Audio recognition method and device, electronic equipment and storage medium

Abstract

The invention relates to an audio recognition method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-recognized target audio; obtaining a target multimedia matched with the target audio; wherein the target multimedia at least comprises multimedia obtained by identifying the target audio and multimedia in a target multimedia library; and obtaining an identification result of whether the target audio is spliced audio data based on the target multimedia. The target multimedia is obtained by at least identifying the target audio and the multimedia in the target multimedia library, so that the target audio to be identified can be accurately identified when the target audio is obtained by splicing the original edition audio through turning and singing or modifying and the like.

Description

Technical Field

[0001] The present disclosure relates to the technical field of audio recognition, and in particular to an audio recognition method, device, electronic device and storage medium. Background Art

[0002] As mobile phones and other terminals become more popular, many users are used to listening to their favorite music through their mobile phones. Some users will splice several songs together to create a spliced ​​song, such as a medley, and upload the spliced ​​song to the platform to make profits.

[0003] When identifying spliced ​​songs, the related technology usually uses fingerprint recognition and other methods for detection. If the spliced ​​audio frequency band does not belong to the original song, the recognition is likely to fail, resulting in low efficiency in identifying spliced ​​songs in the related technology. Summary of the invention

[0004] The present disclosure provides an audio recognition method, device, electronic device and storage medium.

[0005] According to one aspect of the present disclosure, there is provided an audio recognition method, the method comprising:

[0006] Obtain the target audio to be recognized;

[0007] Acquire target multimedia matching the target audio; wherein the target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in a target multimedia library;

[0008] A recognition result of whether the target audio is spliced ​​audio data is obtained based on the target multimedia.

[0009] According to another aspect of the present disclosure, there is provided an audio recognition device, the device comprising:

[0010] An audio acquisition module, used to acquire the target audio to be recognized;

[0011] A multimedia acquisition module, used for acquiring target multimedia matching the target audio; wherein the target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in a target multimedia library;

[0012] A result determination module is used to obtain a recognition result of whether the target audio is spliced ​​audio data based on the target multimedia.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0014] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above method of the present disclosure is implemented.

[0015] The audio recognition method, device, electronic device, and storage medium provided by the embodiments of the present disclosure can obtain a recognition result of whether the target audio to be recognized is spliced ​​audio data based on the target multimedia by acquiring the target audio to be recognized and obtaining the target multimedia that matches the target audio. Since the target multimedia at least includes the target audio and the multimedia in the target multimedia library, when the target audio is obtained by splicing the original audio through a cover or adaptation, the target audio to be recognized can be accurately recognized. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Further details, features and advantages of the present disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic diagram of a scenario provided for an exemplary embodiment of the present disclosure;

[0018] Figure 2 A flowchart of an audio recognition method provided for an exemplary embodiment of the present disclosure;

[0019] Figure 3 A schematic block diagram of functional modules of an audio recognition device provided by an exemplary embodiment of the present disclosure;

[0020] Figure 4 A structural block diagram of an electronic device provided for an exemplary embodiment of the present disclosure;

[0021] Figure 5 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0023] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0024] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0025] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0026] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0027] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0028] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0029] As an optional but non-limiting implementation, in response to receiving an active request from the user, the method of sending a prompt message to the user may be, for example, a pop-up window, in which the prompt message may be presented in text. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device. It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0030] Since the relevant technology usually directly detects whether the song to be identified is a spliced ​​song through fingerprint recognition, if the song to be identified is a cover or changed song, this method in the relevant technology will not be able to identify it, and the recognition efficiency of the spliced ​​song will be low.

[0031] Therefore, in the embodiment of the present disclosure, in order to improve the recognition rate of the audio to be recognized and accurately determine whether the audio to be recognized is a spliced ​​audio based on the existing audio, a multimedia pool is first established for the target audio to be recognized in the embodiment of the present disclosure. It should be noted that the target audio can be audio data such as songs, operas, or crosstalk. The embodiment is described by taking the target audio including songs as an example, but the embodiment is not limited thereto.

[0032] In an embodiment, a target multimedia library may be obtained, and the target multimedia library may include multiple multimedia, and the multimedia may be audio, or may be data such as audio and video, and the multimedia may carry at least audio data. For example, for a certain platform, the target multimedia library may be a database with corresponding copyright on the platform. In order to determine whether the data containing audio uploaded by other users is a combination of several multimedia in the target multimedia library, it is necessary to detect the data containing audio uploaded by the user to avoid the situation where the data containing audio uploaded by the user infringes the copyright of multimedia created by other users in the target multimedia library.

