WO2019052121A1 - Music identification system, method and apparatus, and music management server - Google Patents

Music identification system, method and apparatus, and music management server Download PDF

Info

Publication number
WO2019052121A1
WO2019052121A1 PCT/CN2018/077238 CN2018077238W WO2019052121A1 WO 2019052121 A1 WO2019052121 A1 WO 2019052121A1 CN 2018077238 W CN2018077238 W CN 2018077238W WO 2019052121 A1 WO2019052121 A1 WO 2019052121A1
Authority
WO
WIPO (PCT)
Prior art keywords
music
identification code
code
database
vocoding
Prior art date
Application number
PCT/CN2018/077238
Other languages
French (fr)
Chinese (zh)
Inventor
杨丽玉
刘怡中
Original Assignee
厦门声连网信息科技有限公司
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 厦门声连网信息科技有限公司 filed Critical 厦门声连网信息科技有限公司
Publication of WO2019052121A1 publication Critical patent/WO2019052121A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
    • G10L19/02—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis using spectral analysis, e.g. transform vocoders or subband vocoders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/10—Network architectures or network communication protocols for network security for controlling access to devices or network resources
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/12—Applying verification of the received information

Definitions

  • the present invention relates to the field of Internet communications, and in particular, to a music recognition system, device, and music management server and method.
  • Technical problem 2 On the basis of technical problem 1, the recognized music needs digital copyright protection, then there is a need for a music recognition technology that can accurately identify music and provide digital copyright protection.
  • the existing music recognition method can only Identify the music itself, no longer load data on it or load a music identifier.
  • the technical problem to be solved by the present invention is to provide a music recognition system, device and music management server and method for realizing effective identification and copyright protection of music.
  • the database is further configured to pre-save a plurality of original music and a corresponding identification code;
  • the music management server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, where Adding a check bit to the identification code, and converting the identification code added to the check bit into a binary vocode; wherein the check bit is used to indicate that the vocode is a music vocoding; Fourier transform unit And performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit configured to adjust a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and The corresponding original music composition is generated to generate the music having the music vocoding.
  • the music recognition device includes an identification unit for identifying a music vocal code carried by the received music to obtain an identification code, and the identification unit includes: a parsing module, configured to acquire
  • the database is further configured to pre-save a plurality of original music and a corresponding identification code;
  • the music management server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, where Adding a check bit to the identification code, and converting the identification code added to the check bit into a binary vocode; wherein the check bit is used to indicate that the vocode is a music vocoding; Fourier transform unit And performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit configured to adjust a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and The corresponding original music composition is generated to generate the music having the music vocoding.
  • the music recognition device includes an identification unit for identifying a music vocal code carried by the received music to obtain an identification code
  • the identification unit includes: a parsing module, configured to parse the acquired music to Obtaining an ultrasonic signal, and performing Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding; and an checking module, configured to check a check bit of the obtained vocode to determine whether the vocode is a musical sound Code, and extract the corresponding identification code when it is determined to be a music vocoding.
  • the data information includes basic information of the music, associated information, and extended application information.
  • the extended application information includes at least: music audition, music download, music purchase, music authorization authentication information, and music block chain key.
  • another technical solution adopted by the present invention is to provide a music recognition method, the method comprising: the music recognition device acquires music played by a music playing device, and recognizes the voice code carried by the music. Obtaining a corresponding identification code, and sending a verification request carrying the identification code to the music management server; the music management server, in response to the verification request, querying a database to determine an identifier that matches an identification code carried by the verification request a code; when the music management server queries the matching identification code, acquires data information corresponding to the identification code from the database, and sends the data information to the music recognition device, so that the music recognition device Obtaining data information of the music; wherein a plurality of the music codes previously synthesized by the corresponding identification code are synthesized and corresponding to the original music, and are stored in the database corresponding to the identification code.
  • the method further includes: obtaining an identification code corresponding to the original music from a database, adding a check bit to the identification code, and converting an identification code added to the check bit into a binary voice code;
  • the check bit is used to indicate that the voice code is a music voice code, and the plurality of original music and corresponding identification code are pre-stored in the database; and the binary voice code is subjected to Fourier forward Varying to obtain an acoustic signal; and adjusting the frequency of the acoustic signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesizing the ultrasonic signal with corresponding original music to generate the music having the musical vocoding.
  • the music recognition device acquires music played by a music playing device, identifies the voice code carried by the music to obtain a corresponding identification code, and sends a verification request carrying the identification code to the music management server, including
  • the music recognition device acquires music played by a music playback device; the music recognition device parses the acquired music to obtain an ultrasonic signal, and performs Fourier inverse transformation on the ultrasonic signal to obtain a corresponding a vocode; the music recognition device checks the obtained check bit of the vocode to determine whether the vocode is a music vocoding, and extracts a corresponding identification code when determining the music vocoding;
  • the music recognition device transmits an authentication request carrying the identification code to the music management server.
  • a music recognition device comprising: an acquisition unit, configured to receive music played by a music playback device; and an identification unit, configured to receive The vocal code carried by the music is identified to obtain a corresponding identification code; the verification requesting unit is configured to send a verification request carrying the identification code to a music management server to request the music management server to determine whether it is in the database Querying the matching identification code; the receiving unit is configured to receive the data information sent by the music management server, where the data information is sent when the music management server queries the matching identification code in the database, and Corresponding to the identification code; wherein a plurality of pieces of the music previously synthesized by the corresponding identification code are synthesized and corresponding to the original music, and are stored in the database corresponding to the identification code.
  • the identification unit includes: a parsing module, configured to parse the acquired music to obtain an ultrasonic signal, perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code; and an inspection module, configured to: The obtained check bit of the vocode is checked to determine whether the vocode is a music vocoding, and a corresponding identification code is extracted when it is determined to be a music vocoding.
  • the data information includes basic information of the music, associated information, and extended application information
  • the extended application information includes at least: music audition, music download, music purchase, music authorization authentication information, and music block chain key values
  • the device further includes: an execution unit, configured to display basic information of the music in the music recognition device, access corresponding link address according to the associated information to obtain extended information, and further configured to access according to the extended application information The corresponding link address to get the extension application.
  • another technical solution adopted by the present invention is to provide a music recognition method, the method comprising: responding to a verification request carrying an identification code sent by a music recognition device, and determining whether it can be queried in a database And an identifier that matches the identification code; wherein the verification request is generated when the music recognition device identifies the music voice code carried by the acquired music to obtain a corresponding identification code; when the query matches Obtaining, from the database, data information corresponding to the identification code; and transmitting the data information to the music recognition device; wherein the plurality of pieces of music are previously converted by a corresponding identification code The music vocoding is obtained by synthesizing the corresponding original music, and is stored in the database corresponding to the identification code.
  • another technical solution adopted by the present invention is to provide a music management server, where the server includes: a verification unit, configured to respond to a verification request carrying an identification code sent by a music identification device, and determine whether An identifier that matches the identification code can be queried in the database; wherein the verification request is generated when the music recognition device identifies the music vocal code carried by the acquired music to obtain a corresponding identification code.
  • a data acquisition unit configured to: when the verification unit queries the identification of the match, acquire data information data corresponding to the identification code from the database; and send a unit, configured to send the data information to the a music recognition device; wherein a plurality of the music sounds previously converted by the corresponding identification code are synthesized with the corresponding original music, and are stored in the database corresponding to the identification code.
  • a music processing method comprising: acquiring an identification code corresponding to the original music from a database, adding a check bit to the identification code, and Converting an identification code added to the check bit into a binary vocode; wherein a plurality of the original music and a corresponding identification code are pre-stored in the database, and the check bit is used to indicate the vocoding a music vocoding; performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and adjusting a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and the corresponding original Music synthesis, generating the music with music vocoding.
  • a music management server the server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, and join the identification code Checking the bit and converting the identification code added to the check bit into a binary vocode; wherein the database is used to pre-save a plurality of original music and a corresponding identification code, the check bit is used to indicate
  • the vocoding code is a music vocoding code; a Fourier transform unit for performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit for adjusting a frequency of the acoustic wave signal to an ultrasonic signal The frequency is obtained by obtaining an ultrasonic signal, and the ultrasonic signal is synthesized with corresponding original music to generate the music having the musical vocoding.
  • the music having the music identification code is directly recognized, and the music information is obtained through the music identification code, thereby avoiding A technical problem that identifies the wrong music due to the influence of environmental noise.
  • the authorization authentication information, the transaction information, and the like are added to the music identification code, and the music authorization, transaction, and the like are also obtained while the music is recognized, and the purpose of the music copyright protection is achieved through the authentication and recognition.
  • FIG. 1 is a schematic structural diagram of a music recognition system in an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of a music management server according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of synthesizing a music sound code with original music in an embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of a music recognition apparatus according to an embodiment of the present invention.
  • FIG. 5 is a schematic flowchart diagram of a music processing method according to a first embodiment of the present invention.
  • FIG. 6 is a schematic flow chart of a method for recognizing music by the music recognition device of FIG. 5;
  • FIG. 7 is a schematic flow chart of a music processing method in a second embodiment of the present invention.
  • FIG. 8 is a schematic flow chart of a music processing method in a third embodiment of the present invention.
  • FIG. 9 is a schematic flow chart of a music processing method in a fourth embodiment of the present invention.
  • Blockchain A mode of implementing and managing practice processing in a peer-to-peer network environment by constructing blockchain data structures that are unforgeable, non-tamperable, and traceable through transparent and trusted rules.
  • Vocal code The acoustic signal is subjected to Fourier inverse transform to obtain meaningful data.
  • FIG. 1 is a schematic structural diagram of a music recognition system according to an embodiment of the present invention.
  • the system 100 includes a database 10, a music playback device 20, a music recognition device 30, and a music management server 40.
  • the music playback device 20 is for playing music, and the music playback device 20 may be a device having a music playback function, such as a mobile device, a computer, a television, an audio or a broadcast.
  • the database 10 is for pre-storing a plurality of pieces of music having a music vocoding and an identification code corresponding to the music. Wherein, each piece of music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music (the principle of music synthesis will be described in detail below).
  • FIG. 2 is a schematic structural diagram of the music management server 40 in the embodiment of the present invention.
  • the music management server 40 includes a converting unit 41, a Fourier transform unit 42, a synthesizing unit 43, a verifying unit 44, a data acquiring unit 45, and a transmitting unit 46.
  • the database 10 is further configured to pre-store a plurality of original music and a corresponding identification code, the identification code being unique identification information corresponding to the original music.
