人工制作的方式，数字乐谱文件在制作的过程中由于人工的参与，一方面造成数字乐谱文件的制作成本较大，另一方面制作完的数字乐谱文件也没有有效的方法对其质量进行检测，从而造成数字乐谱文件的制作效率比较低。
针对上述的相关技术中数字乐谱文件的制作效率低的技术问题，目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种歌曲的数字乐谱文件的生成方法、装置和存储介质，以至少解决相关技术中数字乐谱文件的制作效率低的技术问题。
根据本申请实施例的一个方面，提供了一种歌曲的数字乐谱文件的生成方法。该歌曲的数字乐谱文件的生成方法包括：从歌曲对应的清唱音频文件中获取满足第一条件的清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；根据歌曲的时间信息从候选清唱音频文件中 划分出多个有效音频片段；提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部。
根据本申请实施例的另一方面，还提供了一种歌曲的数字乐谱文件的生成装置。该歌曲的数字乐谱文件的生成装置包括：获取单元，被设置为从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；划分单元，被设置为根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；提取单元，被设置为提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及生成单元，被设置为根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部。
根据本申请实施例的另一方面，还提供了一种终端，其中，终端被设置为执行程序代码，程序代码用于执行本申请实施例的歌曲的数字乐谱文件的生成方法中的步骤。
根据本申请实施例的另一方面，还提供了一种存储介质，其中，存储介质被设置为存储程序代码，程序代码用于执行本申请实施例的歌曲的数字乐谱文件的生成方法中的步骤。
在本申请实施例中，从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；根据每个有效音频片段的音符信息生成数字乐谱文件，其 中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请实施例的一种歌曲的数字乐谱文件的生成方法的硬件环境的示意图；
图2是根据本申请实施例的一种歌曲的数字乐谱文件的生成方法的流程图；
图3是根据本申请实施例的一种根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段的方法的流程图；
图4是根据本申请实施例的一种提取每个有效音频片段的音符信息的方法的流程图；
图5是根据本申请实施例的一种对每个有效音频片段执行处理的方法的流程图；
图6是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图；
图7是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图；
图8是根据本申请实施例的一种合并音符值的方法的流程图；
图9是根据本申请实施例的一种生成多个有效音频片段对应的三元组 的方法的流程图；
图10是根据本申请实施例的一种根据每个有效音频片段的音符信息生成数字乐谱文件的方法的流程图；
图11是根据本申请实施例的一种获取候选清唱音频文件的方法的流程图；
图12是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图；
图13是根据本申请实施例的一种根据每个有效音频片段的音符信息生成数字乐谱文件的视化格式的示意图；
图14是根据本申请实施例的一种歌曲的数字乐谱文件的生成装置的示意图；
图15是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图；
图16是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图；
图17是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图；以及
图18是根据本申请实施例的一种终端的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
根据本申请实施例，提供了一种歌曲的数字乐谱文件的生成方法实施例。
可选地，在本实施例中，上述歌曲的数字乐谱文件的生成方法可以应用于如图1所示的由服务器102和终端104所构成的硬件环境中。图1是根据本申请实施例的一种歌曲的数字乐谱文件的生成方法的硬件环境的示意图。如图1所示，服务器102通过网络与终端104进行连接，上述网络包括但不限于：广域网、城域网或局域网，终端104并不限定于PC、手机、平板电脑等。本申请实施例的歌曲的数字乐谱文件的生成方法可以由服务器102来执行，也可以由终端104来执行，还可以是由服务器102和终端104共同执行。其中，终端104执行本申请实施例的歌曲的数字乐谱文件的生成方法也可以是由安装在其上的客户端来执行。
图2是根据本申请实施例的一种歌曲的数字乐谱文件的生成方法的流程图。如图2所示，该方法可以包括以下步骤：
步骤S202，从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件。
清唱音频文件包括用户对歌曲进行演唱的清唱数据。候选清唱音频文件为满足第一条件的清唱音频文件，其中，第一条件为用于在歌曲对应的清唱音频文件中筛选出候选清唱音频文件的筛选条件，也即，确定清唱音频文件是否达到候选标准，比如，大量的其他用户对上传的清唱音频文件 进行打分，多个清唱音频文件中的每个清唱音频文件都得到相应的分数，将第一条件设为分数高于预定分数阈值的条件，比如，在0～10分之间对清唱音频文件进行打分，将第一条件设为分数高于8分的条件，进而将分数高于预定分数阈值的清唱音频文件确定为候选清唱音频文件。可选地，大量的其他用户还可以对上传的清唱音频文件进行评价，比如，“满意”、“不满意”、“差评”、“一般”、“优秀”、“赞”等，将第一条件设为评价结果达到预定评价阈值的条件，比如，将第一条件设为评价结果达到10个“满意”、20个优秀、30个赞的条件，则将评价结果达到预定阈值的清唱音频文件确定为候选清唱音频文件。
可选地，上述第一条件除了包括上述筛选条件之外，还进一步包括人工筛选的条件，也即，上述筛选条件为第一条件中的初步筛选条件。比如，在确定上传的清唱音频文件达到上述初步筛选条件之后，由特定的制作人员对达到初步筛选条件的清唱音频文件进行试听，确定达到初步筛选条件的清唱音频文件的演唱音准是否准确，也即，确定对达到初步筛选条件的清唱音频文件进行演唱的用户的演唱音准是否达到可用标准。如果确定达到初步筛选条件的清唱音频文件的演唱音准准确，则确定上传的清唱音频文件为候选清唱音频文件。
在该实施例中，上述清唱音频文件包括用户对歌曲进行演唱的清唱数据，该清唱数据包括用户在演唱歌曲时所采集到的用户的声音数据，该声音数据包括用于指示用户的声音的音调的数据，用于指示用户的声音的音色的数据，用于指示用户的声音的响度的数据，用于指示用户的声音的乐音的数据等。该清唱音频文件还可以包括用户演唱某手歌曲的音准数据，该音准数据用于指示用户演唱某手歌曲的音高，以使特定的制作人员判断用户演唱歌曲是否准确。
可选地，判断歌曲是否存在对应的清唱音频文件，如果判断出歌曲中不存在对应的清唱音频文件，则发送用于请求上传清唱音频文件的上传请求。在发送上传请求之前，对接收上传请求的对象进行筛选。可以获取数 据库中存储的用户所演唱的歌曲的历史演唱数据。根据历史演唱数据确定用于表示用户演唱水平的等级数据，将等级数据达到预定等级阈值的用户确定为目标用户，优选将该目标用户对歌曲进行演唱所生成的清唱音频文件确定为候选清唱音频文件，则收录该目标用户的清唱音频文件的终端也即接收上传请求的对象。
在对接收上传请求的对象进行筛选时，还可以从数据库中获取对用户所演唱的歌曲进行评价的评价数据和对歌曲进行打分的打分数据，比如，评价数据包括用于指示“满意”、“不满意”、“差评”、“一般”、“优秀”、“赞”等数据，打分数据可以用于指示0～10分之间的打分数据。根据评价数据和打分数据确定用于表示用户演唱水平的等级数据，进而将等级数据达到预设等级阈值的用户确定为目标用户，获取该目标用户对歌曲进行演唱所生成的清唱音频文件。
可选地，待生成数字乐谱文件的歌曲为新歌，暂时没有用户对其进行演唱，则有奖邀请高水平的用户对新歌进行演唱以获取上述新歌对应的清唱音频文件。
步骤S204，根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段。
在本申请上述步骤S204提供的技术方案中，一首歌曲对应一个歌词文件，歌词文件包括每句歌词对应的时间信息。歌词文件中的每一句对应一个音频片段。可选地，将具有歌词且没有多余噪音的音频片段确定为候选清唱音频文件的有效音频片段。在获取候选清唱音频文件之后，从候选清唱音频文件中划分出多个有效音频片段，可选地，获取候选清唱音频文件对应的歌词文件中的每一句的时长信息，按照每一句歌词文件的时长信息对候选清唱音频文件进行划分，得到划分结果，并检测划分结果是否有多余的噪音，进而将没有歌词的部分去除掉，并且确保有效音频片段没有多余的噪音。
步骤S206，提取每个有效音频片段的音符信息。
在该实施例中，音符信息包括一个或多个三元组，从有效音频片段中可以提取出三元组。可以将每个有效音频片段执行处理，比如，对每个有效音频片段执行滤波处理，得到基频段，对基频段中的基频值进行音符化处理，得到基频值的音符值，然后将音符值进行合并，可以将音符值中的相同音符值的点连在一起，并生成每个有效音频片段对应的三元组，每个有效音频片段对应的三元组包括三元组的起始时间，三元组的音符值，三元组的持续时间。每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值。其中，音符的起始时间也即为三元组的起始时间，该起始时间的单位可以为毫秒，音符的持续时间也即为三元组的持续时间，该持续时间的单位可以为毫秒，音符的音符值也即为三元组的音符值。在从候选清唱音频文件中划分出多个有效音频片段之后，提取出每个有效音频片段的音符信息。
步骤S208，根据每个有效音频片段的音符信息生成数字乐谱文件。
数字乐谱文件包括三元组中的部分或全部。在提取每个有效音频片段的音符信息之后，根据音符的起始时间，音符的持续时间，音符的音符值生成数字乐谱文件。可选地，将音符信息中的多个三元组组成三元组序列，对三元组序列进行规整，得到数字乐谱文件。可选地，在对三元组序列进行规整时，可以将所有n个有效音频片段x1对应的三元组Wi连到一起，比如，直接将每一句对应的三元组起始时间s加上该句在整个歌曲中的起始时间而连到一起，得到整首歌曲对应的三元组序列Wa＝Oii∈[1，t]，其中，O用于表示三元组，i用于表示第i个，t用于表示此三元组序列的三元组总个数。当三元组满足以下(1)至(3)条件之一时(i>1and i<t)，则对Oi进行处理(其中mi为第i个三元组的音符值，mi-1为第i-1个三元组的音符值，mi+1为第i+1个三元组的音符值)：
(1)|mi-mi-1|≥6；
(2)|mi-mi+1|≥6；
(3)|mi-1-mi+1|≤3。