[0033] First, in the embodiment, the target audio to be identified can be compared with the multimedia in the target multimedia library, and multimedia with a certain degree of similarity to the target audio can be obtained by fingerprint recognition, and the obtained multimedia can be added to the multimedia pool. For example, the target audio can be compared with the multimedia in the target multimedia library in pairs, and fingerprint scores after the pairwise comparison can be obtained, and multimedia with fingerprint scores greater than a certain threshold can be added to the multimedia pool.

[0034] Specifically, the fingerprint features of the target audio can be extracted, and the fingerprint features of each multimedia in the target multimedia library can be extracted respectively, and the above-mentioned fingerprint score can be obtained by comparing the fingerprint features. For example, the greater the similarity between the two, the higher the fingerprint score obtained. In this way, the multimedia with a fingerprint score greater than a certain threshold is multimedia that is similar to the target audio through fingerprint identification.

[0035] Secondly, the target audio to be identified can also be compared with the multimedia in the target multimedia library, and multimedia with a certain similarity to the target audio can be obtained by audio recognition, and the obtained multimedia can be added to the multimedia pool. For example, the target audio can be compared with the multimedia in the multimedia library in pairs, and the cover scores after the pairwise comparison can be obtained, and the multimedia with a cover score greater than a certain threshold can be added to the multimedia pool. It should be noted that the audio recognition method in the embodiment can specifically be cover recognition, and the embodiment is described by taking cover recognition as an example, and the embodiment is not limited to this.

[0036] Specifically, the cover features of the target audio can be extracted, and the cover features of each multimedia in the target multimedia library can be extracted respectively, and the above-mentioned cover score can be obtained by comparing the cover features. For example, the greater the similarity between the two, the higher the cover score obtained. In this way, the multimedia with a cover score greater than a certain threshold belongs to the multimedia that is similar to the target audio through cover identification. Among them, the cover feature can be at least one of pitch, tone, rhythm and timbre. For example, when a user adapts a song to an Rmix version, or changes the speed and tone, or increases or decreases the tone, or when different people cover the song, the cover identification can be performed based on the above-mentioned cover features to determine whether the song is obtained by covering other songs.

[0037] Thirdly, the target audio may be sliced ​​to obtain multiple slices, and the multiple slices may be compared with the multimedia in the target multimedia library, and multimedia with a certain degree of similarity to the corresponding slices may be obtained by cover song recognition, and the obtained multimedia may be added to the multimedia pool. For example, the slices may be compared with the multimedia in the target multimedia library in pairs, and the cover song scores after the pairwise comparison may be obtained, and multimedia with a cover song score greater than a certain threshold may be added to the multimedia pool.

[0038] The multimedia obtained in the above manner is added to the multimedia pool, and multiple multimedia contained in the multimedia pool can be obtained. Since the multimedia in the multimedia pool may contain other data, it is necessary to filter the multimedia in the multimedia pool to remove some multimedia to avoid interference caused by other data and improve the matching efficiency of the target audio to be identified and the multimedia in the multimedia pool.

[0039] For example, when matching multimedia in the multimedia pool with the target audio, multimedia whose matching duration accounts for 50% of the target audio duration can be retained. For example, when the target audio is a song, this can prevent the existence of a medley of songs in the multimedia pool. In an embodiment, when the matching duration overlap between any two multimedia in the multimedia pool reaches a certain threshold, such as when the overlap reaches more than 50%, only the multimedia with the highest fingerprint score or cover score in the two multimedia can be retained. For example, if it is recognized that the multimedia pool includes 2 different versions of song A, only the version of song A with the highest score can be retained.

[0040] The multimedia in the multimedia pool may be further filtered by target audio, which may include the following methods:

[0041] a) If there is multimedia in the multimedia pool that contains characters less than a certain threshold, the multimedia is excluded from the multimedia pool. For example, if there is multimedia in the multimedia pool that has a corresponding number of lyrics less than P, then the multimedia is removed from the multimedia pool, where P is a positive integer.

[0042] b) If there is multimedia in the multimedia pool that matches the last Q seconds of the target audio, then the multimedia is excluded from the multimedia pool. In the embodiment, if the multimedia matches the last few seconds of the target audio, it may be caused by a watermark problem in the data, and the multimedia needs to be excluded, where Q is a positive integer.