  • the converting unit 41 is configured to acquire an identification code corresponding to each original music from the database 10, add a check bit to the identification code, and convert the identification code added to the check bit into a binary sound code, that is, a music sound code.
  • the data structure needs to be added with the information head and the check bit in addition to the data content itself, 3 Part of the complete information segment, as shown in Figure 3, the front of the information segment is the information header, which can be used as a separator to locate the starting position of the received sound wave.
  • the middle of the information segment is the valid data bit, that is, the actual information transmitted, and in the present embodiment, the data information corresponding to the identification code.
  • the check bit is added to the check bit to verify the data type, that is, the data information is music.
  • the data information includes basic information of music, associated information, and extended application information.
  • the basic information includes: the name of the music, the singer, the lyrics, the composition, and the album;
  • the related information includes: other music audition link addresses of the singer;
  • the extended application information includes: audition link address, download address, copyright information, purchase Link address, authorization authentication information, music blockchain key value.
  • a Fourier transform unit 42 configured to perform a Fourier positive change on the music vocoding generated by the conversion unit 41 to obtain an acoustic signal
  • the synthesizing unit 43 is configured to adjust the frequency of the acoustic signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesize the ultrasonic signal with the corresponding original music to generate music having the musical vocoding.
  • the synthesizing unit 43 synthesizes the ultrasonic signals with the corresponding original music in a plurality of consecutive intervals.
  • the human ear can't hear the ultrasonic signal, when people listen to the music with the music vocal code, the music vocal code is completely unseen, and the sound heard is like the sound quality of the original music.
  • the synthesizing unit 43 of the music management server 40 when the synthesizing unit 43 of the music management server 40 generates music having the music vocoding, the music is saved in the database 10 to form a music database.
  • synthesizing the music vocoding with the original music is not only performed by the music management server 40 as described in the embodiment of the present invention, but also implemented by other music processing devices or devices, and synthesized and generated.
  • the vocalized music is saved to the database 10 to form a music database.
  • the music playback device 20 downloads or directly acquires the music to be played from the music database in the database 10, and plays the music.
  • the music recognition device 30 acquires the music being played, recognizes the carried music sound code to obtain a corresponding identification code, and transmits an authentication request to the music management server 40.
  • FIG. 4 is a schematic structural diagram of a music recognition apparatus 30 according to an embodiment of the present invention.
  • the music recognition apparatus 30 may be a smart mobile device, a computer, or the like, and has a microphone, for acquiring music played.
  • the music recognition device 30 includes:
  • the acquiring unit 31 is configured to acquire music played by a music playing device 20;
  • the identifying unit 32 is configured to identify the vocal code carried by the acquired music to obtain a corresponding identification code
  • the verification requesting unit 33 is configured to send an authentication request carrying the identification code to the music management server 40 to request the music management server 40 to determine whether a matching identification code is queried in the database.
  • the identification unit 32 includes:
  • the parsing module 321 is configured to parse the acquired music to read the ultrasonic signal, and perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding.
  • the checking module 322 is configured to check the obtained check bit of the vocoding, determine whether the vocoding is a music vocoding, and extract a corresponding identification code when determining the music vocoding.
  • the verification unit 44 of the music management server 40 is configured to query the database 10 to determine an identification code matching the identification code carried by the verification request in response to the verification request sent by the music identification device 30; the data acquisition unit 45 is from the database 10. The data information corresponding to the identification code is acquired and transmitted by the transmitting unit 46 to the music recognition device 30, so that the music recognition device acquires the data information corresponding to the music.
  • the verification unit 44 queries the database 10 to determine whether the identification code exists, and if so, can prove that the first music is the music saved in the database 10, and then further query to obtain related information of the music, for example: creator , copyright ownership, audition link address, purchase link address, etc. If it does not exist, it is proved that the first music is not the music stored in the database 10, and the related information is inevitably inquired.
  • the data information includes basic information of music, associated information, and extended application information.
  • the music recognition device 30 further includes an execution unit 34 for displaying basic information of the music in the music recognition device 30, accessing the corresponding link address according to the associated information to obtain the extended information, and also for accessing the corresponding link address according to the extended application information. Get the extension app.
  • An example is as follows.
  • the data information includes the music identification information as: name, composition, lyrics, lyrics, and the information may be extended on the Internet.
  • the associated information of the query for example, other musical works that the lyricist of the first music also creates.
  • the user can display the basic information of the first music through the music recognition device 30, and can also access the corresponding link address to obtain the extension information.
  • the music information includes the music identification information in addition to the information in the application scenario example 1, and includes the extended application of the information on the Internet.
  • multimedia information music audition, download or purchase.
  • the user can directly access the music audition link address, the download link address, or the purchase link address through the application information acquired by the music recognition device 30 to perform audition, download or purchase of the music.
  • the data identification information includes the music identification information, in addition to the information in the application scenario examples 1 and 2, and the authorization authentication information of the music. For example, the authorized use information for the music.
  • the data information may also be a related music blockchain key value of the music, a use authorization value for obtaining non-repudiation thereof, and use authorization transaction information.
  • the corresponding function can be realized by jumping, accessing the corresponding page or program through the corresponding link address.
  • FIG. 5 is a schematic flowchart diagram of a music processing method according to a first embodiment of the present invention.
  • the method shown in this embodiment is applied to the music processing system as described above.
  • the database of the music processing system pre-stores a plurality of music having a music vocal code and an identification code corresponding to the music.
  • Each piece of music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music.
  • the method includes:
  • step S50 the music recognition device acquires music played by a music playing device, identifies the carried voice code to obtain a corresponding identification code, and sends a verification request carrying the identification code to the music management server.
  • Step S501 acquiring music played by the music playing device
  • Step S502 parsing the acquired music to read the ultrasonic signal, and performing Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code
  • Step S502 checking the check bit of the voice code to determine whether the voice code is a music voice code: if yes, proceeding to step S503; otherwise, the process ends.
  • Step S503 extracting an identification code in the vocoding code. Then, the process proceeds to step S51.
  • Step S51 the music management server responds to the verification request, queries the database to determine whether to find the identification code matching the identification code carried by the verification request; if yes, proceeds to step S52; otherwise, the process ends.
  • Step S52 Obtain data information corresponding to the identification code from the database, and send the data information to the music recognition device, so that the music recognition device acquires data information of the music.
  • FIG. 7 is a schematic flowchart diagram of a music processing method according to a second embodiment of the present invention. The method shown in this embodiment is applied to the music management server as described above, and includes:
  • Step S60 responding to the verification request carrying the identification code sent by a music recognition device, and determining whether the identification code matching the identification code can be queried in the database; if yes, proceeding to step S61; otherwise, the process ends.
  • the verification request is generated when the music recognition device identifies the music voice code carried by the acquired music to obtain a corresponding identification code.
  • Step S61 Obtain data information corresponding to the identification code from the database.
  • the plurality of pieces of music are synthesized in advance by the music code converted by the corresponding identification code and the corresponding original music, and are stored in the database corresponding to the identification code.
  • step S62 the data information is transmitted to the music recognition device.
  • FIG. 8 is a schematic flowchart of a music processing method according to a third embodiment of the present invention. The method shown in the embodiment is applied to the music recognition apparatus as described above, and includes:
  • Step S70 Acquire music played by a music playing device.
  • Step S71 identifying the vocal code carried by the music to obtain a corresponding identification code.
  • the acquired music is parsed to read the ultrasonic signal in the interval, and the ultrasonic signal is subjected to Fourier inverse transform to obtain a corresponding vocoding code; then, the obtained vocoding code is verified, and The corresponding identification code is extracted when the verification is passed.
  • the check bit of the obtained vocode is checked to determine whether the vocode is a music vowel, and if so, the check passes, and the data information in the vocoding is further extracted to obtain a corresponding identification code. Otherwise, the verification fails, and the music processing method flow ends.
  • Step S72 sending a verification request carrying the identification code to the music management server to request the music management server to determine whether a matching identification code is queried in the database.
  • Step S73 Receive data information corresponding to the identification code sent by the music management server, where the data information is sent when the music management server queries the matching identification code in the database, and corresponds to the identification code.
  • FIG. 9 is a schematic flowchart diagram of a music processing method according to a fourth embodiment of the present invention. The method shown in this embodiment is applied to the music management server as described above, and includes:
  • Step S80 Obtain an identification code corresponding to the original music from a database, add a check bit to the identification code, and convert an identification code added to the check bit into a binary voice code; Music and corresponding identification codes are pre-stored in the database;
  • Step S81 performing a Fourier forward change on the binary vocoding to obtain an acoustic signal
  • Step S82 adjusting the frequency of the acoustic wave signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesizing the ultrasonic signal with corresponding original music to generate the music having the music vocoding.
  • the music recognition is performed by the mobile terminal, the music having the music identification code is directly recognized, and the music information is obtained through the music identification code. And avoid the technical problem of identifying the wrong music due to the influence of environmental noise.
  • the authorization authentication information, the transaction information, and the like are added to the music identification code, and the music authorization, transaction, and the like are also obtained while the music is recognized, and the purpose of the music copyright protection is achieved through the authentication and recognition.
  • the disclosed system, terminal and method may be implemented in other manners.
  • the terminal embodiment described above is schematic, and the division of the unit is a logical function division, and the actual implementation may have another division manner.
  • the units described as separate components may or may not be physically separate, ie may be located in one place, or may be distributed over multiple network elements. 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 invention 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 hardware plus software functional units.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • all or part of the technical solution of the present invention may be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for causing a computer device (which may be a personal computer, The management server, or network device, etc. or processor, performs all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read only memory (English: read-only memory, abbreviation: ROM), a random access memory (English: Random Access Memory, abbreviation: RAM), a magnetic disk or an optical disk, and the like.
  • a U disk a mobile hard disk
  • a read only memory English: read-only memory, abbreviation: ROM
  • a random access memory English: Random Access Memory, abbreviation: RAM
  • magnetic disk or an optical disk and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Hardware Design (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Reverberation, Karaoke And Other Acoustics (AREA)

Abstract

A music identification system, method and apparatus, and a music management server. The music identification method comprises: a music identification apparatus (30) acquiring one piece of music played by a music playing apparatus (20), and identifying a carried sound code to obtain a corresponding identification code; and a music management server (40) querying a database (10) to determine a matched identification code, and sending corresponding data information to the music identification apparatus (30), wherein multiple pieces of music are obtained by means of pre-synthesizing sound codes converted and generated from corresponding identification codes, and corresponding original music, and same are correspondingly saved in the database (10) with the identification codes. By means of the method, a music identification code with a unique identity can be synthesized into the music, and a mobile terminal directly identifies music with a music identification code, thereby avoiding the technical problem that music is incorrectly identified due to the influence of ambient noise.