在对三元组进行处理时，在si＝si-1+li-1成立的情况下，合并第i-1与第i个二元组，也即，通过l'i-1＝li-1+li计算第i-1个三元组的持续时间l'i-1，并删除第i个三元组，其中，si为第i个三元组的起始时间，si-1为第i-1个三元组的起始时间，li-1为第i-1个三元组的持续时间，li为第i个三元组的持续时间；在si＝si-1+li-1不成立，si+1＝si+li成立的情况下，通过l'i+1＝li+1+li计算第i+1个三元组的持续时间l'i+1，通过s'i+1＝si计算第i+1个三元组的起始时间s'i+1，并删除第i个三元组的持续时间，其中，si+1为第i+1个三元组的起始时间，li+1为第i+1个三元组的持续时间；在si＝si-1+li-1不成立时，si+1＝si+li也不成立的情况下，直接删除第i个三元组，从而将三元组序列进行规整，将规整后的三元组序列生成数字乐谱文件。
在得到数字乐谱文件之后，按照预设格式输出数字乐谱文件。可选地，对数字乐谱文件进行质量检测，比如，保留质量检测合格的数字乐谱文件，删除质量检测不合格的数字乐谱文件，从而降低了人工对数字乐谱文件的制作成本，提高了数字乐谱文件的制作效率。
可选地，该数字乐谱文件为MIDI文件，从而通过上述步骤有效地降低了制作MIDI文件的人工成本，并且提高了MIDI文件的制作质量，提高了MIDI文件的制作效率。
可选地，该实施例从歌曲对应的清唱音频文件中获取的候选清唱音频文件可以为一个，也可以为多个。当候选音频文件为多个候选音频文件时，根据歌曲的时间信息对每个候选清唱音频文件进行划分，得到每个候选清唱音频文件的多个有效音频片段，根据每个候选清唱音频文件对应的多个有效音频片段的音符信息生成每个候选清唱音频文件对应的数字乐谱文件，每个候选清唱音频文件对应的数字乐谱文件可以为MIDI文件。可选地，每个候选清唱音频文件对应的数字乐谱文件可以由用户自主选择，将选择到的候选清唱音频文件对应的数字乐谱文件确定为该歌曲最终的数字乐谱文件，也可以对每个候选清唱音频文件对应的数字乐谱文件进行质量检测，得到质量检测结果，将质量检测结果最高的数字乐谱文件确定为 该歌曲最终的数字乐谱文件。
通过上述步骤S202至步骤S208，通过从歌曲对应的清唱音频文件中获取满足第一条件的清唱音频文件；根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及根据每个有效音频片段的音符信息生成数字乐谱文件，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，避免了通过人工制作数字乐谱文件的高成本，从而实现了提高数字乐谱文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。
作为一种可选的实施方式，步骤S204，根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段，通过根据歌词文件中每句歌词对应的时间信息将将候选清唱音频文件中划分出多个有效音频片段进行实现。
图3是根据本申请实施例的一种根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段的方法的流程图。如图3所示，该方法包括以下步骤：
步骤S301，获取歌曲对应的歌词文件。
在该实施例中，一首歌曲对应一个歌词文件，获取歌曲对应的歌词文件，该歌词文件包括每句歌词对应的时间信息。
候选清唱音频文件自带歌词文件，根据候选清唱音频文件自带的歌词文件获取候选清唱音频文件中每个音频片段的播放时长，歌词文件中包括用于指示播放时长的指示信息，也即，通过指示信息可以确定歌词文件中的每个音频片段在播放过程中的播放时长。
步骤S302，根据歌词文件中每句歌词对应的时间信息将候选清唱音 频文件划分出多个有效音频片段。
具体的，每句歌词对应时间信息即为候选清唱音频文件中每个音频片段的播放时长。在获取歌曲对应的歌词文件之后，由歌词文件中每句歌词对应的时间信息确定候选清唱音频文件中的多个音频片段，每个音频片段与歌词文件中的每句歌词相对应。举例而言，歌词文件中第一句歌词对应的时间信息为1～8秒，第二句歌词对应的时间信息为1～10秒，第三句歌词对应的时间信息为1～6秒，则由1～8秒划分出候选清唱音频文件中的第一音频片段，该第一音频片段与第一句歌词相对应，由1～10秒划分出候选音频文件中的第二音频片段，该第二音频片段与第二句歌词相对应，由1～6秒划分出候选音频文件中的第三音频片段，该第三音频片段与第三句歌词相对应。
可选地，获取候选清唱音频文件中的原始音频数据，根据每句歌词对应的时间信息对原始音频数据进行划分，得到多个音频片段，将每个音频片段中没有歌词的部分去掉，并且去除掉具有多余噪音的部分，从而从多个有效音频片段中提取多个有效音频片段，进而实现了根据歌词文件中每句歌词对应的时间信息将候选清唱音频文件划分出多个有效音频片段的目的。
该实施例通过获取歌曲对应的歌词文件，根据歌词文件中每句歌词对应的时间信息将候选清唱音频文件划分出多个有效音频片段，从而实现了根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段的目的，进而达到了提高数字乐谱文件的制作效率的技术效果。
作为一种可选的实施方式，步骤S206，提取每个有效音频片段的音符信息包括：在多个有效音频片段中基频值为非零的音频片段的播放时长之和超过预设时间的情况下，对每个有效音频片段执行处理，得到基频段，通过对基频段中的基频值执行音符化处理得到的音符值进行合并，以实现对有效音频片段的音符信息的提取。
图4是根据本申请实施例的一种提取每个有效音频片段的音符信息的 方法的流程图。如图4所示，该方法包括以下步骤：
步骤S401，提取每个有效音频片段的基频信息。
基频信息包括音频片段的基频值。在从候选清唱音频文件中划分出多个有效音频片段之后，提取每个有效音频片段的基频信息，该基频信息可以为帧移为10毫秒，帧长为30毫秒的基频，该基频信息包括音频片段的基频值。由于人们在发声时带振动产生的频率经过声道过滤后会产生大量的泛音，为了便于后续对候选清唱音频文件的处理，需要从音频信息中提取直接表现声带振动频率的基音，该基音也决定了整个音符的音高，也即，基频值。
步骤S402，获取多个有效音频片段中基频值为非零的音频片段的播放时长之和。
在提取每个有效音频片段的基频信息之后，获取每个有效音频片段的基频值，再从多个有效音频片段中提取有效音频值为非零的音频片段，比如，多个有效音频片段包括音频片段1、音频片段2、音频片段3和音频片段4，其中，音频片段1和音频片段2为音频值为非零的音频片段，音频片段3和音频片段4为音频值为零的音频片段，则从音频片段1、音频片段2、音频片段3和音频片段4中提取音频片段1和音频片段2。在从多个音频片段中提取出音频值为非零的音频片段之后，获取基频值为非零的音频片段的播放时长，对基频值为非零的音频片段的播放时长进行求和计算，得到基频值为非零的音频片段的播放时长之和，比如，在从上述音频片段1、音频片段2、音频片段3和音频片段4中提取出音频片段1和音频片段2之后，分别获取音频片段1和音频片段2的播放时长，比如，音频片段1的播放时长为2秒，音频片段2的播放时长为3秒，则对音频片段1的播放时长2秒和音频片段2的播放时长3秒进行求和计算，得到基频值为非零的音频片段的播放时长5秒。
可选地，在从多个有效音频片段中获取上述基频值为非零的音频片段时，可以获取多个有效音频片段中相邻有效音频片段的基频值，在相邻有 效音频片段的基频值的差值满足一定条件时，比如，相邻有效音频片段的基频值的差值小于预定差值，则将相邻的有效音频片段的基频值置零，也即，根据有效音频片段中前后基频点的基频值的差异来检测奇异基频点，并将奇异基频点置零，使得该相邻的有效音频片段为基频值为零的音频片段。
步骤S403，判断播放时长之和是否超过预设时间。
在获取多个有效音频片段中基频值为非零的有效音频片段在播放时的播放时长之和之后，判断播放时长之和是否超过预设时间，其中，预设时间可以为10秒，判断基频值为非零的有效音频片段的播放时长之和是否超过10秒。
在判断播放时长之和是否超过预设时间之后，如果判断出播放时长未超过预设时间，也即，基频值为非零的音频片段的播放时长之和比较短，则确定有效音频片段未过关，不能用于得到基频段；或者，重新提取每个有效音频片段的基频信息，获取多个有效音频片段中基频值为非零的音频片段的播放时长之和，再次判断播放时长之和是否超过预设时间，如果播放时长仍未超过预设时间，则直接确定有效音频片段未过关，不能用于得到基频段；或者，不对有效音频片段进行处理。
步骤S404，对每个有效音频片段执行处理，得到基频段。
在判断播放时长之和是否超过预设时间之后，如果判断出播放时长之和超过预设时间，对每个有效音频片段执行处理，得到基频段，也即，分别对多个有效音频片段执行处理，得到基频段。可选地，对每个有效音频片段执行滤波处理，得到基频段。在播放时长之和超过预设时间的情况下，对每个有效音频片段执行处理，这样得到的基频段由于播放时长之和较长，可以将基频段中的基频值进行音符化处理，得到基频值的音符值，可以很好地划分包括有起始时间、音符值和持续时间的三元组，从而可以准确得到有效音频片段的音符信息，达到提取每个有效音频片段的音符信息的目的，进而根据每个有效音频片段的音符信息生成数字乐谱文件，达到提高 清唱音频文件的制作效率的效果。
步骤S405，获取基频段中的基频值。
在对有效音频片段执行处理，得到基频段之后，获取基频段中的基频值。可选地，将基频段中小于预设帧数的零基频段值设置为基频段最后一帧基频值，比如，将基频段后面小于15帧的零基频段的基频值都置为基频段最后一帧基频值。
步骤S406，对基频值执行音符化处理，得到基频值的音符值。
在获取基频段中的基频值之后，对基频值进行符号化处理，比如，通过公式
Figure PCTCN2017101008-appb-000001
计算基频值的音符值f(x)，其中，x为基频段的基频值。可选地，对基频段中的全部基频值进行音符化，得到音符值。
步骤S407，合并音符值，得到有效音频片段的音符信息。
在对基频值执行音符化处理，得到基频值的音符值之后，合并音符值，将音符值相同的点连在一起，这样就得到一个三元组序列W＝Oii，i∈[1，k]，其中O为三元组(s，m，l)，其中s为该三元组的起始时间(单位为毫秒)、m为该三元组的音符值、l为该三元组的持续时间(单位为毫秒)，k为三元组序列包括的三元组个数，从而得到有效音频片段的音符信息。
该实施例通过提取每个有效音频片段的基频信息，其中，基频信息包括音频片段的基频值；获取多个有效音频片段中基频值为非零的音频片段的播放时长之和；如果播放时长之和超过预设时间，对每个有效音频片段执行处理，得到基频段；获取基频段中的基频值；对基频值执行音符化处理，得到基频值的音符值；以及合并音符值，得到有效音频片段的音符信息，实现了提取每个有效音频片段的音符信息的目的，进而达到了提高清唱音频文件的制作效率的效果。
作为一种可选的实施方式，步骤S404，对每个有效音频片段执行处理包括：根据音频片段对应的长度对音频片段执行滤波处理，得到滤波片段，获取滤波片段的基频值。
图5是根据本申请实施例的一种对每个有效音频片段执行处理的方法的流程图。如图5所示，该方法包括以下步骤：
步骤S501，获取每个有效音频片段对应的长度。
该实施例中的音频片段对应的长度，也即，基频段长度，单位为帧。如果判断出播放时长之和超过预设时间，获取每个有效音频片段对应的长度。
步骤S502，对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段。
在获取每个有效音频片段对应的长度之后，判断每个有效音频片段对应的长度是否小于第一预设值，对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段，比如，第一预设值为35帧，对基频段长度小于35帧的有效音频片段直接进行窗长为基频段长度的中值滤波，得到第一滤波片段。