[0043] c) When there is multimedia in the multimedia pool that is obtained by cover recognition with the target audio, if the longest identical part between the multimedia and the target audio has less than M characters, the multimedia is excluded from the multimedia pool. For example, if the multimedia recalled by cover recognition based on the target audio in the target multimedia library has less than M characters in the longest identical part of the lyrics between the multimedia and the target audio, the multimedia is excluded from the multimedia library. Where M is a positive integer.

[0044] d) When there is multimedia in the multimedia pool obtained by fingerprint identification with the target audio, if the longest identical part between the multimedia and the target audio has less than N characters, the multimedia is excluded from the multimedia pool. For example, if the multimedia recalled by fingerprint identification in the target multimedia library based on the target audio has less than N characters in the longest identical part of the lyrics between the multimedia and the target audio, the multimedia is excluded from the multimedia library. Where N is a positive integer, and N is less than M.

[0045] e) When there is a multimedia with X characters at the beginning of the same as the target audio in the multimedia pool, the multimedia is excluded from the target multimedia pool. For example, if there are X lyrics at the beginning of the same as the target audio in the target multimedia pool, the target multimedia is excluded from the target multimedia pool. Where X is a positive integer.

[0046] In the embodiment, if the number of characters of the target audio is less than Y, the target audio may not be judged as the spliced ​​audio data. For example, if the number of lyrics corresponding to the target audio is less than Y, no judgment may be made because the number of lyrics is too small, otherwise it may be meaningless. Wherein, Y is a positive integer and can be set as needed.

[0047] In the embodiment provided by the present disclosure, after filtering the multimedia in the multimedia pool in the above manner, if there are at least two multimedia in the multimedia pool, the multimedia in the multimedia pool can be matched two by two, and if there are target multimedia in the multimedia pool that meets the following conditions, the target audio to be identified can be determined to be spliced ​​audio data.

[0048] 1) The longest number of characters that are the same between any two multimedia is less than M. For example, the longest number of lyrics that are the same between any two multimedia is less than M.

[0049] 2) Any two multimedia are not each other's cover data, for example, any two multimedia are not each other's cover songs, and the cover recognition scores of the two are less than a certain threshold.

[0050] 3) The names of any two multimedia are different. For example, the song names of any two multimedia are different.

[0051] In the embodiments provided in the present disclosure, if the target audio to be identified is determined to be spliced ​​audio data, such as a spliced ​​song, then the composition information of the target audio can be provided by the target multimedia in the multimedia pool. The composition information may include the proportion order and proportion duration of the target multimedia that constitute each part of the target audio.

[0052] For example, Figure 1 As shown, the target audio is spliced ​​by target multimedia A, target multimedia B and target multimedia C. Taking the target multimedia as songs as an example, the sequential proportions of the three songs that make up the target audio in the 280s target audio can be obtained.

[0053] Based on the above embodiments, the present disclosure first provides an audio recognition method, such as Figure 2 As shown, the method may include the following steps:

[0054] In step S210, the target audio to be recognized is obtained.

[0055] In an embodiment, the target audio to be identified may be an audio work such as a song, a drama, or a cross talk. The target audio may also be audio extracted from a video, for example, the target audio may be extracted from a MV (Music Video), so as to facilitate identification of the target audio.

[0056] In step S220, target multimedia matching the target audio is acquired.

[0057] In step S230, a recognition result of whether the target audio is spliced ​​audio data is obtained based on the target multimedia.

[0058] The target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in the target multimedia library.

[0059] In the embodiment, the target audio is identified with the multimedia in the target multimedia database, which can be specifically the cover song identification in the above embodiment. By performing cover song identification on the target audio and the multimedia in the target database respectively, the multimedia whose cover song identification score is greater than a certain threshold value can be added to the multimedia pool, and the target audio and the multimedia in the target database can also be fingerprinted respectively, and the multimedia whose fingerprint identification score is greater than a certain threshold value is added to the multimedia pool, and the target multimedia matching the target audio can be obtained by filtering the multimedia in the multimedia pool. In the embodiment, the multimedia obtained by at least one of the cover song identification mode and the fingerprint identification mode can also be directly used as the target multimedia, and the embodiment is not limited to this.