Description

一种音乐识别***、装置及音乐管理服务器和方法Music recognition system, device and music management server and method 【技术领域】[Technical Field]
本发明涉及互联网通信领域，特别涉及一种音乐识别***、装置及音乐管理服务器和方法。The present invention relates to the field of Internet communications, and in particular, to a music recognition system, device, and music management server and method.
【背景技术】【Background technique】
现在智能手机等移动终端都具有音乐播放功能，用户在播放音乐的同时，当用户听到环境中(来自于其他设备)播放的音乐是自己喜欢的音乐而想要进行收藏时，现有的智能手机还可以通过语音识别，对采集到的音乐片段进行识别并搜索网络数据库，从而查找到匹配的音乐。但是这种情况，存在以下技术问题：Now mobile terminals such as smart phones have a music playing function. While the user is playing music, when the user hears that the music played in the environment (from other devices) is his favorite music and wants to collect, the existing intelligence The mobile phone can also identify the collected music pieces by voice recognition, and search the network database to find matching music. However, in this case, the following technical problems exist:
技术问题一：现有的音乐播放、识别技术，通常都是通过语音识别或是声纹比对技术进行音乐的识别，这种方式存在的技术问题是：若环境噪音比较大、环境比较嘈杂，所采集到的音乐信息时不准确的，有时可能就无法识别、查找到准确的音乐。此外，这种语言识别或是声纹比对技术需要一个非常庞大的数据库，每个音乐ID都需要于数据库中储存好几兆的声纹数据空间与***资源。Technical Problem 1: Existing music playback and recognition technologies usually use music recognition or voiceprint comparison technology to identify music. The technical problem of this method is: if the ambient noise is relatively large and the environment is noisy, The collected music information is inaccurate, and sometimes it may not be possible to identify and find accurate music. In addition, this language recognition or voiceprint comparison technology requires a very large database, each music ID needs to store several megabytes of voiceprint data space and system resources in the database.
技术问题二：在技术问题一的基础上，识别到的音乐需要进行数字版权保护，那么需要一种能够精确识别音乐，并能够提供数字版权保护的音乐识别技术，现有的音乐识别方式只能识别音乐本身，无法再在其上加载数据或加载音乐识别码。Technical problem 2: On the basis of technical problem 1, the recognized music needs digital copyright protection, then there is a need for a music recognition technology that can accurately identify music and provide digital copyright protection. The existing music recognition method can only Identify the music itself, no longer load data on it or load a music identifier.
【发明内容】[Summary of the Invention]
本发明主要解决的技术问题是提供一种音乐识别***、装置及音乐管理服务器和方法，实现音乐的有效识别和版权保护。The technical problem to be solved by the present invention is to provide a music recognition system, device and music management server and method for realizing effective identification and copyright protection of music.
其中，所述数据库还用于预先保存多首原始音乐以及对应的识别码；所述音乐管理服务器包括：转换单元，用于从所述数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述检查位元用于表明所述声码为音乐声码；傅里叶变换单元，用于将所述二进制声码进行傅里叶正向变化得到声波信号；以及合成单元，用于将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。The database is further configured to pre-save a plurality of original music and a corresponding identification code; the music management server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, where Adding a check bit to the identification code, and converting the identification code added to the check bit into a binary vocode; wherein the check bit is used to indicate that the vocode is a music vocoding; Fourier transform unit And performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit configured to adjust a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and The corresponding original music composition is generated to generate the music having the music vocoding.
其中，所述音乐识别装置包括用于对接收到的音乐所携带的音乐声码进行识别以得到识别码的识别单元，所述识别单元包括：解析模块，用于对获取到The music recognition device includes an identification unit for identifying a music vocal code carried by the received music to obtain an identification code, and the identification unit includes: a parsing module, configured to acquire
其中，所述数据库还用于预先保存多首原始音乐以及对应的识别码；所述音乐管理服务器包括：转换单元，用于从所述数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述检查位元用于表明所述声码为音乐声码；傅里叶变换单元，用于将所述二进制声码进行傅里叶正向变化得到声波信号；以及合成单元，用于将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。The database is further configured to pre-save a plurality of original music and a corresponding identification code; the music management server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, where Adding a check bit to the identification code, and converting the identification code added to the check bit into a binary vocode; wherein the check bit is used to indicate that the vocode is a music vocoding; Fourier transform unit And performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit configured to adjust a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and The corresponding original music composition is generated to generate the music having the music vocoding.
其中，所述音乐识别装置包括用于对接收到的音乐所携带的音乐声码进行识别以得到识别码的识别单元，所述识别单元包括：解析模块，用于对获取到的音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；检查模块，用于对得到的声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码。The music recognition device includes an identification unit for identifying a music vocal code carried by the received music to obtain an identification code, and the identification unit includes: a parsing module, configured to parse the acquired music to Obtaining an ultrasonic signal, and performing Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding; and an checking module, configured to check a check bit of the obtained vocode to determine whether the vocode is a musical sound Code, and extract the corresponding identification code when it is determined to be a music vocoding.
其中，所述数据信息包含所述音乐的基本信息、关联信息以及延伸应用信息；所述延伸应用信息至少包括：音乐试听、音乐下载、音乐购买、音乐授权认证信息以及音乐区块链键值。The data information includes basic information of the music, associated information, and extended application information. The extended application information includes at least: music audition, music download, music purchase, music authorization authentication information, and music block chain key.
为解决上述技术问题，本发明采用的另一个技术方案是：提供一种音乐识别方法，所述方法包括：音乐识别装置获取一音乐播放装置播放的音乐，对所述音乐携带的声码进行识别以得到对应的识别码，并向音乐管理服务器发送一携带所述识别码的验证请求；所述音乐管理服务器响应所述验证请求，查询数据库以确定与所述验证请求携带的识别码匹配的识别码；所述音乐管理服务器查询到匹配的识别码时，从所述数据库中获取所述识别码对应的数据信息，并将所述数据信息发送至所述音乐识别装置，使所述音乐识别装置获取所述音乐的数据信息；其中，多首所述音乐预先由对应的识别码转换生成的声码与对应的原始音乐合成而得到，并与识别码对应地保存在所述数据库中。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a music recognition method, the method comprising: the music recognition device acquires music played by a music playing device, and recognizes the voice code carried by the music. Obtaining a corresponding identification code, and sending a verification request carrying the identification code to the music management server; the music management server, in response to the verification request, querying a database to determine an identifier that matches an identification code carried by the verification request a code; when the music management server queries the matching identification code, acquires data information corresponding to the identification code from the database, and sends the data information to the music recognition device, so that the music recognition device Obtaining data information of the music; wherein a plurality of the music codes previously synthesized by the corresponding identification code are synthesized and corresponding to the original music, and are stored in the database corresponding to the identification code.
其中，所述方法还包括：从数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述检查位元用于表明所述声码为音乐声码，多首所述原始音乐以及对应的识别码预先保存在所述数据库中；将所述二进制声码进行傅里叶正向变化得到声波信号；以及将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。The method further includes: obtaining an identification code corresponding to the original music from a database, adding a check bit to the identification code, and converting an identification code added to the check bit into a binary voice code; The check bit is used to indicate that the voice code is a music voice code, and the plurality of original music and corresponding identification code are pre-stored in the database; and the binary voice code is subjected to Fourier forward Varying to obtain an acoustic signal; and adjusting the frequency of the acoustic signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesizing the ultrasonic signal with corresponding original music to generate the music having the musical vocoding.
其中，所述音乐识别装置获取一音乐播放装置播放的音乐，对所述音乐携带的声码进行识别以得到对应的识别码，并向音乐管理服务器发送一携带所述识别码的验证请求，包括：所述音乐识别装置获取一音乐播放装置播放的音乐；所述音乐识别装置对获取到的所述音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；所述音乐识别装置对得到的所述声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码；以及所述音乐识别装置向所述音乐管理服务器发送一携带所述识别码的验证请求。The music recognition device acquires music played by a music playing device, identifies the voice code carried by the music to obtain a corresponding identification code, and sends a verification request carrying the identification code to the music management server, including The music recognition device acquires music played by a music playback device; the music recognition device parses the acquired music to obtain an ultrasonic signal, and performs Fourier inverse transformation on the ultrasonic signal to obtain a corresponding a vocode; the music recognition device checks the obtained check bit of the vocode to determine whether the vocode is a music vocoding, and extracts a corresponding identification code when determining the music vocoding; The music recognition device transmits an authentication request carrying the identification code to the music management server.
为解决上述技术问题，本发明采用的另一个技术方案是：提供一种音乐识别装置，所述装置包括：获取单元，用于接收一音乐播放装置播放的音乐；识 别单元，用于对接收到的所述音乐所携带的声码进行识别以得到对应的识别码；验证请求单元，用于向一音乐管理服务器发送携带所述识别码的验证请求，以请求所述音乐管理服务器确定是否在数据库中查询到匹配的识别码；接收单元，用于接收所述音乐管理服务器发送的数据信息；其中，所述数据信息为所述音乐管理服务器在数据库中查询到匹配的识别码时发送的，且与所述识别码对应；其中，多首所述音乐预先由对应的识别码转换生成的声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a music recognition device, the device comprising: an acquisition unit, configured to receive music played by a music playback device; and an identification unit, configured to receive The vocal code carried by the music is identified to obtain a corresponding identification code; the verification requesting unit is configured to send a verification request carrying the identification code to a music management server to request the music management server to determine whether it is in the database Querying the matching identification code; the receiving unit is configured to receive the data information sent by the music management server, where the data information is sent when the music management server queries the matching identification code in the database, and Corresponding to the identification code; wherein a plurality of pieces of the music previously synthesized by the corresponding identification code are synthesized and corresponding to the original music, and are stored in the database corresponding to the identification code.