步骤S503，对长度大于等于第一预设值的有效音频片段执行第二滤波处理，得到第二滤波片段。
在获取每个有效音频片段对应的长度之后，判断每个有效音频片段对应的长度是否小于第一预设值，对长度大于等于第一预设值的音频片段执行第二滤波处理，得到第二滤波片段，比如，第一预设值为35帧，对基频段长度大于等于35帧的音频片段，每帧做10点的中值滤波，得到第二滤波片段。
在该实施例中，中值滤波用于对有效音频片段中的噪声信号进行滤除，并且在滤除噪声信号的同时，能够保护有效音频片段的信号边缘，使之不被模糊。在对有效音频片段进行中值滤波时，设定窗长，将窗长中的音频 片段的数据设为中值滤波的信号样本值，将信号样本值按照从小到大的顺序进行排列，这样排序后的数据的中值，便为中值滤波的输出值。
举例而言，在对基频段长度大于等于35帧的音频片段，每帧做10点的中值滤波时，设定窗长为10个点，也即，对长度大于等于第一预设值的有效音频片段的每帧音频片段中的10个数据进行中值滤波，将窗长中的10个数据设为中值滤波的信号样本值，将信号样本值按照从小到大的顺序进行排列，这样排序后的数据的中值，便为中值滤波的输出值，从而得到第二滤波片段。
可选地，获取基频段中的基频值包括：获取第一滤波片段的基频值和第二滤波片段的基频值。
该实施例通过获取每个有效音频片段对应的长度；对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段；对长度大于等于第一预设值的音频片段执行第二滤波处理，得到第二滤波片段，达到了对每个有效音频片段执行处理的目的，进而达到了提高数字乐谱文件的制作效率的目的。
作为一种可选的实施方式，在获取每个有效音频片段对应的长度之后，在长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值。
图6是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图。如图6所示，该方法还包括以下步骤：
步骤S601，判断长度小于第二预设值的有效音频片段中是否存在零音频片段。
在获取每个有效音频片段对应的长度之后，判断长度小于第二预设值的有效音频片段中是否存在零音频片段，其中，零音频片段为基频值为零的音频片段。
零音频片段为基频值为零的音频片段，第二预设值可以为15帧，判 断长度小于15帧的音频片段中是否存在零音频片段。
步骤S602，将零音频片段的基频值设置为预设基频值。
在判断长度小于第二预设值的有效音频片段中存在零音频片段之后，如果判断出长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值，可选地，预设基频值为基频段最后一帧基频值，可以将基频段后面小于15帧的零基频片段的基频值都置为基频段最后一帧基频值。
可选地，获取基频段中的基频值包括：获取第一滤波片段的基频值、第二滤波片段的基频值和预设基频值。
该实施例通过在获取每个有效音频片段对应的长度之后，判断长度小于第二预设值的有效音频片段中是否存在零音频片段，其中，零音频片段为基频值为零的音频片段；如果判断出长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值；获取第一滤波片段的基频值、第二滤波片段的基频值和预设基频值，达到了对每个有效音频片段执行处理的目的，进而达到了提高清唱音频文件的制作效率的目的。
作为一种可选的实施方式，在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，通过在相邻音频片段的基频值的差值满足第二条件的情况下，将相邻音频片段的基频值置零。
图7是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图。如图7所示，该方法还包括以下步骤：
步骤S701，获取多个有效音频片段中相邻音频片段的基频值。
在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，获取多个有效音频片段中相邻音频片段的基频值。
步骤S702，计算相邻音频片段的基频值的差值。
在获取多个有效音频片段中相邻音频片段的基频值之后，对相邻音频片段的基频值进行计算，得到相邻音频片段的基频值的差值。
步骤S703，判断差值是否满足第二条件。
在计算相邻音频片段的基频值的差值之后，判段差值是否满足第二条件，该第二条件可以是差值小于预定差值的条件，为用于检测奇异基频点的条件，根据前后基频点的基频值的差值检测奇异基频点。
步骤S704，将相邻音频片段的基频值置零。
如果判断出差值满足第二条件，则根据前后基频点的基频值的差值确定出奇异基频点，将相邻音频片段的基频值置零。
该实施例通过在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，获取多个有效音频片段中相邻音频片段的基频值；计算相邻音频片段的基频值的差值；判断差值是否满足条件；如果判断出差值满足第二条件，将相邻音频片段的基频值置零，实现了对音频片段进行置零处理的操作，进而提高了清唱音频文件的制作效率。
作为一种可选的实施方式，步骤S407，合并音符值，得到有效音频片段的音符信息包括：根据音符值中的相同音符值生成多个有效音频片段对应的三元组，将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列。
图8是根据本申请实施例的一种合并音符值的方法的流程图。如图8所示，该方法包括以下步骤：
步骤S801，将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组。
获取音符值中的相同音符值，将相同音符值的点连在一起，并生成多个有效音频片段对应的三元组，多个有效音频片段对应的三元组包括三元组的起始时间，三元组的音符值，三元组的持续时间。
步骤S802，将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列。
在将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组之后，将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列。
该实施例通过将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组；以及将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列，实现了合并音符值，得到有效音频片段的音符信息的目的。
作为一种可选的实施方式，步骤S801，生成多个有效音频片段对应的三元组包括：根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组。
图9是根据本申请实施例的一种生成多个有效音频片段对应的三元组的方法的流程图。如图9所示，该方法包括以下步骤：
步骤S901，获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间。
该实施例在生成多个有效音频片段对应的三元组时，获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间。
步骤S902，根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组。
在获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间之后，根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的 持续时间生成多个有效音频片段对应的三元组。
该实施例通过获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间；根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组，达到了生成多个有效音频片段对应的三元组的目的，进而提高了清唱音频文件的制作效率。
作为一种可选的实施方式，第一三元组序列包括第一三元组和第二三元组，步骤S208，根据每个有效音频片段的音符信息生成数字乐谱文件包括在不同条件下得到第二三元组序列，将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
图10是根据本申请实施例的一种根据每个有效音频片段的音符信息生成数字乐谱文件的方法的流程图。如图10所示，该方法包括以下步骤：
步骤S1001，合并第一三元组和第二三元组，得到第三三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列。
获取第一三元组的起始时间，第二三元组的起始时间和第二三元组的持续时间，当第一三元组的起始时间等于第二三元组的起始时间与第二三元组的持续时间之和时，合并第一三元组和第二三元组，得到第三三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列。
步骤S1002，合并第四三元组和第一三元组，得到第五三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列。
获取第四三元组的起始时间，当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，当第四三元组的起始时间等于第一三元组的起始时间与第一三元组的持续时间之和时，合并第四三元组和第一三元组，得到第五三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列。
步骤S1003，从第一三元组序列中删除第一三元组，得到第二三元组 序列。
当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，且当第四三元组的起始时间不等于第一三元组的起始时间与第一三元组的持续时间之和时，从第一三元组序列中删除第一三元组，得到第二三元组序列。
步骤S1004，将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
在通过步骤S1001、步骤S1002、步骤S1003不同条件下得到的第二三元组之后，将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
作为一种可选的实施方式，当si＝si-1+li-1成立时，通过l'i-1＝li-1+li计算第三三元组的持续时间l'i-1，其中，si为第一三元组的起始时间，si-1为第二三元组的起始时间，li-1为第二三元组的持续时间，li为第一三元组的持续时间；当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算第五三元组的持续时间l'i+1，通过s'i+1＝si计算第五三元组的起始时间s'i+1，其中，si+1为第四三元组的起始时间，li+1为第四三元组的持续时间。
作为一种可选的实施方式，步骤S202，从歌曲对应的清唱音频文件中获取候选清唱音频文件包括：获取对多个原始清唱音频文件的回复信息，在回复信息所表示的质量等级达到预定等级的情况下，将原始清唱音频文件确定为候选清唱音频文件。
图11是根据本申请实施例的一种获取候选清唱音频文件的方法的流程图。如图11所示，该获取候选清唱音频文件的方法包括以下步骤：
步骤S1101，获取上传的多个原始清唱音频文件。
原始清唱音频文件可以为用户演唱歌曲上传的清唱音频文件，获取上传的多个原始清唱音频文件。