[0060] It should be noted that the target multimedia library in the embodiment can be, for example, a database including various songs on the platform, or a hot song library, which can be the top Z songs on the charts of the day or within a period of time. Since some users can take advantage of the hot spots, they can splice and upload the more popular songs to the platform and make a profit. Therefore, the target audio can be matched with the songs in the hot song library to improve the recognition efficiency of the target audio. If there is no song matching the target audio in the hot song library, it can be further matched in the total song library.

[0061] In the embodiment, if the target multimedia matching the target audio is obtained, it can be determined that the target audio is the spliced ​​audio data. Otherwise, if the target multimedia matching the target audio is not obtained, it can be determined that the target audio is not the spliced ​​audio data.

[0062] The audio recognition method provided by the embodiment of the present disclosure can obtain a recognition result of whether the target audio to be recognized is spliced ​​audio data based on the target multimedia by obtaining the target audio to be recognized and obtaining the target multimedia that matches the target audio. Since the target multimedia at least includes the target audio and multimedia in the target multimedia library being recognized by cover singing, when the target audio is obtained by splicing the original audio through cover singing or adaptation, the target audio to be recognized can also be accurately recognized.

[0063] In order to accurately obtain the target multimedia that matches the target audio data to be identified, a multimedia pool can be established, and the multimedia in the multimedia pool can be filtered. Therefore, based on the above embodiment, in another embodiment provided by the present disclosure, the method can also include the following steps:

[0064] Step S240: establishing a multimedia pool.

[0065] The multimedia pool includes a plurality of multimedia obtained from a target multimedia library and matching the target audio.

[0066] In an embodiment, the target audio to be identified may be compared with multimedia in a target multimedia library. For example, multimedia having a certain degree of similarity with the target audio may be obtained by cover song recognition, and the obtained multimedia may be added to the multimedia pool.

[0067] Specifically, the target feature of the target audio can be extracted, and the target feature can be used to identify the cover version based on the target multimedia library, and the multimedia whose audio similarity of the cover version is greater than the second target threshold can be added to the multimedia pool. The target feature can include at least one of pitch, tone, rhythm and timbre. In this way, when the original song is changed or covered, the target audio can be accurately identified through the target feature.

[0068] In an embodiment, the target audio may be sliced ​​to obtain multiple slices. Cover recognition is performed on the multiple slices based on the target multimedia library, and multimedia in the target multimedia library that meets the target condition is added to the multimedia pool. The target condition may include at least one of: the audio similarity of the cover recognition is greater than the first target threshold and the matching duration is greater than the first duration.

[0069] Specifically, the target audio can be sliced ​​to obtain multiple slices, and the multiple slices can be compared with the multimedia in the target multimedia library respectively. Multimedia with a certain audio similarity to the corresponding slice can be obtained through cover recognition, and the obtained multimedia can be added to the multimedia pool.

[0070] In the embodiment, the target audio to be identified can also be compared with the multimedia in the target multimedia library, and multimedia with a certain degree of similarity to the target audio can be obtained by fingerprint recognition, and the obtained multimedia can be added to the multimedia pool. For example, the target audio can be compared with the multimedia in the target multimedia library in pairs, and fingerprint scores after the pairwise comparison can be obtained, and multimedia with fingerprint scores greater than a certain threshold can be added to the multimedia pool.

[0071] Specifically, the fingerprint features of the target audio can be extracted, and the fingerprint features can be fingerprinted based on the target multimedia library, and multimedia with fingerprint recognition similarity greater than the third target threshold can be added to the multimedia pool. It should be noted that the threshold data such as the first target threshold, the second target threshold, and the third target threshold in the embodiment can be set according to actual needs, and the embodiment is not limited thereto.

[0072] By matching the multimedia through the above-mentioned fingerprint recognition and cover recognition, the multimedia included in the established multimedia pool can achieve more comprehensive coverage. Not only can it match the multimedia directly obtained by splicing, but it can also match the multimedia obtained by cover or change, thereby accurately determining whether the target audio is spliced ​​audio data.

[0073] Step S250: filtering the multimedia in the multimedia pool to obtain a multimedia pool containing the target multimedia.

[0074] In an embodiment, since the multimedia pool including multiple multimedia obtained in the above manner may include useless or irrelevant data, the multimedia in the multimedia pool may be filtered to improve the accuracy of target audio recognition.