其中，所述识别单元包括：解析模块，用于对获取到的音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；以及检查模块，用于对得到的所述声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码。The identification unit includes: a parsing module, configured to parse the acquired music to obtain an ultrasonic signal, perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code; and an inspection module, configured to: The obtained check bit of the vocode is checked to determine whether the vocode is a music vocoding, and a corresponding identification code is extracted when it is determined to be a music vocoding.
其中，所述数据信息包含所述音乐的基本信息、关联信息以及延伸应用信息，所述延伸应用信息至少包括：音乐试听、音乐下载、音乐购买、音乐授权认证信息以及音乐区块链键值；所述装置还包括：执行单元，用于在所述音乐识别装置显示所述音乐的基本信息，根据所述关联信息访问相应的链接地址以获取延伸信息，还用于根据所述延伸应用信息访问相应的链接地址以获取延伸应用。The data information includes basic information of the music, associated information, and extended application information, and the extended application information includes at least: music audition, music download, music purchase, music authorization authentication information, and music block chain key values; The device further includes: an execution unit, configured to display basic information of the music in the music recognition device, access corresponding link address according to the associated information to obtain extended information, and further configured to access according to the extended application information The corresponding link address to get the extension application.
为解决上述技术问题，本发明采用的另一个技术方案是：提供一种音乐识别方法，所述方法包括：响应一音乐识别装置发送的携带识别码的验证请求，并判断是否能够在数据库中查询到与所述识别码匹配的识别码；其中，所述验证请求是所述音乐识别装置对获取到的音乐所携带的音乐声码进行识别而得到对应的识别码时产生的；当查询到匹配的识别码时，从所述数据库中获取与所述识别码对应的数据信息；以及将所述数据信息发送至所述音乐识别装置；其中，多首所述音乐预先由对应的识别码转换生成的音乐声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a music recognition method, the method comprising: responding to a verification request carrying an identification code sent by a music recognition device, and determining whether it can be queried in a database And an identifier that matches the identification code; wherein the verification request is generated when the music recognition device identifies the music voice code carried by the acquired music to obtain a corresponding identification code; when the query matches Obtaining, from the database, data information corresponding to the identification code; and transmitting the data information to the music recognition device; wherein the plurality of pieces of music are previously converted by a corresponding identification code The music vocoding is obtained by synthesizing the corresponding original music, and is stored in the database corresponding to the identification code.
为解决上述技术问题，本发明采用的另一个技术方案是：提供一种音乐管 理服务器，所述服务器包括：验证单元，用于响应一音乐识别装置发送的携带识别码的验证请求，并判断是否能够在数据库中查询到与所述识别码匹配的识别码；其中，所述验证请求是所述音乐识别装置对获取到的音乐所携带的音乐声码进行识别而得到对应的识别码时产生的；数据获取单元，用于当所述验证单元查询到匹配的识别时，从所述数据库中获取与所述识别码对应的数据信息数据；发送单元，用于将所述数据信息发送至所述音乐识别装置；其中，多首所述音乐预先由对应的识别码转换生成的音乐声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。In order to solve the above technical problem, another technical solution adopted by the present invention is to provide a music management server, where the server includes: a verification unit, configured to respond to a verification request carrying an identification code sent by a music identification device, and determine whether An identifier that matches the identification code can be queried in the database; wherein the verification request is generated when the music recognition device identifies the music vocal code carried by the acquired music to obtain a corresponding identification code. a data acquisition unit, configured to: when the verification unit queries the identification of the match, acquire data information data corresponding to the identification code from the database; and send a unit, configured to send the data information to the a music recognition device; wherein a plurality of the music sounds previously converted by the corresponding identification code are synthesized with the corresponding original music, and are stored in the database corresponding to the identification code.
为解决上述技术问题，本发明采用的另一个技术方案是：一种音乐处理方法，所述方法包括：从数据库中获取原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，多首所述原始音乐以及对应的识别码预先保存在所述数据库中，所述检查位元用于表明所述声码为音乐声码；将所述二进制声码进行傅里叶正向变化得到声波信号；以及将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。In order to solve the above technical problem, another technical solution adopted by the present invention is: a music processing method, the method comprising: acquiring an identification code corresponding to the original music from a database, adding a check bit to the identification code, and Converting an identification code added to the check bit into a binary vocode; wherein a plurality of the original music and a corresponding identification code are pre-stored in the database, and the check bit is used to indicate the vocoding a music vocoding; performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and adjusting a frequency of the acoustic signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal and the corresponding original Music synthesis, generating the music with music vocoding.
为解决上述技术问题，本发明采用的另一个技术方案是：一种音乐管理服务器，所述服务器包括：转换单元，用于从数据库中获取原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述数据库用于预先保存多首原始音乐以及对应的识别码，所述检查位元用于表明所述声码为音乐声码；傅里叶变换单元，用于将所述二进制声码进行傅里叶正向变化得到声波信号；以及合成单元，用于将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。In order to solve the above technical problem, another technical solution adopted by the present invention is: a music management server, the server includes: a conversion unit, configured to acquire an identification code corresponding to the original music from the database, and join the identification code Checking the bit and converting the identification code added to the check bit into a binary vocode; wherein the database is used to pre-save a plurality of original music and a corresponding identification code, the check bit is used to indicate The vocoding code is a music vocoding code; a Fourier transform unit for performing a Fourier forward change of the binary vocoding to obtain an acoustic signal; and a synthesizing unit for adjusting a frequency of the acoustic wave signal to an ultrasonic signal The frequency is obtained by obtaining an ultrasonic signal, and the ultrasonic signal is synthesized with corresponding original music to generate the music having the musical vocoding.
以上方案中，通过在音乐中合成唯一性身份的音乐识别码，使得在通过移动终端进行音乐识别时，直接对具有音乐识别码的音乐进行识别，通过音乐识别码获得该音乐的信息，而避免因环境噪音的影响而出现识别音乐有误的技术 问题。进一步地，在音乐识别码中增加授权认证信息、交易信息等，在识别出该音乐的同时还可以获得该音乐的授权、交易等信息，并通过鉴权识别达到音乐版权保护的目的。In the above solution, by synthesizing the unique identification of the music identification code in the music, when the music recognition is performed by the mobile terminal, the music having the music identification code is directly recognized, and the music information is obtained through the music identification code, thereby avoiding A technical problem that identifies the wrong music due to the influence of environmental noise. Further, the authorization authentication information, the transaction information, and the like are added to the music identification code, and the music authorization, transaction, and the like are also obtained while the music is recognized, and the purpose of the music copyright protection is achieved through the authentication and recognition.
【附图说明】[Description of the Drawings]
图1是本发明实施方式中的一种音乐识别***的结构示意图；1 is a schematic structural diagram of a music recognition system in an embodiment of the present invention;
图2是本发明实施方式中的一种音乐管理服务器的结构示意图；2 is a schematic structural diagram of a music management server according to an embodiment of the present invention;
图3是本发明实施方式中将音乐声码与原始音乐合成的示意图；3 is a schematic diagram of synthesizing a music sound code with original music in an embodiment of the present invention;
图4是本发明实施方式中的一种音乐识别装置的结构示意图；4 is a schematic structural diagram of a music recognition apparatus according to an embodiment of the present invention;
图5是本发明第一实施方式中的一种音乐处理方法的流程示意图；FIG. 5 is a schematic flowchart diagram of a music processing method according to a first embodiment of the present invention; FIG.
图6是图5中音乐识别装置对音乐进行识别的方法的流程示意图；6 is a schematic flow chart of a method for recognizing music by the music recognition device of FIG. 5;
图7是本发明第二实施方式中的一种音乐处理方法的流程示意图；7 is a schematic flow chart of a music processing method in a second embodiment of the present invention;
图8是本发明第三实施方式中的一种音乐处理方法的流程示意图；8 is a schematic flow chart of a music processing method in a third embodiment of the present invention;
图9本发明第四实施方式中的一种音乐处理方法的流程示意图。FIG. 9 is a schematic flow chart of a music processing method in a fourth embodiment of the present invention.
【具体实施方式】【Detailed ways】
首先对本发明实施方式所需引用的现有技术名词进行解释。The prior art nomenclature referred to in the embodiments of the present invention is first explained.
区块链：一种在对等网络环境下，通过透明和可信规则，构建不可伪造、不可篡改和可追溯的块链式数据结构，实现和管理实务处理的模式。Blockchain: A mode of implementing and managing practice processing in a peer-to-peer network environment by constructing blockchain data structures that are unforgeable, non-tamperable, and traceable through transparent and trusted rules.
声码：声波信号进行傅里叶逆向变换后得到有意义的数据。Vocal code: The acoustic signal is subjected to Fourier inverse transform to obtain meaningful data.
为详细说明本发明的技术内容、构造特征、所实现目的及效果，以下结合附图和实施例对本发明进行详细说明。The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
请参阅图1，为本发明实施方式的一种音乐识别***的结构示意图。该***100包括：数据库10、音乐播放装置20、音乐识别装置30以及音乐管理服务器40。Please refer to FIG. 1 , which is a schematic structural diagram of a music recognition system according to an embodiment of the present invention. The system 100 includes a database 10, a music playback device 20, a music recognition device 30, and a music management server 40.
音乐播放装置20用于播放音乐，该音乐播放装置20可以是移动设备、计 算机、电视、音响或广播等，具有音乐播放功能的装置。The music playback device 20 is for playing music, and the music playback device 20 may be a device having a music playback function, such as a mobile device, a computer, a television, an audio or a broadcast.
该数据库10用于预先保存多首具有音乐声码的音乐，以及与该音乐对应的识别码。其中，每首音乐是预先由对应的识别码转换生成的声码与原始音乐合成得到的(音乐合成原理将在下文进行详细说明)。The database 10 is for pre-storing a plurality of pieces of music having a music vocoding and an identification code corresponding to the music. Wherein, each piece of music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music (the principle of music synthesis will be described in detail below).
具体地，请同时参阅图2，为本发明实施方式中的音乐管理服务器40的结构示意图。该音乐管理服务器40包括转换单元41、傅里叶变换单元42、合成单元43、验证单元44、数据获取单元45以及发送单元46。Specifically, please refer to FIG. 2 at the same time, which is a schematic structural diagram of the music management server 40 in the embodiment of the present invention. The music management server 40 includes a converting unit 41, a Fourier transform unit 42, a synthesizing unit 43, a verifying unit 44, a data acquiring unit 45, and a transmitting unit 46.