步骤S1102，获取对多个原始清唱音频文件的回复信息。
在获取上传的多个原始清唱音频文件之后，获取对多个原始清唱音频文件的回复信息，该回复信息用于表示原始清唱音频文件的质量等级，可以为用户演唱歌曲在上传之后，其他用户对其作品进行打分和/或评价，通过打分和/或评价从而确定质量等级。
步骤S1103，判断回复信息所表示的质量等级是否达到预定等级。
在获取对多个原始清唱音频文件的回复信息之后，判断回复信息所表示的质量等级是否达到预定等级。
步骤S1104，将原始清唱音频文件确定为候选清唱音频文件。
如果判断出回复信息所表示的质量等级达到预定等级，则将原始清唱音频文件确定为候选清唱音频文件。可选地，如果判断出回复信息所表示的质量等级未达到预定等级，则不将原始清唱音频文件确定为候选清唱音频文件。
可选地，当用户评价达到某一阈值后，比如，当得到大于等于32个“赞”时，则认为此用户演唱歌曲达到候选标准，将原始清唱音频文件确定为候选清唱音频文件。
该实施例通过获取上传的多个原始清唱音频文件；获取对多个原始清唱音频文件的回复信息，回复信息用于表示原始清唱音频文件的质量等级；判断回复信息所表示的质量等级是否达到预定等级；以及如果判断出回复信息所表示的质量等级达到预定等级，则将原始清唱音频文件确定为候选清唱音频文件，达到了获取候选清唱音频文件的目的。
作为一种可选的实施方式，确定原始清唱音频文件为候选清唱音频文件包括：在判断出评价指标符合预设评价指标的情况下，获取原始清唱音频文件的音准数据；判断音准数据是否符合预设音准；以及如果判断出音准数据符合预设音准，确定原始清唱音频文件为候选清唱音频文件，实现了度候选清唱音频文件的获取。
可选地，在获取候选清唱音频文件之后，将候选清唱音频文件的格式调整为预设格式，比如，将候选清唱音频文件的格式调整为16k16bit pcm格式，以得到调整清唱音频文件，根据歌曲的时间信息从调整清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息；以及根据每个有效音频片段的音符信息生成数字乐谱文件，达到了自动生成数字乐谱文件的目的。
该实施例通过获取候选清唱音频文件，候选清唱音频文件包括用户候选清唱音频文件对应的歌曲进行演唱的清唱数据；从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。
下面结合优选的实施例对本申请的技术方案进行说明。
图12是根据本申请实施例的另一种歌曲的数字乐谱文件的生成方法的流程图。如图12所示，该包括以下步骤：
步骤S1201，基于用户评价选取候选用户演唱歌曲。
在上传用户演唱的歌曲的清唱音频文件之后，会有大量其他用户对上传的清唱音频文件进行打分和/或评价，当打分和/或评价达到某一阈值y后，则认为此用户演唱的歌曲达到候选标准，再由制作人员进行试听，确定用户演唱音准是否达到可用的标准，如果达到可用的标准则执行步骤S1202。
可选地，如果要生成清唱音频文件的歌曲为新歌，暂时没有人演唱， 则有奖邀请资深高水平的用户演唱，即可生成清唱音频文件。
步骤S1202，根据歌词文件提取有效数据段。
歌曲自带的歌词文件包含了每一句歌曲的时长信息，通过此时长信息将原始音频数据按照每一句的时间进行切割，将没有歌词的部分去除掉，确保无效部分没有多余的噪音，这样就得到一系列的音频片段{x1，x2...xn}，其中n为歌词文件中的句子的个数。
步骤S1203，音符提取。
将用户上传的清唱音频文件调整为16k16bit pcm格式。提取该音频的基频信息(帧移10ms，帧长30ms)，由于人在发声时声带振动产生的频率经过声道过滤后会产生大量泛音，为了便于后续操作，需要从音频中提取直接表现声带振动频率的基音，基音也决定了整个音符的音高。根据与前后基频点基频值的差异检测奇异基频点，并置零。判断基频值非零的段落时间之和是否超过10秒，如果低于10秒则直接判定为未过关。在基频值非零的段落时间之和超过10秒的情况下，当有效音频片段的长度小于35帧时，直接进行窗长为基频段长度的中值滤波，得到基频段；当有效音频片段的长度大于等于35帧时，每帧做10点中值滤波，得到基频段。对基频段后面小于15帧的零基频段的基频值都置为基频段最后一帧基频值，从而实现了零基频点填充。
在获取基频段中的基频值之后，对基频值进行符号化处理，比如，通过公式
Figure PCTCN2017101008-appb-000002
计算基频值的音符值f(x)，其中，x为基频段的基频值。可选地，对基频段中的全部基频值进行音符化，得到音符值。
合并得到的音符值，将得到的音符值相同的点连在一起，这样就得到一个三元组序列W＝Oii，i∈[1，k]，其中O为三元组(s，m，l)，其中s为该 三元组的起始时间(单位为毫秒)、m为该三元组的音符值、l为该三元组的持续时间(单位为毫秒)，k为三元组此句话对应的三元组个数，从而得到有效音频片段的音符信息。
步骤S1204，后端规整。
将所有n个单句音频片段x1对应的三元组Wi连到一起，直接将每一句对应的三元组起始时间s加上该句在整个歌曲中的起始时间即可，得到整首歌对应的三元组序列Wa＝Oii∈[1，t]，其中，i用于表示第i个，t为此三元组序列的三元组个数。去奇异音符，当三元组满足以下(1)至(3)条件之一时(i>1and i<t)，则对三元组Oi进行特殊处理(其中mi为第i个三元组的音符值，mi-1为第i-1个三元组的音符值，mi+1为第i+1个三元组的音符值)：
(1)|mi-mi-1|≥6；
(2)|mi-mi+1|≥6；
(3)|mi-1-mi+1|≤3。
对三元组进行处理：
当si＝si-1+li-1成立时，则合并第i-1与第i个二元组，也即，通过l'i-1＝li-1+li计算第i-1个三元组的持续时间l'i-1，并删除第i个三元组，其中，si为第i个三元组的起始时间，si-1为第i-1个三元组的起始时间，li-1为第i-1个三元组的持续时间，li为第i个三元组的持续时间。
当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算第i+1个三元组的持续时间l'i+1，通过s'i+1＝si计算第i+1个三元组的起始时间s'i+1，并删除第i个三元组的持续时间，其中，si+1为第i+1个三元组的起始时间，li+1为第i+1个三元组的持续时间。
当si＝si-1+li-1不成立时，si+1＝si+li也不成立时，直接删除第i个三元组。
本申请实施例通过候选清唱音频文件生成数字乐谱文件，其中，候选清唱音频文件包括用户对候选清唱音频文件对应的歌曲进行演唱的清唱数据，从而使用户的声音自动生成数字乐谱文件，而不需要人工制作，降低了数字乐谱文件制作的成本，提高了数字乐谱文件制作的效率。
本申请实施例的应用环境可以但不限于参照上述实施例中的应用环境，本实施例中对此不再赘述。本申请实施例提供了用于实施上述信息获取、传输方法的一种可选的具体应用。
图13是根据本申请实施例的一种根据每个有效音频片段的音符信息生成数字乐谱文件的视化格式的示意图。如图13所示，数字乐谱文件的视化格式为将三元组序列按照每一行(例如，36000 150 55)表示一个三元组，第一列(例如，36000 36150 36200 36330 36960)为音符的起始时间(单位ms)，第二列(例如，150 50 130 630 30)为音符持续时间(单位ms)，第三列(例如，55 56 57 56 55)为音符的音符值。
在全民k歌应用中，每一首可供演唱的歌曲都会有一个对应的MIDI文件，此文件描述了原唱歌手演绎此歌曲的音高走势。此文件则为可以使用的MIDI文件，其作用有很多，比如，给用户提供可视化音高参考曲线、对于用户不足之处进行修音、对用户演唱进行评价等，之前MIDI文件均采用人工制作的方式，这样一方面人工成本较大，另一方面制作完的MIDI文件也没有有效的办法进行质量检测，而通过本申请实施例的获取候选清唱音频文件；从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
根据本申请实施例，还提供了一种用于实施上述歌曲的数字乐谱文件的生成方法的歌曲的数字乐谱文件的生成装置。图14是根据本申请实施例的一种歌曲的数字乐谱文件的生成装置的示意图。如图14所示，该装置可以包括：获取单元10、划分单元20、提取单元30和生成单元40。
获取单元10，被设置为从歌曲对应的清唱音频文件中获取满足第一条件的清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据。
划分单元20，被设置为根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段。
提取单元30，被设置为提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值。
生成单元40，被设置为根据每个有效音频片段的音符信息生成数字乐 谱文件，其中，数字乐谱文件包括三元组中的部分或全部。
此处需要说明的是，上述获取单元10、划分单元20、提取单元30和生成单元40可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
图15是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图。如图15所示，该装置可以包括：获取单元10、划分单元20、提取单元30和生成单元40。其中，划分单元20包括：第一获取模块21、划分模块22。
需要说明的是，该实施例的获取单元10、划分单元20、提取单元30和生成单元40与图14所示实施例的歌曲的数字乐谱文件的生成装置中的作用相同，此处不再赘述。
第一获取模块21，被设置为获取歌曲对应的歌词文件，歌词文件包括每句歌词对应的时间信息。
划分模块22，被设置为根据歌词文件中每句歌词对应的时间信息将候选清唱音频文件划分为多个有效音频片段。
此处需要说明的是，上述第一获取模块21和划分模块22可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
图16是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图。如图16所示，该装置可以包括：获取单元10、划分单元20、提取单元30和生成单元40，提取单元30包括：提取模块31、第二获取模块32、判断模块33、第一处理模块34、第三获取模块35、第二处理模 块36和合并模块37。
需要说明的是，获取单元10、划分单元20、提取单元30和生成单元40与图14所示实施例的歌曲的数字乐谱文件的生成装置中的作用相同，此处不再赘述。
提取模块31，被设置为提取每个有效音频片段的基频信息，其中，基频信息包括音频片段的基频值。
第二获取模块32，被设置为获取多个有效音频片段中基频值为非零的音频片段的播放时长之和。
判断模块33，被设置为判断播放时长之和是否超过预设时间。
第一处理模块34，被设置为在判断出播放时长之和超过预设时间时，对每个有效音频片段执行处理，得到基频段。
可选地，在判断播放时长之和是否超过预设时间之后，如果判断出播放时长未超过预设时间，也即，基频值为非零的音频片段的播放时长之和比较短，则确定有效音频片段未过关，不能用于得到基频段；或者，重新提取每个有效音频片段的基频信息，获取多个有效音频片段中基频值为非零的音频片段的播放时长之和，再次判断播放时长之和是否超过预设时间，如果播放时长仍未超过预设时间，则直接确定有效音频片段未过关，不能用于得到基频段；或者，不对有效音频片段进行处理。
第三获取模块35，被设置为获取基频段中的基频值。
第二处理模块36，被设置为对基频值执行音符化处理，得到基频值的音符值。