[0075] In an embodiment, the overlap between any two multimedia in the multimedia pool can be obtained, and when the overlap is greater than the overlap threshold, the multimedia with the lowest target score among the two multimedia is removed. The target score represents the similarity between the multimedia and the target audio.

[0076] Specifically, for example, when matching multimedia in the multimedia pool with the target audio, multimedia whose matching duration accounts for 50% of the target audio duration is retained. In this way, when the target audio is a song, it is possible to prevent the existence of medley songs in the multimedia pool. In an embodiment, when the matching duration overlap between any two multimedia in the multimedia pool reaches a certain threshold, for example, the overlap reaches more than 50%, only the multimedia with the highest fingerprint score or cover score in the two multimedia can be retained. For example, if it is identified that the multimedia pool includes 3 songs with the same name but different versions, only the song with the highest score can be retained.

[0077] When filtering multimedia in the multimedia pool, the multimedia to be filtered in the multimedia pool may also be filtered based on the target audio, which may specifically include the following methods:

[0078] When the multimedia to be filtered is obtained based on cover recognition, a first number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the first number is less than a first preset number, the multimedia to be filtered is removed. Specifically, when there is multimedia obtained by fingerprint recognition with the target audio in the multimedia pool, if the longest identical part of the multimedia with the target audio has less than a certain number of characters, the multimedia can be excluded from the multimedia pool.

[0079] Alternatively, when the multimedia to be filtered is obtained based on fingerprint recognition, a second number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the second number is less than a second preset number, the multimedia to be filtered is removed. The second preset number is less than the first preset number. Specifically, when there is multimedia in the multimedia pool that is obtained by fingerprint recognition with the target audio, if the longest and identical part of the characters between the multimedia and the target audio is less than a certain number, the multimedia is excluded from the multimedia pool.

[0080] Alternatively, when the target audio data and the multimedia to be filtered have the same starting part with the same characters, the multimedia to be filtered is removed. The starting part includes the first preset number of characters. Specifically, when there is multimedia in the multimedia pool that has the same beginning as the target audio, the multimedia is excluded from the target multimedia pool. For example, if there are multiple lyrics in the target multimedia pool that have the same beginning as the target audio, the target multimedia is excluded from the target multimedia pool.

[0081] Alternatively, when the multimedia to be filtered is obtained by matching the data of the ending part with the target audio data, the multimedia to be filtered is removed. The data of the ending part represents the data of the preset time length before the end of the playback of the multimedia to be filtered. Specifically, if there is multimedia in the multimedia pool that matches the last few seconds of the target audio, then the multimedia can be excluded from the multimedia pool.

[0082] Based on the above embodiments, in another embodiment provided by the present disclosure, the above-mentioned target multimedia can be at least two, and any two target multimedia can be matched. When the number of identical characters between any two target multimedia is less than a third preset number, the audio similarity of cover recognition between any two target multimedia is less than a similarity threshold, and any two target multimedia have different names, the target audio can be confirmed as spliced ​​audio data.

[0083] When it is determined that the target audio to be identified is spliced ​​audio data, the information proportion of the target multimedia in the target audio can be obtained. The information proportion includes the proportion order and proportion duration of each target part of the target multimedia in the target multimedia. For example, when the target audio is a spliced ​​song or a medley song, the song composition information of the spliced ​​song or medley song can be obtained, such as Figure 1 As shown, it can show which songs the target audio is composed of, the proportion and order of each song in the target audio, etc.

[0084] In the case of dividing each functional module according to each function, an embodiment of the present disclosure provides an audio recognition device, which may be a server or a chip applied to a server. Figure 3 The following is a schematic block diagram of the functional modules of an audio recognition device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the audio recognition device comprises:

[0085] The audio acquisition module 10 is used to acquire the target audio to be recognized;

[0086] The multimedia acquisition module 20 is used to acquire target multimedia that matches the target audio; wherein the target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in a target multimedia library;

[0087] The result determination module 30 is used to obtain a recognition result of whether the target audio is spliced ​​audio data based on the target multimedia.

[0088] In another embodiment provided by the present disclosure, the device further includes:

[0089] A multimedia pool establishment module, used for establishing a multimedia pool; the multimedia pool includes a plurality of multimedia obtained from the target multimedia library and matching the target audio;

[0090] The filtering module is used to filter the multimedia in the multimedia pool to obtain a multimedia pool containing the target multimedia.