该数据库10还用于预先保存多首原始音乐以及对应的识别码，该识别码为对应原始音乐的唯一身份识别信息。The database 10 is further configured to pre-store a plurality of original music and a corresponding identification code, the identification code being unique identification information corresponding to the original music.
该转换单元41，用于从数据库10中获取每首原始音乐对应的识别码，在该识别码中加入检查位元，并将加入检查位元的识别码转换为二进制声码，即，音乐声码。The converting unit 41 is configured to acquire an identification code corresponding to each original music from the database 10, add a check bit to the identification code, and convert the identification code added to the check bit into a binary sound code, that is, a music sound code.
考虑到用于接收声波的音乐识别装置的识别方法、正确性校验，待传送数据的字符串编码成声波前，其数据结构除了数据内容本身以外，需要加上信息头跟检查位，3个部分构成完整的信息段，如图3所示，信息段的最前面为信息头，可作为分隔符，用以在定位接收声波的起始位置。信息段中间为有效数据位，即传输的实际信息，在本实施方式中为识别码对应的数据信息。最后为检查位，被加入检查位元，用以校验数据类型，即，该数据信息为音乐。Considering the identification method and correctness check of the music recognition device for receiving sound waves, before the character string of the data to be transmitted is encoded into the sound wave, the data structure needs to be added with the information head and the check bit in addition to the data content itself, 3 Part of the complete information segment, as shown in Figure 3, the front of the information segment is the information header, which can be used as a separator to locate the starting position of the received sound wave. The middle of the information segment is the valid data bit, that is, the actual information transmitted, and in the present embodiment, the data information corresponding to the identification code. Finally, the check bit is added to the check bit to verify the data type, that is, the data information is music.
在本实施方式中，该数据信息包含音乐的基本信息、关联信息以及延伸应用信息。其中，基本信息包括：音乐的名称、演唱者、作词、作曲、收录专辑；关联信息包括：演唱者的其他音乐试听链接地址等；延伸应用信息包括：试听链接地址、下载地址、版权信息、购买链接地址、授权认证信息、音乐区块链键值。In the embodiment, the data information includes basic information of music, associated information, and extended application information. The basic information includes: the name of the music, the singer, the lyrics, the composition, and the album; the related information includes: other music audition link addresses of the singer; the extended application information includes: audition link address, download address, copyright information, purchase Link address, authorization authentication information, music blockchain key value.
傅里叶变换单元42，用于将转换单元41生成的音乐声码进行傅里叶正向变化而得到声波信号；a Fourier transform unit 42 configured to perform a Fourier positive change on the music vocoding generated by the conversion unit 41 to obtain an acoustic signal;
合成单元43，用于将声波信号的频率调整至超声波信号频率以得到超声波 信号，并将超声波信号与对应的原始音乐进行合成，以生成具有音乐声码的音乐。The synthesizing unit 43 is configured to adjust the frequency of the acoustic signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesize the ultrasonic signal with the corresponding original music to generate music having the musical vocoding.
具体地，合成单元43将超声波信号以多个连续间隔的方式与对应的原始音乐合成。Specifically, the synthesizing unit 43 synthesizes the ultrasonic signals with the corresponding original music in a plurality of consecutive intervals.
由于人耳听不到超声波信号，因此，当人们收听具有音乐声码的音乐时，完全感觉不到音乐声码的存在，听到的声音就如同听到原始音乐的音质一样。Since the human ear can't hear the ultrasonic signal, when people listen to the music with the music vocal code, the music vocal code is completely unseen, and the sound heard is like the sound quality of the original music.
进一步地，音乐管理服务器40的合成单元43当生成具有音乐声码的音乐时，将这些音乐保存在数据库10中，形成音乐数据库。Further, when the synthesizing unit 43 of the music management server 40 generates music having the music vocoding, the music is saved in the database 10 to form a music database.
在其他实施方式中，将音乐声码与原始音乐进行合成，并不仅仅如本发明实施方式中所述，由音乐管理服务器40完成，还可以由其他音乐处理装置或设备实现，并将合成生成的具有声码的音乐保存至数据库10中形成音乐数据库。音乐播放装置20从数据库10中的音乐数据库中下载或直接获取所需播放的音乐，并播放该音乐。In other embodiments, synthesizing the music vocoding with the original music is not only performed by the music management server 40 as described in the embodiment of the present invention, but also implemented by other music processing devices or devices, and synthesized and generated. The vocalized music is saved to the database 10 to form a music database. The music playback device 20 downloads or directly acquires the music to be played from the music database in the database 10, and plays the music.
音乐识别装置30获取正在播放的音乐，并对携带的音乐声码进行识别以得到对应的识别码，并向音乐管理服务器40发送验证请求。The music recognition device 30 acquires the music being played, recognizes the carried music sound code to obtain a corresponding identification code, and transmits an authentication request to the music management server 40.
具体地，请参阅图4，为本发明实施方式中的音乐识别装置30的结构示意图，该音乐识别装置30可以是智能移动设备、计算机等，具有诸如麦克风，用于获取播放的音乐。其中，该音乐识别装置30包括：Specifically, please refer to FIG. 4 , which is a schematic structural diagram of a music recognition apparatus 30 according to an embodiment of the present invention. The music recognition apparatus 30 may be a smart mobile device, a computer, or the like, and has a microphone, for acquiring music played. The music recognition device 30 includes:
获取单元31，用于获取一音乐播放装置20播放的音乐；The acquiring unit 31 is configured to acquire music played by a music playing device 20;
识别单元32，用于对获取到的音乐所携带的声码进行识别以得到对应的识别码；The identifying unit 32 is configured to identify the vocal code carried by the acquired music to obtain a corresponding identification code;
验证请求单元33，用于向向音乐管理服务器40发送携带该识别码的验证请求，以请求该音乐管理服务器40确定是否在数据库中查询到匹配的识别码。具体地，该识别单元32包括：The verification requesting unit 33 is configured to send an authentication request carrying the identification code to the music management server 40 to request the music management server 40 to determine whether a matching identification code is queried in the database. Specifically, the identification unit 32 includes:
解析模块321，用于对获取到的音乐进行解析以读取超声波信号，并对该超声波信号进行傅里叶逆向变换以得到对应的声码。The parsing module 321 is configured to parse the acquired music to read the ultrasonic signal, and perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding.
检查模块322，用于对得到的声码的检查位元进行校验，确定该声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码。The checking module 322 is configured to check the obtained check bit of the vocoding, determine whether the vocoding is a music vocoding, and extract a corresponding identification code when determining the music vocoding.
进一步地，该音乐管理服务器40的验证单元44用于响应音乐识别装置30发送的验证请求，查询数据库10以确定与该验证请求携带的识别码匹配的识别码；数据获取单元45从数据库10中获取与该识别码对应的数据信息，并由发送单元46发送至音乐识别装置30，使该音乐识别装置获取到该音乐对应的数据信息。Further, the verification unit 44 of the music management server 40 is configured to query the database 10 to determine an identification code matching the identification code carried by the verification request in response to the verification request sent by the music identification device 30; the data acquisition unit 45 is from the database 10. The data information corresponding to the identification code is acquired and transmitted by the transmitting unit 46 to the music recognition device 30, so that the music recognition device acquires the data information corresponding to the music.
具体地，验证单元44查询数据库10以判断该识别码是否存在，若存在，即可证明该首音乐是该数据库10中保存的音乐，然后进一步查询，取得该音乐的相关信息，例如：创作者、版权所属、试听链接地址、购买链接地址等。若不存在，则证明该首音乐不是该数据库10中保存的音乐，则必然查询不到相关的信息。Specifically, the verification unit 44 queries the database 10 to determine whether the identification code exists, and if so, can prove that the first music is the music saved in the database 10, and then further query to obtain related information of the music, for example: creator , copyright ownership, audition link address, purchase link address, etc. If it does not exist, it is proved that the first music is not the music stored in the database 10, and the related information is inevitably inquired.
进一步地，数据信息包含音乐的基本信息、关联信息以及延伸应用信息。该音乐识别装置30还包括执行单元34，用于在音乐识别装置30显示音乐的基本信息，根据关联信息访问相应的链接地址以获取延伸信息，还用于根据延伸应用信息访问相应的链接地址以获取延伸应用。举例说明如下。Further, the data information includes basic information of music, associated information, and extended application information. The music recognition device 30 further includes an execution unit 34 for displaying basic information of the music in the music recognition device 30, accessing the corresponding link address according to the associated information to obtain the extended information, and also for accessing the corresponding link address according to the extended application information. Get the extension app. An example is as follows.
应用场景举例一Application scenario example 1
当音乐识别装置30如上所述接收到音乐管理服务器40发送的音乐的数据信息时，该数据信息中包含音乐识别信息为：名称、作曲、作词、歌词，还包括这些信息在互联网上可供延伸查询的关联信息，例如，该首音乐的作词者还创作的其他音乐作品。用户可以通过音乐识别装置30显示该首音乐的基本信息，还可以访问相应的链接地址获取延伸信息。When the music recognition device 30 receives the data information of the music transmitted by the music management server 40 as described above, the data information includes the music identification information as: name, composition, lyrics, lyrics, and the information may be extended on the Internet. The associated information of the query, for example, other musical works that the lyricist of the first music also creates. The user can display the basic information of the first music through the music recognition device 30, and can also access the corresponding link address to obtain the extension information.
应用场景举例二Application scenario example 2
当音乐识别装置30如上所述接收到音乐管理服务器40发送的音乐的数据 信息时，该数据信息中包含音乐识别信息除了包含应用场景举例一中的信息，还包括这些信息在互联网上的延伸应用，例如，多媒体信息、音乐试听、下载或购买。用户可以通过音乐识别装置30获取到的应用信息，直接访问音乐试听链接地址、下载链接地址或购买链接地址，进行音乐的试听、下载或购买。When the music identification device 30 receives the data information of the music sent by the music management server 40 as described above, the music information includes the music identification information in addition to the information in the application scenario example 1, and includes the extended application of the information on the Internet. For example, multimedia information, music audition, download or purchase. The user can directly access the music audition link address, the download link address, or the purchase link address through the application information acquired by the music recognition device 30 to perform audition, download or purchase of the music.
应用场景举例三Application scenario example three
当音乐识别装置30如上所述接收到音乐管理服务器40发送的音乐的数据信息时，该数据信息中包含音乐识别信息除了包含应用场景举例一、二中的信息，还包括该音乐的授权认证信息，例如，该音乐的授权使用信息。When the music identification device 30 receives the data information of the music sent by the music management server 40 as described above, the data identification information includes the music identification information, in addition to the information in the application scenario examples 1 and 2, and the authorization authentication information of the music. For example, the authorized use information for the music.