合并模块37，被设置为合并音符值，得到有效音频片段的音符信息。
此处需要说明的是，上述提取模块31、第二获取模块32、判断模块33、第一处理模块34、第三获取模块35、第二处理模块36和合并模块37可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上 述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选地，该歌曲的数字乐谱文件的生成装置还包括：计算单元、第一判断单元和置零单元。其中，获取单元10被设置为在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，获取多个有效音频片段中相邻音频片段的基频值；计算单元被设置为计算相邻音频片段的基频值的差值；第一判断单元被设置为判断差值是否满足条件；置零单元被设置为在判断出差值满足第二条件时，将相邻音频片段的基频值置零。
此处需要说明的是，上述计算单元、第一判断单元和置零单元可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述单元实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选地，合并模块37包括生成模块和组合模块。其中，生成模块，被设置为将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组；组合模块被设置为将多个有效音频片段对应的三元组组合成被设置为表示音符信息的第一三元组序列。
此处需要说明的是，上述生成模块和组合模块可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选地，生成模块被设置为获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间，以及根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组。
可选地，第一三元组序列包括第一三元组和第二三元组，生成单元40被设置为当第一三元组的起始时间等于第二三元组的起始时间与第二三元组的持续时间之和时，合并第一三元组和第二三元组，得到第三三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，当第四三元组的起始时间等于第一三元组的起始时间与第一三元组的持续时间之和时，合并第四三元组和第一三元组，得到第五三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，且当第四三元组的起始时间不等于第一三元组的起始时间与第一三元组的持续时间之和时，从第一三元组序列中删除第一三元组，得到第二三元组序列；以及将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
可选地，当si＝si-1+li-1成立时，通过l'i-1＝li-1+li计算第三三元组的持续时间l'i-1，其中，si为第一三元组的起始时间，si-1为第二三元组的起始时间，li-1为第二三元组的持续时间，li为第一三元组的持续时间；当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算第五三元组的持续时间l'i+1，通过s'i+1＝si计算第五三元组的起始时间s'i+1，其中，si+1为第四三元组的起始时间，li+1为第四三元组的持续时间。
图17是根据本申请实施例的另一种歌曲的数字乐谱文件的生成装置的示意图。如图17所示，该装置可以包括：获取单元10、划分单元20、提取单元30和生成单元40。其中，提取单元30包括：提取模块31、第二获取模块32、判断模块33、第一处理模块34、第三获取模块35、第二处理模块36和合并模块37，其中，第一处理模块34包括：获取子模块341、第一处理子模块342和第二处理子模块343。
需要说明的是，该实施例的获取单元10、划分单元20、提取单元30和生成单元40，提取模块31、第二获取模块32、判断模块33、第一处理 模块34、第三获取模块35、第二处理模块36和合并模块37与图16所示实施例的歌曲的数字乐谱文件的生成装置中的作用相同，此处不再赘述。
获取子模块341，被设置为获取每个有效音频片段对应的长度。
第一处理子模块342，被设置为对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段。
第二处理子模块343，被设置为对长度大于等于第一预设值的音频片段执行第二滤波处理，得到第二滤波片段。
第三获取模块35被设置为获取第一滤波片段的基频值和第二滤波片段的基频值。
此处需要说明的是，上述获取子模块341、第一处理子模块342和第二处理子模块343可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选地，该歌曲的数字乐谱文件的生成装置还包括：第二判断单元和设置单元。其中，第二判断单元，被设置为在获取每个有效音频片段对应的长度之后，判断长度小于第二预设值的有效音频片段中是否存在零音频片段，其中，零音频片段为基频值为零的音频片段；设置单元，被设置为在判断出长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值；第三获取模块35被设置为获取第一滤波片段的基频值、第二滤波片段的基频值和预设基频值。
此处需要说明的是，上述第二判断单元和设置单元可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
可选地，获取单元10包括第四获取模块、第五获取模块和确定模块。其中，第四获取模块，被设置为获取上传的多个原始清唱音频文件；第五获取模块被设置为获取对多个原始清唱音频文件的回复信息，其中，回复信息被设置为表示原始清唱音频文件的质量等级；确定模块，被设置为判断回复信息所表示的质量等级是否达到预定等级，在判断出回复信息所表示的质量等级达到预定等级时，则将原始清唱音频文件确定为候选清唱音频文件。
此处需要说明的是，上述第四获取模块、第五获取模块和确定模块可以作为装置的一部分运行在终端中，可以通过终端中的处理器来执行上述模块实现的功能，终端也可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌声电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。
需要说明的是，该实施例中的获取单元10可以被设置为执行本申请实施例1中的步骤S202，该实施例中的划分单元20可以被设置为执行本申请实施例1中的步骤S204，该实施例中的提取单元30可以被设置为执行本申请实施例1中的步骤S206，该实施例中的生成单元40可以被设置为执行本申请实施例1中的步骤S208。
在该实施例中，通过获取单元10从歌曲对应的清唱音频文件中获取满足第一条件的清唱音频文件，通过划分单元20根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段，通过提取单元30提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值，通过生成单元40根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问 题。
此处需要说明的是，上述单元和模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例1所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在如图1所示的硬件环境中，可以通过软件实现，也可以通过硬件实现，其中，硬件环境包括网络环境。
本申请实施例所提供的各个功能模块可以在移动终端、计算机终端或者类似的运算装置中运行，也可以作为存储介质的一部分进行存储。
由此，本申请的实施例可以提供一种终端，该终端可以是计算机终端群中的任意一个计算机终端设备。可选地，在本实施例中，上述终端也可以替换为移动终端等终端设备。
可选地，在本实施例中，上述终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
根据本申请实施例，还提供了一种用于实施上述歌曲的数字乐谱文件的生成方法的终端，其中，终端就可以为计算机终端，该计算机终端可以是计算机终端群中的任意一个计算机终端设备。可选地，在本实施例中，上述计算机终端也可以替换为移动终端等终端设备。
可选地，在本实施例中，上述计算机终端可以位于计算机网络的多个网络设备中的至少一个网络设备。
图18是根据本申请实施例的一种终端的结构框图。如图18所示，该终端可以包括：一个或多个(图中仅示出一个)处理器181、存储器183、以及传输装置185，如图18所示，该终端还可以包括输入输出设备187。
其中，存储器183可用于存储软件程序以及模块，如本申请实施例中的歌曲的数字乐谱文件的生成方法和装置对应的程序指令/模块，处理器181通过运行存储在存储器183内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的歌曲的数字乐谱文件的生成方法。存储器183可包括高速随机存储器，还可以包括非易失性存储器，如一个或 者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器183可进一步包括相对于处理器181远程设置的存储器，这些远程存储器可以通过网络连接至终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
上述的传输装置185用于经由一个网络接收或者发送数据，还可以用于处理器与存储器之间的数据传输。上述的网络具体实例可包括有线网络及无线网络。在一个实例中，传输装置185包括一个网络适配器(Network Interface Controller，NIC)，其可通过网线与其他网络设备与路由器相连从而可与互联网或局域网进行通讯。在一个实例中，传输装置185为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
其中，具体地，存储器183用于存储应用程序。
处理器181可以通过传输装置185调用存储器183存储的应用程序，以执行上述方法实施例中的各个可选或优选实施例的方法步骤的程序代码，包括：
从歌曲对应的清唱音频文件中获取满足第一条件的清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；
根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；
提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；
根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部。
处理器181还用于执行下述步骤：获取歌曲对应的歌词文件，歌词文件包括每句歌词对应的时间信息；根据歌词文件中每句歌词对应的时间信息将候选清唱音频文件划分出多个有效音频片段。
处理器181还用于执行下述步骤：提取每个有效音频片段的基频信息，其中，基频信息包括音频片段的基频值；获取多个有效音频片段中基频值为非零的音频片段的播放时长之和；如果播放时长之和超过预设时间，对每个有效音频片段执行处理，得到基频段；获取基频段中的基频值；对基频值执行音符化处理，得到基频值的音符值；以及合并音符值，得到有效音频片段的音符信息。