[0091] In another embodiment provided by the present disclosure, the device further includes:

[0092] A slicing module, used for slicing the target audio to obtain multiple slices;

[0093] The first identification module is used to identify the multiple slices based on the target multimedia library, and add multimedia that meets the target condition in the target multimedia library to the multimedia pool.

[0094] In another embodiment provided by the present disclosure, the target condition includes: the recognized audio similarity is greater than a first target threshold, and / or the matching duration is greater than a first duration.

[0095] In another embodiment provided by the present disclosure, the device further includes:

[0096] A target feature extraction module, used to extract the target features of the target audio;

[0097] The second recognition module is used to recognize the target feature based on the target multimedia library, and add multimedia with recognition similarity greater than a second target threshold into the multimedia pool.

[0098] In another embodiment provided by the present disclosure, the device further includes:

[0099] A fingerprint feature extraction module, used to extract fingerprint features of the target audio;

[0100] The fingerprint recognition module is used to perform fingerprint recognition on the fingerprint feature based on the target multimedia library, and add multimedia with fingerprint recognition similarity greater than a third target threshold into the multimedia pool.

[0101] In another embodiment provided by the present disclosure, the filtering module is specifically used for:

[0102] Obtaining the degree of overlap between any two multimedia in the plurality of multimedia;

[0103] When the overlap degree is greater than the overlap degree threshold, the multimedia with the lowest target score among the any two multimedia is removed; wherein the target score represents the similarity between the multimedia and the target audio.

[0104] In another embodiment provided by the present disclosure, the filtering module is specifically used for:

[0105] The multimedia to be filtered in the multimedia pool is filtered based on the target audio; wherein,

[0106] When the multimedia to be filtered is obtained based on recognition, a first number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the first number is less than a first preset number, the multimedia to be filtered is removed.

[0107] In another embodiment provided by the present disclosure, the filtering module may also be specifically used for:

[0108] When the multimedia to be filtered is obtained based on fingerprint recognition, a second number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the second number is less than a second preset number, the multimedia to be filtered is removed; wherein the second preset number is less than the first preset number;

[0109] In another embodiment provided by the present disclosure, the filtering module may also be specifically used for:

[0110] When the target audio data and the multimedia to be filtered have the same starting part of characters, the multimedia to be filtered is removed; the starting part includes the first preset number of characters;

[0111] In another embodiment provided by the present disclosure, the filtering module may also be specifically used for:

[0112] When the multimedia to be filtered is obtained by matching the data of the ending part with the target audio data, the multimedia to be filtered is removed; the data of the ending part represents the data of the preset time length before the multimedia to be filtered ends.

[0113] In another embodiment provided by the present disclosure, the number of the target multimedia is at least two; and the apparatus further includes:

[0114] A matching module, used for matching any two target multimedia;

[0115] A data determination module is used to confirm that the target audio is spliced ​​audio data when the number of identical characters between any two of the target multimedia is less than a third preset number, the audio recognition similarity between any two of the target multimedia is less than a similarity threshold, and the any two of the target multimedia have different names.

[0116] In another embodiment provided by the present disclosure, the device further includes:

[0117] The information acquisition module is used to obtain the information proportion of the target multimedia in the target audio; wherein the information proportion includes the proportion sequence and proportion duration of each target part of the target multimedia in the target multimedia.

[0118] The audio recognition device provided by the embodiment of the present disclosure can obtain a recognition result of whether the target audio to be recognized is spliced ​​audio data based on the target multimedia by acquiring the target audio to be recognized and obtaining the target multimedia matching the target audio. Since the target multimedia at least includes the target audio and the multimedia in the target multimedia library, when the target audio is obtained by splicing the original audio through a cover or adaptation, the target audio to be recognized can also be accurately recognized.

[0119] An embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory for storing instructions executable by the at least one processor; wherein the at least one processor is configured to execute the instructions to implement the above method disclosed in the embodiment of the present disclosure.

[0120] Figure 4 The structure diagram of an electronic device provided by an exemplary embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the electronic device 1800 includes at least one processor 1801 and a memory 1802 coupled to the processor 1801 , and the processor 1801 can execute corresponding steps in the above method disclosed in the embodiment of the present disclosure.