进一步地，该数据信息还可以是该音乐的相关音乐区块链键值、取得其不可否认性的使用授权价值及使用授权交易信息。Further, the data information may also be a related music blockchain key value of the music, a use authorization value for obtaining non-repudiation thereof, and use authorization transaction information.
用户通过音乐识别装置30获取到如上所述的授权认证信息时，能够通过相应的链接地址跳转、访问相应的页面或程序，实现相应的功能。When the user acquires the authorization authentication information as described above through the music recognition device 30, the corresponding function can be realized by jumping, accessing the corresponding page or program through the corresponding link address.
请参阅图5，为本发明第一实施方式中的音乐处理方法的流程示意图，该实施方式示出的方法应用于如上所述的音乐处理***。其中，该音乐处理***的数据库预先保存多首具有音乐声码的音乐，以及与该音乐对应的识别码。每首音乐是预先由对应的识别码转换生成的声码与原始音乐合成得到的。该方法包括：Please refer to FIG. 5, which is a schematic flowchart diagram of a music processing method according to a first embodiment of the present invention. The method shown in this embodiment is applied to the music processing system as described above. Wherein, the database of the music processing system pre-stores a plurality of music having a music vocal code and an identification code corresponding to the music. Each piece of music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music. The method includes:
步骤S50，音乐识别装置获取一音乐播放装置播放的音乐，对携带的声码进行识别以得到对应的识别码，并向音乐管理服务器发送一携带该识别码的验证请求。In step S50, the music recognition device acquires music played by a music playing device, identifies the carried voice code to obtain a corresponding identification code, and sends a verification request carrying the identification code to the music management server.
请同时参阅图6，具体地：Please also refer to Figure 6, specifically:
步骤S501，获取该音乐播放装置播放的音乐；Step S501, acquiring music played by the music playing device;
步骤S502，对获取到的音乐进行解析以读取超声波信号，并对该超声波信号进行傅里叶逆向变换以得到对应的声码；Step S502, parsing the acquired music to read the ultrasonic signal, and performing Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code;
步骤S502，对该声码的检查位元进行校验，以确定该声码是否为音乐声码：若是，则进入步骤S503；否则，流程结束。Step S502, checking the check bit of the voice code to determine whether the voice code is a music voice code: if yes, proceeding to step S503; otherwise, the process ends.
步骤S503，提取该声码中的识别码。然后，进入步骤S51。Step S503, extracting an identification code in the vocoding code. Then, the process proceeds to step S51.
步骤S51，该音乐管理服务器响应该验证请求，查询数据库以确定是否查询到与该验证请求携带的识别码匹配的识别码；若是，则进入步骤S52；否则，流程结束。Step S51, the music management server responds to the verification request, queries the database to determine whether to find the identification code matching the identification code carried by the verification request; if yes, proceeds to step S52; otherwise, the process ends.
步骤S52，从数据库中获取与该识别码对应的数据信息，并将该数据信息发送至音乐识别装置，使该音乐识别装置获取音乐的数据信息。Step S52: Obtain data information corresponding to the identification code from the database, and send the data information to the music recognition device, so that the music recognition device acquires data information of the music.
请参阅图7，为本发明第二实施方式中的音乐处理方法的流程示意图，该实施方式示出的方法应用于如上所述的音乐管理服务器，包括：FIG. 7 is a schematic flowchart diagram of a music processing method according to a second embodiment of the present invention. The method shown in this embodiment is applied to the music management server as described above, and includes:
步骤S60，响应一音乐识别装置发送的携带识别码的验证请求，并判断是否能够在数据库中查询到与该识别码匹配的识别码；若是，则进入步骤S61；否则，流程结束。Step S60, responding to the verification request carrying the identification code sent by a music recognition device, and determining whether the identification code matching the identification code can be queried in the database; if yes, proceeding to step S61; otherwise, the process ends.
其中，该验证请求是音乐识别装置对获取到的音乐所携带的音乐声码进行识别而得到对应的识别码时产生的。The verification request is generated when the music recognition device identifies the music voice code carried by the acquired music to obtain a corresponding identification code.
步骤S61，从数据库中获取与该识别码对应的数据信息。Step S61: Obtain data information corresponding to the identification code from the database.
其中，多首音乐预先由对应的识别码转换生成的音乐声码与对应原始音乐合成而得到，并与识别码对应地保存在数据库中。Wherein, the plurality of pieces of music are synthesized in advance by the music code converted by the corresponding identification code and the corresponding original music, and are stored in the database corresponding to the identification code.
步骤S62，将数据信息发送至音乐识别装置。In step S62, the data information is transmitted to the music recognition device.
请参阅图8，为本发明第三实施方式中的音乐处理方法的流程示意图，该实施方式示出的方法应用于如上所述的音乐识别装置，包括：FIG. 8 is a schematic flowchart of a music processing method according to a third embodiment of the present invention. The method shown in the embodiment is applied to the music recognition apparatus as described above, and includes:
步骤S70，获取一音乐播放装置播放的音乐。Step S70: Acquire music played by a music playing device.
步骤S71，对该音乐携带的声码进行识别以得到对应的识别码。Step S71, identifying the vocal code carried by the music to obtain a corresponding identification code.
具体地，对获取到的音乐进行解析以读取间隔中的超声波信号，并对该超 声波信号进行傅里叶逆向变换以得到对应的声码；然后，对得到的声码进行校验，并在校验通过时提取对应的识别码。Specifically, the acquired music is parsed to read the ultrasonic signal in the interval, and the ultrasonic signal is subjected to Fourier inverse transform to obtain a corresponding vocoding code; then, the obtained vocoding code is verified, and The corresponding identification code is extracted when the verification is passed.
进一步地，对得到的声码的检查位元进行校验以确定该声码是否为音乐声码，若是则校验通过，进一步地提取该声码中的数据信息，以得到对应的识别码。否则校验不通过，则该音乐处理方法流程结束。Further, the check bit of the obtained vocode is checked to determine whether the vocode is a music vowel, and if so, the check passes, and the data information in the vocoding is further extracted to obtain a corresponding identification code. Otherwise, the verification fails, and the music processing method flow ends.
步骤S72，向音乐管理服务器发送携带该识别码的验证请求，以请求音乐管理服务器确定是否在数据库中查询到匹配的识别码。Step S72, sending a verification request carrying the identification code to the music management server to request the music management server to determine whether a matching identification code is queried in the database.
步骤S73，接收音乐管理服务器发送的该是识别码对应的数据信息；其中，该数据信息为音乐管理服务器在数据库中查询到匹配的识别码时发送的，且与该识别码对应。Step S73: Receive data information corresponding to the identification code sent by the music management server, where the data information is sent when the music management server queries the matching identification code in the database, and corresponds to the identification code.
请参阅图9，为本发明第四实施方式中的音乐处理方法的流程示意图，该实施方式示出的方法应用于如上所述的音乐管理服务器，包括：FIG. 9 is a schematic flowchart diagram of a music processing method according to a fourth embodiment of the present invention. The method shown in this embodiment is applied to the music management server as described above, and includes:
步骤S80，从数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，多首原始音乐以及对应的识别码预先保存在所述数据库中；Step S80: Obtain an identification code corresponding to the original music from a database, add a check bit to the identification code, and convert an identification code added to the check bit into a binary voice code; Music and corresponding identification codes are pre-stored in the database;
步骤S81，将所述二进制声码进行傅里叶正向变化得到声波信号；以及Step S81, performing a Fourier forward change on the binary vocoding to obtain an acoustic signal;
步骤S82，将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。Step S82, adjusting the frequency of the acoustic wave signal to the ultrasonic signal frequency to obtain an ultrasonic signal, and synthesizing the ultrasonic signal with corresponding original music to generate the music having the music vocoding.
本发明实施方式中，通过在音乐中合成唯一性身份的音乐识别码，使得在通过移动终端进行音乐识别时，直接对具有音乐识别码的音乐进行识别，通过音乐识别码获得该音乐的信息，而避免因环境噪音的影响而出现识别音乐有误的技术问题。In the embodiment of the present invention, by synthesizing the unique identification of the music identification code in the music, when the music recognition is performed by the mobile terminal, the music having the music identification code is directly recognized, and the music information is obtained through the music identification code. And avoid the technical problem of identifying the wrong music due to the influence of environmental noise.
进一步地，在音乐识别码中增加授权认证信息、交易信息等，在识别出该音乐的同时还可以获得该音乐的授权、交易等信息，并通过鉴权识别达到音乐版权保护的目的。Further, the authorization authentication information, the transaction information, and the like are added to the music identification code, and the music authorization, transaction, and the like are also obtained while the music is recognized, and the purpose of the music copyright protection is achieved through the authentication and recognition.
在本发明所提供的实施方式中，所揭露的***、终端和方法，可以通过其它的方式实现。例如，以上所描述的终端实施例是示意性的，所述单元的划分，为一种逻辑功能划分，实际实现时可以有另外的划分方式。In the embodiments provided by the present invention, the disclosed system, terminal and method may be implemented in other manners. For example, the terminal embodiment described above is schematic, and the division of the unit is a logical function division, and the actual implementation may have another division manner.
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，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。The units described as separate components may or may not be physically separate, ie may be located in one place, or may be distributed over multiple network elements. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
另外，在本发明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，也可以采用硬件加软件功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention 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 hardware plus software functional units.
所述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，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的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一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，管理服务器，或者网络设备等)或处理器执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(英文：read-only memory，缩写：ROM)、随机存取存储器(英文：Random Access Memory，缩写：RAM)、磁碟或者光盘等各种可以存储程序代码的介质。The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the technical solution of the present invention may be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for causing a computer device (which may be a personal computer, The management server, or network device, etc. or processor, performs all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: a U disk, a mobile hard disk, a read only memory (English: read-only memory, abbreviation: ROM), a random access memory (English: Random Access Memory, abbreviation: RAM), a magnetic disk or an optical disk, and the like. A variety of media that can store program code.
以上所述仅为本发明的实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformation of the present invention and the contents of the drawings may be directly or indirectly applied to other related technologies. The fields are all included in the scope of patent protection of the present invention.