处理器181还用于执行下述步骤：获取每个有效音频片段对应的长度；对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段；对长度大于等于第一预设值的音频片段执行第二滤波处理，得到第二滤波片段；获取第一滤波片段的基频值和第二滤波片段的基频值。
处理器181还用于执行下述步骤：在获取每个有效音频片段对应的长度之后，如果长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值，其中，零音频片段为基频值为零的音频片段；获取第一滤波片段的基频值、第二滤波片段的基频值和预设基频值。
处理器181还用于执行下述步骤：在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，获取多个有效音频片段中相邻音频片段的基频值；计算相邻音频片段的基频值的差值；如果差值满足第二条件，将相邻音频片段的基频值置零。
处理器181还用于执行下述步骤：将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组；以及将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列。
处理器181还用于执行下述步骤：获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间；以及根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组。
处理器181还用于执行下述步骤：第一三元组序列包括第一三元组和第二三元组，当第一三元组的起始时间等于第二三元组的起始时间与第二三元组的持续时间之和时，合并第一三元组和第二三元组，得到第三三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，当第四三元组的起始时间等于第一三元组的起始时间与第一三元组的持续时间之和时，合并第四三元组和第一三元组，得到第五三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，且当第四三元组的起始时间不等于第一三元组的起始时间与第一三元组的持续时间之和时，从第一三元组序列中删除第一三元组，得到第二三元组序列；以及将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
处理器181还用于执行下述步骤：当si＝si-1+li-1成立时，通过l'i-1＝li-1+li计算第三三元组的持续时间l'i-1，其中，si为第一三元组的起始时间，si-1为第二三元组的起始时间，li-1为第二三元组的持续时间，li为第一三元组的持续时间；当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算第五三元组的持续时间l'i+1，通过s'i+1＝si计算第五三元组的起始时间s'i+1，其中，si+1为第四三元组的起始时间，li+1为第四三元组的持续时间。
处理器181还用于执行下述步骤：获取上传的多个原始清唱音频文件；获取对多个原始清唱音频文件的回复信息，其中，回复信息用于表示原始清唱音频文件的质量等级；如果回复信息所表示的质量等级达到预定等级，则将原始清唱音频文件确定为候选清唱音频文件。
在本申请实施例中，获取候选清唱音频文件；从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间， 音符的持续时间，音符的音符值；根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
本领域普通技术人员可以理解，图18所示的结构仅为示意，终端可以是智能手机(如Android手机、iOS手机等)、平板电脑、掌上电脑以及移动互联网设备(Mobile Internet Devices，MID)、PAD等终端设备。图18其并不对上述电子装置的结构造成限定。例如，终端还可包括比图18中所示更多或者更少的组件(如网络接口、显示装置等)，或者具有与图18所示不同的配置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令终端设备相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。
本申请的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以存储程序代码，所述程序代码用于执行上述方法实施例所提供的歌曲的数字乐谱文件的生成方法中的步骤。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的 程序代码：
从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，清唱音频文件包括用户对歌曲进行演唱的清唱数据；
根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；
提取每个有效音频片段的音符信息，其中，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；
根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部。
可选地，存储介质还被设置为存储用于执行以下步骤的程序代码：获取歌曲对应的歌词文件，歌词文件包括每句歌词对应的时间信息；根据歌词文件中每句歌词对应的时间信息将候选清唱音频文件划分出多个有效音频片段。
存储介质还被设置为存储用于执行以下步骤的程序代码：提取每个有效音频片段的基频信息，其中，基频信息包括音频片段的基频值；获取多个有效音频片段中基频值为非零的音频片段的播放时长之和；如果播放时长之和超过预设时间，对每个有效音频片段执行处理，得到基频段；获取基频段中的基频值；对基频值执行音符化处理，得到基频值的音符值；以及合并音符值，得到有效音频片段的音符信息。
存储介质还被设置为存储用于执行以下步骤的程序代码：获取每个有效音频片段对应的长度；对长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段；对长度大于等于第一预设值的音频片段执行第二滤波处理，得到第二滤波片段；获取第一滤波片段的基频值和第二滤波片段的基频值。
存储介质还被设置为存储用于执行以下步骤的程序代码：在获取每个 有效音频片段对应的长度之后，如果长度小于第二预设值的有效音频片段中存在零音频片段，将零音频片段的基频值设置为预设基频值，其中，零音频片段为基频值为零的音频片段；获取第一滤波片段的基频值、第二滤波片段的基频值和预设基频值。
存储介质还被设置为存储用于执行以下步骤的程序代码：在获取多个有效音频片段中基频值为非零的音频片段的时长之和之前，获取多个有效音频片段中相邻音频片段的基频值；计算相邻音频片段的基频值的差值；如果差值满足第二条件，将相邻音频片段的基频值置零。
存储介质还被设置为存储用于执行以下步骤的程序代码：将音符值中的相同音符值进行合并，并生成多个有效音频片段对应的三元组；以及将多个有效音频片段对应的三元组组合成用于表示音符信息的第一三元组序列。
存储介质还被设置为存储用于执行以下步骤的程序代码：获取相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间；以及根据相同音符值、多个有效音频片段对应的三元组的起始时间、多个有效音频片段对应的三元组的持续时间生成多个有效音频片段对应的三元组。
存储介质还被设置为存储用于执行以下步骤的程序代码：第一三元组序列包括第一三元组和第二三元组，当第一三元组的起始时间等于第二三元组的起始时间与第二三元组的持续时间之和时，合并第一三元组和第二三元组，得到第三三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，当第四三元组的起始时间等于第一三元组的起始时间与第一三元组的持续时间之和时，合并第四三元组和第一三元组，得到第五三元组，并从第一三元组序列中删除第一三元组，得到第二三元组序列；当第一三元组的起始时间不等于第二三元组的起始时间与第二三元组的持续时间之和时，且当第四三元组的起始时间不等于第一三 元组的起始时间与第一三元组的持续时间之和时，从第一三元组序列中删除第一三元组，得到第二三元组序列；以及将第二三元组序列中的三元组按照预设格式输出，得到数字乐谱文件。
存储介质还被设置为存储用于执行以下步骤的程序代码：当si＝si-1+li-1成立时，通过l'i-1＝li-1+li计算第三三元组的持续时间l'i-1，其中，si为第一三元组的起始时间，si-1为第二三元组的起始时间，li-1为第二三元组的持续时间，li为第一三元组的持续时间；当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算第五三元组的持续时间l'i+1，通过s'i+1＝si计算第五三元组的起始时间s'i+1，其中，si+1为第四三元组的起始时间，li+1为第四三元组的持续时间。
存储介质还被设置为存储用于执行以下步骤的程序代码：获取上传的多个原始清唱音频文件；获取对多个原始清唱音频文件的回复信息，其中，回复信息用于表示原始清唱音频文件的质量等级；如果回复信息所表示的质量等级达到预定等级，则将原始清唱音频文件确定为候选清唱音频文件。
可选地，本实施例中的具体示例可以参考上述实施例中所描述的示例，本实施例在此不再赘述。
可选地，在本实施例中，上述存储介质可以包括但不限于：U盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
如上参照附图以示例的方式描述了根据本申请的歌曲的数字乐谱文件的生成方法、装置和存储介质。但是，本领域技术人员应当理解，对于上述本申请所提出的歌曲的数字乐谱文件的生成方法、装置和存储介质，还可以在不脱离本申请内容的基础上做出各种改进。因此，本申请的保护范围应当由所附的权利要求书的内容确定。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
上述实施例中的集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在上述计算机可读取的存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在存储介质中，包括若干指令用以使得一台或多台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的客户端，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。
工业实用性
在本申请实施例中，从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，候选清唱音频文件包括用户对候选清唱音频文件对应的歌曲进行演唱的清唱数据；根据歌曲的时间信息从候选清唱音频文件中划分出多个有效音频片段；提取每个有效音频片段的音符信息，音符信息包括一个或多个三元组，每个三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；根据每个有效音频片段的音符信息生成数字乐谱文件，其中，数字乐谱文件包括三元组中的部分或全部，通过用户候选清唱音频文件对应的歌曲进行演唱的清唱数据生成数字乐谱文件，达到了自动生成数字乐谱文件的目的，从而实现了提高清唱音频文件的制作效率的技术效果，进而解决了相关技术中数字乐谱文件的制作效率低的技术问题。

Claims (17)

  1. 一种歌曲的数字乐谱文件的生成方法，包括：
    从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，所述清唱音频文件包括用户对所述歌曲进行演唱的清唱数据；
    根据所述歌曲的时间信息从所述候选清唱音频文件中划分出多个有效音频片段；
    提取每个所述有效音频片段的音符信息，其中，所述音符信息包括一个或多个三元组，每个所述三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及
    根据每个所述有效音频片段的音符信息生成数字乐谱文件，其中，所述数字乐谱文件包括所述三元组中的部分或全部。
  2. 根据权利要求1所述的方法，其中，根据所述歌曲的时间信息从所述候选清唱音频文件中划分出多个有效音频片段包括：
    获取所述歌曲对应的歌词文件，所述歌词文件包括每句歌词对应的时间信息；以及
    根据所述歌词文件中每句歌词对应的时间信息将所述候选清唱音频文件划分出多个有效音频片段。
  3. 根据权利要求1所述的方法，其中，所述提取每个所述有效音频片段的音符信息包括：
    提取每个所述有效音频片段的基频信息，其中，所述基频信息包括音频片段的基频值；
    获取所述多个有效音频片段中所述基频值为非零的音频片段的播放时长之和；
    如果所述播放时长之和超过预设时间，对每个所述有效音频片段执行处理，得到基频段；
    获取所述基频段中的基频值；
    对所述基频值执行音符化处理，得到所述基频值的音符值；以及
    合并所述音符值，得到所述多个有效音频片段的音符信息。
  4. 根据权利要求3所述的方法，其中，
    对每个所述有效音频片段执行处理包括：获取每个所述有效音频片段对应的长度；对所述长度小于第一预设值的有效音频片段执行第一滤波处理，得到第一滤波片段；对所述长度大于等于所述第一预设值的有效音频片段执行第二滤波处理，得到第二滤波片段；
    获取所述基频段中的基频值包括：获取所述第一滤波片段的基频值和所述第二滤波片段的基频值。
  5. 根据权利要求4所述的方法，其中，
    在获取每个所述有效音频片段对应的长度之后，所述方法还包括：如果所述长度小于第二预设值的有效音频片段中存在零音频片段，将所述零音频片段的基频值设置为预设基频值，其中，所述零音频片段为所述基频值为零的音频片段；
    获取所述基频段中的基频值包括：获取所述第一滤波片段的基频值、所述第二滤波片段的基频值和所述预设基频值。
  6. 根据权利要求3所述的方法，其中，在获取所述多个有效音频片段中所述基频值为非零的音频片段的时长之和之前，所述方法还包括：
    获取所述多个有效音频片段中相邻音频片段的基频值；
    计算所述相邻音频片段的基频值的差值；
    如果所述差值满足第二条件，将所述相邻音频片段的基频值置零。
  7. 根据权利要求3所述的方法，其中，合并所述音符值，得到所述有效音频片段的音符信息包括：
    将所述音符值中的相同音符值进行合并，并生成所述多个有效音频片段对应的三元组；以及
    将所述多个有效音频片段对应的三元组组合成用于表示所述音符信息的第一三元组序列。
  8. 根据权利要求7所述的方法，其中，生成所述多个有效音频片段对应的三元组包括：
    获取所述相同音符值、所述多个有效音频片段对应的三元组的起始时间、所述多个有效音频片段对应的三元组的持续时间；以及
    根据所述相同音符值、所述多个有效音频片段对应的三元组的起始时间、所述多个有效音频片段对应的三元组的持续时间生成所述多个有效音频片段对应的三元组。
  9. 根据权利要求7所述的方法，其中，所述第一三元组序列包括第一三元组和第二三元组，根据所述多个有效音频片段的音符信息生成所述数字乐谱文件包括：
    当所述第一三元组的起始时间等于所述第二三元组的起始时间与所述第二三元组的持续时间之和时，合并所述第一三元组和所述第二三元组，得到第三三元组，并从所述第一三元组序列中删除所述第一三元组，得到第二三元组序列；
    当所述第一三元组的起始时间不等于所述第二三元组的起始时间与所述第二三元组的持续时间之和时，当第四三元组的起始时间等于所述第一三元组的起始时间与所述第一三元组的持续时间之和时，合并所述第四三元组和所述第一三元组，得到第五三元组，并从所述第一三元组序列中删除所述第一三元组，得到所述第二三元组序列；
    当所述第一三元组的起始时间不等于所述第二三元组的起始时间与所述第二三元组的持续时间之和时，且当所述第四三元组的起始时间不等于所述第一三元组的起始时间与所述第一三元组的持续时间之和时，从所述第一三元组序列中删除所述第一三元组，得到所述第二三元组序列；以及
    将所述第二三元组序列中的三元组按照预设格式输出，得到所述 数字乐谱文件。
  10. 根据权利要求9所述的方法，其中，
    当si＝si-1+li-1成立时，通过l'i-1＝li-1+li计算所述第三三元组的持续时间l'i-1，其中，si为所述第一三元组的起始时间，si-1为所述第二三元组的起始时间，li-1为所述第二三元组的持续时间，li为所述第一三元组的持续时间；
    当si＝si-1+li-1不成立，si+1＝si+li成立时，通过l'i+1＝li+1+li计算所述第五三元组的持续时间l'i+1，通过s'i+1＝si计算所述第五三元组的起始时间s'i+1，其中，si+1为所述第四三元组的起始时间，li+1为所述第四三元组的持续时间。
  11. 根据权利要求1所述的方法，其中，获取所述候选清唱音频文件包括：
    获取上传的多个原始清唱音频文件；
    获取对所述多个原始清唱音频文件的回复信息，其中，所述回复信息用于表示所述原始清唱音频文件的质量等级；
    如果所述回复信息所表示的质量等级达到预定等级，则将所述原始清唱音频文件确定为所述候选清唱音频文件。
  12. 一种歌曲的数字乐谱文件的生成装置，包括：
    获取单元，被设置为从歌曲对应的清唱音频文件中获取满足第一条件的候选清唱音频文件，其中，所述清唱音频文件包括用户对所述歌曲进行演唱的清唱数据；
    划分单元，被设置为根据所述歌曲的时间信息从所述候选清唱音频文件中划分出多个有效音频片段；
    提取单元，被设置为提取每个所述有效音频片段的音符信息，其中，所述音符信息包括一个或多个三元组，每个所述三元组包括具有映射关系的音符的起始时间，音符的持续时间，音符的音符值；以及
    生成单元，被设置为根据每个所述有效音频片段的音符信息生成数字乐谱文件，其中，所述数字乐谱文件包括所述三元组中的部分或 全部。
  13. 根据权利要求12所述的装置，其中，所述划分单元包括：
    第一获取模块，被设置为获取所述歌曲对应的歌词文件，所述歌词文件包括每句歌词对应的时间信息；以及
    划分模块，被设置为根据所述歌词文件中每句歌词对应的时间信息将所述候选清唱音频文件划分为多个有效音频片段。
  14. 根据权利要求12所述的装置，其中，所述提取单元包括：
    提取模块，被设置为提取每个所述有效音频片段的基频信息，其中，所述基频信息包括音频片段的基频值；
    第二获取模块，被设置为获取所述多个有效音频片段中所述基频值为非零的音频片段的播放时长之和；
    第一处理模块，被设置为在所述播放时长之和超过预设时间时，对每个所述有效音频片段执行处理，得到基频段；
    第三获取模块，被设置为获取所述基频段中的基频值；
    第二处理模块，被设置为对所述基频值执行音符化处理，得到所述基频值的音符值；以及
    合并模块，被设置为合并所述音符值，得到所述多个有效音频片段的音符信息。
  15. 根据权利要求14所述的装置，
    所述第一处理模块包括：获取子模块，被设置为获取每个所述有效音频片段对应的长度；第一处理子模块，被设置为对所述长度小于第一预设值的音频片段执行第一滤波处理，得到第一滤波片段；第二处理子模块，被设置为对所述长度大于等于所述第一预设值的音频片段执行第二滤波处理，得到第二滤波片段；
    所述第三获取模块被设置为获取所述第一滤波片段的基频值和所述第二滤波片段的基频值。
  16. 一种终端，其中，所述终端被设置为执行程序代码，所述程序代码用于执行所述权利要求1至11中任意一项所述的歌曲的数字乐谱文件的生成方法中的步骤。
  17. 一种存储介质，其中，所述存储介质被设置为存储程序代码，所述程序代码用于执行所述权利要求1至11中任意一项所述的歌曲的数字乐谱文件的生成方法中的步骤。
PCT/CN2017/101008 2016-09-09 2017-09-08 歌曲的数字乐谱文件的生成方法、装置和存储介质 WO2018045988A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/059,109 US10923089B2 (en) 2016-09-09 2018-08-09 Method and apparatus for generating digital score file of song, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610816111.9A CN106448630B (zh) 2016-09-09 2016-09-09 歌曲的数字乐谱文件的生成方法和装置
CN201610816111.9 2016-09-09