Claims (15)

  1. 一种音乐识别***，其特征在于，所述***包括：A music recognition system, characterized in that the system comprises:
    数据库，用于预先保存多首具有音乐声码的音乐以及与所述音乐对应的识别码；其中，每首音乐是预先由对应的识别码转换生成的声码与原始音乐合成而得到；a database for pre-storing a plurality of music having a music vocal code and an identification code corresponding to the music; wherein each music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music;
    音乐播放装置，用于播放音乐；a music playback device for playing music;
    音乐识别装置，用于接收播放的音乐，对携带的声码进行识别以得到识别码，并产生携带所述识别码的验证请求；以及a music recognition device, configured to receive the played music, identify the carried vocal code to obtain an identification code, and generate a verification request carrying the identification code;
    音乐管理服务器，用于接收所述音乐识别装置产生的验证请求，查询所述数据库以确定与所述验证请求携带的识别码匹配的识别码，从所述数据库中获取所述识别码对应的数据信息，并将所述识别码对应的数据信息发送至所述音乐识别装置，使所述音乐识别装置获取到所述音乐对应的数据信息。a music management server, configured to receive an authentication request generated by the music identification device, query the database to determine an identification code that matches an identification code carried by the verification request, and acquire data corresponding to the identification code from the database And transmitting the data information corresponding to the identification code to the music recognition device, so that the music recognition device acquires the data information corresponding to the music.
  2. 根据权利要求1所述的音乐识别***，其特征在于，所述数据库还用于预先保存多首原始音乐以及对应的识别码；The music recognition system according to claim 1, wherein the database is further configured to pre-save a plurality of original music and a corresponding identification code;
    所述音乐管理服务器包括：The music management server includes:
    转换单元，用于从所述数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述检查位元用于表明所述声码为音乐声码；a conversion unit, configured to acquire an identification code corresponding to the original music from the database, add a check bit to the identification code, and convert an identification code added to the check bit into a binary voice code; The check bit is used to indicate that the voice code is a music voice code;
    傅里叶变换单元，用于将所述二进制声码进行傅里叶正向变化得到声波信号；以及a Fourier transform unit, configured to perform a Fourier forward change on the binary vocoding to obtain an acoustic signal;
    合成单元，用于将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。And a synthesizing unit, configured to adjust a frequency of the acoustic wave signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and synthesize the ultrasonic signal with corresponding original music to generate the music having the music vocoding.
  3. 根据权利要求2所述的音乐识别***，其特征在于，所述音乐识别装置包括用于对接收到的音乐所携带的音乐声码进行识别以得到识别码的识别单元， 所述识别单元包括：The music recognition system according to claim 2, wherein the music recognition means comprises an identification unit for identifying the music vocal code carried by the received music to obtain an identification code, the identification unit comprising:
    解析模块，用于对获取到的音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；a parsing module, configured to parse the acquired music to obtain an ultrasonic signal, and perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code;
    检查模块，用于对得到的声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码。The checking module is configured to check the check bit of the obtained vocoding to determine whether the vocoding is a music vocoding, and extract a corresponding identification code when determining the music vocoding.
  4. 根据权利要求1-3任意一项所述的音乐识别***，其特征在于，所述数据信息包含所述音乐的基本信息、关联信息以及延伸应用信息；所述延伸应用信息至少包括：音乐试听、音乐下载、音乐购买、音乐授权认证信息以及音乐区块链键值。The music recognition system according to any one of claims 1 to 3, wherein the data information includes basic information of the music, associated information, and extended application information; and the extended application information includes at least: music audition, Music downloads, music purchases, music license authentication information, and music blockchain key values.
  5. 一种音乐识别***，其特征在于，所述***包括：A music recognition system, characterized in that the system comprises:
    数据库，用于预先保存多首具有音乐声码的音乐以及与所述音乐对应的识别码；其中，每首音乐是预先由对应的识别码转换生成的声码与原始音乐合成而得到；a database for pre-storing a plurality of music having a music vocal code and an identification code corresponding to the music; wherein each music is synthesized by synthesizing the vocode generated in advance by the corresponding identification code with the original music;
    音乐播放装置，用于播放音乐；a music playback device for playing music;
    音乐识别装置，用于接收播放的音乐，对携带的声码进行识别以得到识别码，并产生携带所述识别码的验证请求；以及a music recognition device, configured to receive the played music, identify the carried vocal code to obtain an identification code, and generate a verification request carrying the identification code;
    音乐管理服务器，用于接收所述音乐识别装置产生的验证请求，查询所述数据库以确定与所述验证请求携带的识别码匹配的识别码，从所述数据库中获取所述识别码对应的数据信息，并将所述识别码对应的数据信息发送至所述音乐识别装置，使所述音乐识别装置获取到所述音乐对应的数据信息。a music management server, configured to receive an authentication request generated by the music identification device, query the database to determine an identification code that matches an identification code carried by the verification request, and acquire data corresponding to the identification code from the database And transmitting the data information corresponding to the identification code to the music recognition device, so that the music recognition device acquires the data information corresponding to the music.
  6. 一种音乐识别方法，其特征在于，所述方法包括：A music recognition method, characterized in that the method comprises:
    音乐识别装置获取一音乐播放装置播放的音乐，对所述音乐携带的声码进行识别以得到对应的识别码，并向音乐管理服务器发送一携带所述识别码的验证请求；The music recognition device acquires the music played by the music playing device, identifies the voice code carried by the music to obtain a corresponding identification code, and sends a verification request carrying the identification code to the music management server;
    所述音乐管理服务器响应所述验证请求，查询数据库以确定与所述验证请求携带的识别码匹配的识别码；Responding to the verification request, the music management server queries a database to determine an identification code that matches an identification code carried by the verification request;
    所述音乐管理服务器查询到匹配的识别码时，从所述数据库中获取所述识别码对应的数据信息，并将所述数据信息发送至所述音乐识别装置，使所述音乐识别装置获取所述音乐的数据信息；When the music management server queries the matching identification code, the data information corresponding to the identification code is obtained from the database, and the data information is sent to the music recognition device, so that the music recognition device acquires the Data information about music;
    其中，多首所述音乐预先由对应的识别码转换生成的声码与对应的原始音乐合成而得到，并与识别码对应地保存在所述数据库中。Wherein, the plurality of pieces of music are synthesized in advance by the corresponding code generated by the corresponding identification code conversion and are stored in the database corresponding to the identification code.
  7. 根据权利要求5所述的音乐识别方法，其特征在于，所述方法还包括：The music recognition method according to claim 5, wherein the method further comprises:
    从数据库中获取所述原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述检查位元用于表明所述声码为音乐声码，多首所述原始音乐以及对应的识别码预先保存在所述数据库中；Obtaining an identification code corresponding to the original music from a database, adding a check bit to the identification code, and converting an identification code added to the check bit into a binary voice code; wherein the check bit is used In the indication that the vocoding is a music vocoding, a plurality of the original music and the corresponding identification code are pre-stored in the database;
    将所述二进制声码进行傅里叶正向变化得到声波信号；以及Performing a Fourier forward change on the binary vocoding to obtain an acoustic signal;
    将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。The frequency of the acoustic wave signal is adjusted to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal is synthesized with corresponding original music to generate the music having the musical vocoding.
  8. 根据权利要求6所述的音乐识别方法，其特征在于，所述音乐识别装置获取一音乐播放装置播放的音乐，对所述音乐携带的声码进行识别以得到对应的识别码，并向音乐管理服务器发送一携带所述识别码的验证请求，包括：The music recognition method according to claim 6, wherein the music recognition device acquires music played by a music playing device, recognizes a voice code carried by the music to obtain a corresponding identification code, and manages the music The server sends an authentication request carrying the identifier, including:
    所述音乐识别装置获取一音乐播放装置播放的音乐；The music recognition device acquires music played by a music playing device;
    所述音乐识别装置对获取到的所述音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；The music recognition device parses the acquired music to obtain an ultrasonic signal, and performs Fourier inverse transformation on the ultrasonic signal to obtain a corresponding vocoding code;
    所述音乐识别装置对得到的所述声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码；以及The music recognition device checks the obtained check bit of the vocode to determine whether the vocoding is a music vocoding, and extracts a corresponding identification code when determining the music vocoding;
    所述音乐识别装置向所述音乐管理服务器发送一携带所述识别码的验证请求。The music recognition device transmits an authentication request carrying the identification code to the music management server.
  9. 一种音乐识别装置，其特征在于，所述装置包括：A music recognition device, characterized in that the device comprises:
    获取单元，用于接收一音乐播放装置播放的音乐；An acquiring unit, configured to receive music played by a music playing device;
    识别单元，用于对接收到的所述音乐所携带的声码进行识别以得到对应的 识别码；An identification unit, configured to identify the received voice code of the music to obtain a corresponding identifier;
    验证请求单元，用于向一音乐管理服务器发送携带所述识别码的验证请求，以请求所述音乐管理服务器确定是否在数据库中查询到匹配的识别码；a verification requesting unit, configured to send a verification request carrying the identification code to a music management server, to request the music management server to determine whether a matching identification code is queried in the database;
    接收单元，用于接收所述音乐管理服务器发送的数据信息；其中，所述数据信息为所述音乐管理服务器在数据库中查询到匹配的识别码时发送的，且与所述识别码对应；a receiving unit, configured to receive data information sent by the music management server, where the data information is sent when the music management server queries a matching identification code in a database, and corresponds to the identification code;
    其中，多首所述音乐预先由对应的识别码转换生成的声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。Wherein, the plurality of pieces of the music are synthesized in advance by the corresponding identification code converted by the corresponding identification code, and are stored in the database corresponding to the identification code.
  10. 根据权利要求8所述的音乐识别装置，其特征在于，所述识别单元包括：The music recognition device according to claim 8, wherein the identification unit comprises:
    解析模块，用于对获取到的音乐进行解析以获得超声波信号，并对所述超声波信号进行傅里叶逆向变换以得到对应的声码；以及a parsing module, configured to parse the acquired music to obtain an ultrasonic signal, and perform Fourier inverse transform on the ultrasonic signal to obtain a corresponding vocoding code;
    检查模块，用于对得到的所述声码的检查位元进行校验以确定所述声码是否为音乐声码，并在确定为音乐声码时提取对应的识别码。The checking module is configured to check the obtained check bit of the vocode to determine whether the vocode is a music vocoding, and extract a corresponding identification code when determining the music vocoding.
  11. 根据权利要求8或9所述的音乐识别装置，其特征在于，所述数据信息包含所述音乐的基本信息、关联信息以及延伸应用信息，所述延伸应用信息至少包括：音乐试听、音乐下载、音乐购买、音乐授权认证信息以及音乐区块链键值；所述装置还包括：The music recognition device according to claim 8 or 9, wherein the data information comprises basic information of the music, associated information, and extended application information, and the extended application information includes at least: music audition, music download, Music purchase, music authorization authentication information, and music blockchain key values; the device further includes:
    执行单元，用于在所述音乐识别装置显示所述音乐的基本信息，根据所述关联信息访问相应的链接地址以获取延伸信息，还用于根据所述延伸应用信息访问相应的链接地址以获取延伸应用。An execution unit, configured to display basic information of the music in the music recognition device, access a corresponding link address according to the associated information to obtain extended information, and further configured to access a corresponding link address according to the extended application information to obtain Extend the app.
  12. 一种音乐识别方法，其特征在于，所述方法包括：A music recognition method, characterized in that the method comprises:
    响应一音乐识别装置发送的携带识别码的验证请求，并判断是否能够在数据库中查询到与所述识别码匹配的识别码；其中，所述验证请求是所述音乐识别装置对获取到的音乐所携带的音乐声码进行识别而得到对应的识别码时产生的；Responding to an authentication request carrying an identification code sent by a music recognition device, and determining whether an identification code matching the identification code can be queried in the database; wherein the verification request is the music acquired by the music recognition device The generated music vocal code is identified to obtain the corresponding identification code;
    当查询到匹配的识别码时，从所述数据库中获取与所述识别码对应的数据 信息；以及Obtaining data information corresponding to the identification code from the database when the matching identification code is queried;
    将所述数据信息发送至所述音乐识别装置；Transmitting the data information to the music recognition device;
    其中，多首所述音乐预先由对应的识别码转换生成的音乐声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。Wherein, the plurality of pieces of music are synthesized in advance by the music code converted by the corresponding identification code and the corresponding original music, and are stored in the database corresponding to the identification code.
  13. 一种音乐管理服务器，其特征在于，所述服务器包括：A music management server, characterized in that the server comprises:
    验证单元，用于响应一音乐识别装置发送的携带识别码的验证请求，并判断是否能够在数据库中查询到与所述识别码匹配的识别码；其中，所述验证请求是所述音乐识别装置对获取到的音乐所携带的音乐声码进行识别而得到对应的识别码时产生的；a verification unit, configured to respond to an authentication request carrying an identification code sent by a music recognition device, and determine whether an identification code matching the identification code can be queried in a database; wherein the verification request is the music identification device Generating a music vocal code carried by the acquired music to obtain a corresponding identification code;
    数据获取单元，用于当所述验证单元查询到匹配的识别时，从所述数据库中获取与所述识别码对应的数据信息数据；a data obtaining unit, configured to: when the verification unit queries the matching identification, acquire data information data corresponding to the identification code from the database;
    发送单元，用于将所述数据信息发送至所述音乐识别装置；a sending unit, configured to send the data information to the music recognition device;
    其中，多首所述音乐预先由对应的识别码转换生成的音乐声码与对应原始音乐合成而得到，并与识别码对应地保存在所述数据库中。Wherein, the plurality of pieces of music are synthesized in advance by the music code converted by the corresponding identification code and the corresponding original music, and are stored in the database corresponding to the identification code.
  14. 一种音乐处理方法，其特征在于，所述方法包括：A music processing method, characterized in that the method comprises:
    从数据库中获取原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，多首所述原始音乐以及对应的识别码预先保存在所述数据库中，所述检查位元用于表明所述声码为音乐声码；Obtaining an identification code corresponding to the original music from the database, adding a check bit to the identification code, and converting the identification code added to the check bit into a binary voice code; wherein, the plurality of the original music and corresponding The identification code is pre-stored in the database, and the check bit is used to indicate that the voice code is a music sound code;
    将所述二进制声码进行傅里叶正向变化得到声波信号；以及Performing a Fourier forward change on the binary vocoding to obtain an acoustic signal;
    将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。The frequency of the acoustic wave signal is adjusted to an ultrasonic signal frequency to obtain an ultrasonic signal, and the ultrasonic signal is synthesized with corresponding original music to generate the music having the musical vocoding.
  15. 一种音乐管理服务器，其特征在于，所述服务器包括：A music management server, characterized in that the server comprises:
    转换单元，用于从数据库中获取原始音乐对应的识别码，在所述识别码中加入检查位元，并将加入所述检查位元的识别码转换为二进制的声码；其中，所述数据库用于预先保存多首原始音乐以及对应的识别码，所述检查位元用于 表明所述声码为音乐声码；a conversion unit, configured to obtain an identification code corresponding to the original music from the database, add a check bit to the identification code, and convert the identification code added to the check bit into a binary voice code; wherein the database For pre-storing a plurality of original music and a corresponding identification code, the check bit is used to indicate that the sound code is a music sound code;
    傅里叶变换单元，用于将所述二进制声码进行傅里叶正向变化得到声波信号；以及a Fourier transform unit, configured to perform a Fourier forward change on the binary vocoding to obtain an acoustic signal;
    合成单元，用于将所述声波信号的频率调整至超声波信号频率以得到超声波信号，并将所述超声波信号与对应的原始音乐合成，生成所述具有音乐声码的音乐。And a synthesizing unit, configured to adjust a frequency of the acoustic wave signal to an ultrasonic signal frequency to obtain an ultrasonic signal, and synthesize the ultrasonic signal with corresponding original music to generate the music having the music vocoding.
PCT/CN2018/077238 2017-09-13 2018-02-26 Music identification system, method and apparatus, and music management server WO2019052121A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710820097.4 2017-09-13
CN201710820097.4A CN107657958B (en) 2017-09-13 2017-09-13 Music identification system, device, music management server and method

Publications (1)

Publication Number Publication Date
WO2019052121A1 true WO2019052121A1 (en) 2019-03-21

Family

ID=61129620

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/077238 WO2019052121A1 (en) 2017-09-13 2018-02-26 Music identification system, method and apparatus, and music management server

Country Status (2)

Country Link
CN (1) CN107657958B (en)
WO (1) WO2019052121A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107657958B (en) * 2017-09-13 2020-06-23 厦门声连网信息科技有限公司 Music identification system, device, music management server and method
CN109472120A (en) * 2018-09-19 2019-03-15 侯锐 A kind of copyright protection and acquisition methods, device and equipment of digital audio

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030028796A1 (en) * 2001-07-31 2003-02-06 Gracenote, Inc. Multiple step identification of recordings
CN1641515A (en) * 2004-01-14 2005-07-20 凌阳科技股份有限公司 Device and method for encrypting protection to instruction using check bit element
CN102172433A (en) * 2011-02-24 2011-09-07 颉羽玩具(深圳)有限公司 Electric toy controlled by ultrasonic waves and control method thereof
CN102955916A (en) * 2011-08-25 2013-03-06 全宏科技股份有限公司 Digital content protecting method and digital content storage device
CN103489116A (en) * 2012-06-12 2014-01-01 上海君戈网络科技有限公司 Point reward system of mobile terminal and reward method thereof
US20150302086A1 (en) * 2014-04-22 2015-10-22 Gracenote, Inc. Audio identification during performance
CN105989183A (en) * 2015-05-15 2016-10-05 乐卡汽车智能科技（北京）有限公司 Music recognition method and device of car radio
CN106909608A (en) * 2017-01-09 2017-06-30 深圳前海勇艺达机器人有限公司 Data processing method and device based on intelligent robot
CN107657958A (en) * 2017-09-13 2018-02-02 厦门声连网信息科技有限公司 A kind of music recognition system, device and music management server and method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102222504A (en) * 2011-06-10 2011-10-19 深圳市金光艺科技有限公司 Digital audio multilayer watermark implanting and extracting method
CN102522093A (en) * 2012-01-09 2012-06-27 武汉大学 Sound source separation method based on three-dimensional space audio frequency perception
CN105281842B (en) * 2014-07-24 2018-10-16 福建星网视易信息***有限公司 The encoding of a kind of acoustic communication, decoded method and apparatus
CN107077855B (en) * 2014-07-28 2020-09-22 三星电子株式会社 Signal encoding method and apparatus, and signal decoding method and apparatus

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030028796A1 (en) * 2001-07-31 2003-02-06 Gracenote, Inc. Multiple step identification of recordings
CN1641515A (en) * 2004-01-14 2005-07-20 凌阳科技股份有限公司 Device and method for encrypting protection to instruction using check bit element
CN102172433A (en) * 2011-02-24 2011-09-07 颉羽玩具(深圳)有限公司 Electric toy controlled by ultrasonic waves and control method thereof
CN102955916A (en) * 2011-08-25 2013-03-06 全宏科技股份有限公司 Digital content protecting method and digital content storage device
CN103489116A (en) * 2012-06-12 2014-01-01 上海君戈网络科技有限公司 Point reward system of mobile terminal and reward method thereof
US20150302086A1 (en) * 2014-04-22 2015-10-22 Gracenote, Inc. Audio identification during performance
CN105989183A (en) * 2015-05-15 2016-10-05 乐卡汽车智能科技（北京）有限公司 Music recognition method and device of car radio
CN106909608A (en) * 2017-01-09 2017-06-30 深圳前海勇艺达机器人有限公司 Data processing method and device based on intelligent robot
CN107657958A (en) * 2017-09-13 2018-02-02 厦门声连网信息科技有限公司 A kind of music recognition system, device and music management server and method

Also Published As

Publication number Publication date
CN107657958B (en) 2020-06-23
CN107657958A (en) 2018-02-02

Similar Documents

Publication Publication Date Title
JP6581324B2 (en) Adaptive processing by multiple media processing nodes
US10158633B2 (en) Using the ability to speak as a human interactive proof
JP2020016875A (en) Voice interaction method, device, equipment, computer storage medium, and computer program
CN102959544A (en) Methods and systems for synchronizing media
US8983845B1 (en) Third-party audio subsystem enhancement
US11983195B2 (en) Tokenized voice authenticated narrated video descriptions
WO2019052121A1 (en) Music identification system, method and apparatus, and music management server
JP2007292827A (en) Acoustic signal retrieving apparatus
JP5034599B2 (en) Music introduction sentence generation device, narration addition device, and program
KR20100130809A (en) Electronic commerce system of record by ordering based on sound recognition and user-authentication based on speech or image recognition
WO2023119629A1 (en) Information processing system, information processing method, recording medium, and data structure
US20240127833A1 (en) System and methods thereof for audio authentication
KR102559493B1 (en) Service providing server to provide the digital will service that can verify the authenticity of the voice and the operating method thereof
US11599915B1 (en) Apparatus, system, and method for audio based browser cookies
Alrumayh et al. Understanding and mitigating privacy leaks from third-party smart speaker apps
Selvakumar et al. Content recognition using audio finger printing
JP6169526B2 (en) Specific voice suppression device, specific voice suppression method and program
CN116975823A (en) Data processing method, device, computer equipment, storage medium and product
CN113407768A (en) Voiceprint retrieval method, device, system, server and storage medium
JP2002297153A (en) System and device for music data distribution, communication device, music reproducing device, computer program, and recording medium
KR20190066640A (en) Method and apparatus of editing a music file recorded in a karaoke room
WO2014159854A1 (en) Method and apparatus for simulating a voice

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: 18855691

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18855691

Country of ref document: EP

Kind code of ref document: A1