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/059,109 Continuation US10923089B2 (en) 2016-09-09 2018-08-09 Method and apparatus for generating digital score file of song, and storage medium

Publications (1)

Publication Number Publication Date
WO2018045988A1 true WO2018045988A1 (zh) 2018-03-15

Family

ID=58167614

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/101008 WO2018045988A1 (zh) 2016-09-09 2017-09-08 歌曲的数字乐谱文件的生成方法、装置和存储介质

Country Status (3)

Country Link
US (1) US10923089B2 (zh)
CN (1) CN106448630B (zh)
WO (1) WO2018045988A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106448630A (zh) * 2016-09-09 2017-02-22 腾讯科技（深圳）有限公司 歌曲的数字乐谱文件的生成方法和装置

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108630240B (zh) * 2017-03-23 2020-05-26 北京小唱科技有限公司 一种合唱方法及装置
CN107452361B (zh) * 2017-08-08 2020-07-07 腾讯音乐娱乐（深圳）有限公司 歌曲分句方法及装置
CN107978323B (zh) * 2017-12-01 2022-09-27 腾讯科技（深圳）有限公司 音频识别方法、装置及存储介质
JP6980177B2 (ja) * 2018-01-09 2021-12-15 トヨタ自動車株式会社 オーディオ装置
CN108492817B (zh) * 2018-02-11 2020-11-10 北京光年无限科技有限公司 一种基于虚拟偶像的歌曲数据处理方法及演唱交互系统
CN108766452B (zh) * 2018-04-03 2020-11-06 北京小唱科技有限公司 修音方法及装置
CN110379400B (zh) * 2018-04-12 2021-09-24 森兰信息科技（上海）有限公司 一种用于生成乐谱的方法及系统
WO2019196052A1 (en) * 2018-04-12 2019-10-17 Sunland Information Technology Co., Ltd. System and method for generating musical score
CN110134335B (zh) * 2019-05-10 2022-08-12 天津大学深圳研究院 一种基于键值对的rdf数据管理方法、装置及存储介质
CN110096515A (zh) * 2019-05-10 2019-08-06 天津大学深圳研究院 一种基于三元组的rdf数据管理方法、装置及存储介质
CN110516102B (zh) * 2019-07-18 2021-05-11 杭州电子科技大学 一种基于语谱图识别的歌词时间戳生成方法
CN111159465B (zh) * 2019-12-31 2023-09-29 杭州网易云音乐科技有限公司 一种歌曲分类方法及装置
CN112071287A (zh) * 2020-09-10 2020-12-11 北京有竹居网络技术有限公司 用于生成歌谱的方法、装置、电子设备和计算机可读介质
CN113689836B (zh) * 2021-08-12 2023-08-18 福建星网视易信息系统有限公司 一种将音频转换成音符并显示的方法及终端
US11922911B1 (en) * 2022-12-02 2024-03-05 Staffpad Limited Method and system for performing musical score
CN115985273B (zh) * 2023-03-21 2023-12-26 北京卓颜翰景科技有限公司 基于多传感器数据融合的记谱方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7041888B2 (en) * 2004-01-09 2006-05-09 Yamaha Corporation Fingering guide displaying apparatus for musical instrument and computer program therefor
US8829322B2 (en) * 2012-10-26 2014-09-09 Avid Technology, Inc. Metrical grid inference for free rhythm musical input
CN104978973A (zh) * 2014-10-22 2015-10-14 腾讯科技（深圳）有限公司 一种音频处理方法及装置
CN104978380A (zh) * 2014-10-22 2015-10-14 腾讯科技（深圳）有限公司 一种音频处理方法及装置
CN105788589A (zh) * 2016-05-04 2016-07-20 腾讯科技（深圳）有限公司 一种音频数据的处理方法及装置
CN106448630A (zh) * 2016-09-09 2017-02-22 腾讯科技（深圳）有限公司 歌曲的数字乐谱文件的生成方法和装置

Family Cites Families (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5038658A (en) * 1988-02-29 1991-08-13 Nec Home Electronics Ltd. Method for automatically transcribing music and apparatus therefore
US5693903A (en) * 1996-04-04 1997-12-02 Coda Music Technology, Inc. Apparatus and method for analyzing vocal audio data to provide accompaniment to a vocalist
KR100304092B1 (ko) * 1998-03-11 2001-09-26 마츠시타 덴끼 산교 가부시키가이샤 오디오 신호 부호화 장치, 오디오 신호 복호화 장치 및 오디오 신호 부호화/복호화 장치
KR100412196B1 (ko) * 2001-05-21 2003-12-24 어뮤즈텍(주) 악보 추적 방법 및 그 장치
JP2003248488A (ja) * 2002-02-22 2003-09-05 Ricoh Co Ltd 情報処理システム、情報処理装置、情報処理方法、及びプログラム
US7351903B2 (en) * 2002-08-01 2008-04-01 Yamaha Corporation Musical composition data editing apparatus, musical composition data distributing apparatus, and program for implementing musical composition data editing method
CN101103386A (zh) * 2004-12-15 2008-01-09 缪斯艾米股份有限公司 用于乐谱捕捉和带同步呈现的合成音频演奏的系统与方法
JP4639795B2 (ja) * 2004-12-22 2011-02-23 ヤマハ株式会社 楽器の演奏駆動装置、鍵盤楽器の演奏駆動システム及び鍵盤楽器。
WO2008095190A2 (en) * 2007-02-01 2008-08-07 Museami, Inc. Music transcription
US7754955B2 (en) * 2007-11-02 2010-07-13 Mark Patrick Egan Virtual reality composer platform system
CN101521788A (zh) * 2008-02-25 2009-09-02 徐连彦 无线音频图像调制解调器
US8785760B2 (en) * 2009-06-01 2014-07-22 Music Mastermind, Inc. System and method for applying a chain of effects to a musical composition
CN101916250B (zh) * 2010-04-12 2011-10-19 电子科技大学 一种基于哼唱的音乐检索方法
JP2012022221A (ja) * 2010-07-16 2012-02-02 Ryukoku Univ 拍時刻推定装置および拍時刻推定方法
CN101894552B (zh) * 2010-07-16 2012-09-26 安徽科大讯飞信息科技股份有限公司 基于语谱切分的唱歌评测系统
CN102014195A (zh) * 2010-08-19 2011-04-13 上海酷吧信息技术有限公司 一种可生成音乐的手机及其实现方法
CN101968958B (zh) * 2010-11-02 2012-09-26 安徽科大讯飞信息科技股份有限公司 一种音频数据的比较方法和装置
BRPI1101173A2 (pt) * 2011-03-30 2013-06-04 Alessandro Paolone De Medeiros programa relativo ao funcionamento de um conjunto de processamento de dados, destinado Á escrita e ediÇço de partitura de mésica tocada por instrumento solista
CN102521281B (zh) * 2011-11-25 2013-10-23 北京师范大学 一种基于最长匹配子序列算法的哼唱计算机音乐检索方法
CN102522083B (zh) * 2011-11-29 2014-03-05 北京百纳威尔科技有限公司 一种应用移动终端搜索哼唱歌曲的方法及其移动终端
CN102547524A (zh) * 2011-12-15 2012-07-04 无锡中星微电子有限公司 一种蓝牙耳机中处理音频数据的方法、装置及设备
CN102915725A (zh) * 2012-09-10 2013-02-06 福建星网视易信息系统有限公司 人机互动的歌曲演唱系统、方法
CN102880693A (zh) * 2012-09-20 2013-01-16 浙江大学 一种基于个体发声能力的音乐推荐方法
CN103440250A (zh) * 2013-07-22 2013-12-11 北京承芯卓越科技有限公司 基于16位dsp平台应用的嵌入式哼唱检索方法及系统
CN104143324B (zh) * 2014-07-14 2018-01-12 电子科技大学 一种乐音音符识别方法
CN104200818A (zh) * 2014-08-06 2014-12-10 重庆邮电大学 一种音高检测方法
JP6160599B2 (ja) * 2014-11-20 2017-07-12 カシオ計算機株式会社 自動作曲装置、方法、およびプログラム
US9721551B2 (en) * 2015-09-29 2017-08-01 Amper Music, Inc. Machines, systems, processes for automated music composition and generation employing linguistic and/or graphical icon based musical experience descriptions
CN105469807B (zh) * 2015-12-30 2019-04-02 中国科学院自动化研究所 一种多基频提取方法及装置
CN105741835B (zh) * 2016-03-18 2019-04-16 腾讯科技（深圳）有限公司 一种音频信息处理方法及终端

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7041888B2 (en) * 2004-01-09 2006-05-09 Yamaha Corporation Fingering guide displaying apparatus for musical instrument and computer program therefor
US8829322B2 (en) * 2012-10-26 2014-09-09 Avid Technology, Inc. Metrical grid inference for free rhythm musical input
CN104978973A (zh) * 2014-10-22 2015-10-14 腾讯科技（深圳）有限公司 一种音频处理方法及装置
CN104978380A (zh) * 2014-10-22 2015-10-14 腾讯科技（深圳）有限公司 一种音频处理方法及装置
CN105788589A (zh) * 2016-05-04 2016-07-20 腾讯科技（深圳）有限公司 一种音频数据的处理方法及装置
CN106448630A (zh) * 2016-09-09 2017-02-22 腾讯科技（深圳）有限公司 歌曲的数字乐谱文件的生成方法和装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106448630A (zh) * 2016-09-09 2017-02-22 腾讯科技（深圳）有限公司 歌曲的数字乐谱文件的生成方法和装置

Also Published As

Publication number Publication date
CN106448630B (zh) 2020-08-04
US10923089B2 (en) 2021-02-16
US20180350336A1 (en) 2018-12-06
CN106448630A (zh) 2017-02-22

Similar Documents

Publication Publication Date Title
WO2018045988A1 (zh) 歌曲的数字乐谱文件的生成方法、装置和存储介质
TWI576822B (zh) Ｋ歌處理方法及系統
US10776422B2 (en) Dual sound source audio data processing method and apparatus
CN106652997B (zh) 一种音频合成的方法及终端
WO2017157319A1 (zh) 音频信息处理方法及装置
EP3373299B1 (en) Audio data processing method and device
CN108268530B (zh) 一种歌词的配乐生成方法和相关装置
US6881889B2 (en) Generating a music snippet
CN106991163A (zh) 一种基于演唱者声音特质的歌曲推荐方法
US9892758B2 (en) Audio information processing
CN101740025A (zh) 评估演唱者的嗓音性能的方法和使用该方法的设备
CN105161116A (zh) 多媒体文件高潮片段的确定方法及装置
CN105280196A (zh) 副歌检测方法及系统
KR101648931B1 (ko) 리듬 게임 제작 방법, 장치 및 이를 컴퓨터에서 실행하기 위한 컴퓨터 프로그램
CN111210850B (zh) 歌词对齐方法及相关产品
US20140277638A1 (en) System and method of predicting user audio file preferences
CN105895079B (zh) 语音数据的处理方法和装置
KR101813704B1 (ko) 사용자 음색 분석 장치 및 음색 분석 방법
CN107025902B (zh) 数据处理方法及装置
JP2014191192A (ja) 基準データ作成装置、基準データ作成システム、演奏端末装置
CN106448710B (zh) 一种音乐播放参数的校准方法及音乐播放设备
CN111276113B (zh) 基于音频生成按键时间数据的方法和装置
CN104954369A (zh) 多媒体内容的发送、生成和传输、播放方法和对应装置
CN111667803A (zh) 一种音频处理方法及相关产品
CN110838304A (zh) 一种准确视唱判断方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17848161

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17848161

Country of ref document: EP

Kind code of ref document: A1