[0121] The processor 1801 may also be referred to as a central processing unit (CPU), which may be an integrated circuit chip having signal processing capabilities. Each step in the method disclosed in the embodiment of the present disclosure may be completed by an integrated logic circuit of hardware in the processor 1801 or by instructions in the form of software. The processor 1801 may be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present disclosure may be directly embodied as being executed by a hardware decoding processor, or may be executed by a combination of hardware and software modules in a decoding processor. The software module may be located in a memory 1802, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, or other mature storage media in the art. The processor 1801 reads the information in the memory 1802 and completes the steps of the method in combination with its hardware.

[0122] In addition, when various operations / processes according to the present disclosure are implemented by software and / or firmware, they can be transmitted from a storage medium or a network to a computer system having a dedicated hardware structure, such as Figure 5 The computer system 1900 shown is installed with the programs constituting the software. When the various programs are installed, the computer system can perform various functions, including the functions described above. Figure 5 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure.

[0123] Computer system 1900 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0124] like Figure 5 As shown, the computer system 1900 includes a computing unit 1901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1902 or a computer program loaded from a storage unit 1908 to a random access memory (RAM) 1903. In the RAM 1903, various programs and data required for the operation of the computer system 1900 can also be stored. The computing unit 1901, the ROM 1902, and the RAM 1903 are connected to each other via a bus 1904. An input / output (I / O) interface 1905 is also connected to the bus 1904.

[0125] A plurality of components in the computer system 1900 are connected to the I / O interface 1905, including: an input unit 1906, an output unit 1907, a storage unit 1908, and a communication unit 1909. The input unit 1906 may be any type of device capable of inputting information to the computer system 1900, and the input unit 1906 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 1907 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 1908 may include, but is not limited to, a disk, an optical disk. The communication unit 1909 allows the computer system 1900 to exchange information / data with other devices over a network such as the Internet, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0126] The computing unit 1901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1901 performs the various methods and processes described above. For example, in some embodiments, the above methods disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1900 via the ROM 1902 and / or the communication unit 1909. In some embodiments, the computing unit 1901 may be configured to perform the above methods disclosed in the embodiments of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0127] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the above method disclosed in the embodiment of the present disclosure.

[0128] The computer-readable storage medium in the disclosed embodiments may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. More specifically, the computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0130] The embodiments of the present disclosure further provide a computer program product, including a computer program, wherein when the computer program is executed by a processor, the above method disclosed in the embodiments of the present disclosure is implemented.

[0131] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0132] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0133] The modules, components or units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the names of the modules, components or units do not, in some cases, limit the modules, components or units themselves.

[0134] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0135] The above descriptions are only some embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, a technical solution formed by replacing the above features with the technical features with similar functions disclosed in the present disclosure (but not limited to).

[0136] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. An audio recognition method, characterized in that: The method comprises: Obtain the target audio to be recognized; Acquire target multimedia matching the target audio; wherein the target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in a target multimedia library; A recognition result of whether the target audio is spliced ​​audio data is obtained based on the target multimedia.

2. The method according to claim 1, characterized in that The method further comprises: Establishing a multimedia pool; the multimedia pool includes a plurality of multimedia obtained from the target multimedia library and matching the target audio; The multimedia in the multimedia pool is filtered to obtain a multimedia pool including the target multimedia.

3. The method according to claim 2, characterized in that The method further comprises: Slicing the target audio to obtain multiple slices; The multiple slices are identified based on the target multimedia library, and multimedia in the target multimedia library that meets the target condition is added to the multimedia pool.

4. The method according to claim 3, characterized in that: The target conditions include: the recognized audio similarity is greater than a first target threshold, and / or the matching duration is greater than a first duration.

5. The method according to claim 2, characterized in that: The method further comprises: Extracting target features of the target audio; The target feature is identified based on the target multimedia library, and multimedia with an identified audio similarity greater than a second target threshold is added to the multimedia pool.

6. The method according to claim 2, characterized in that The method further comprises: Extracting fingerprint features of the target audio; The fingerprint feature is fingerprint-identified based on the target multimedia library, and multimedia with a fingerprint identification similarity greater than a third target threshold is added to the multimedia pool.

7. The method according to claim 2, characterized in that: The filtering of multimedia in the multimedia pool includes: Obtaining the degree of overlap between any two multimedia in the plurality of multimedia; When the overlap degree is greater than the overlap degree threshold, the multimedia with the lowest target score among the any two multimedia is removed; wherein the target score represents the similarity between the multimedia and the target audio.

8. The method according to claim 2, characterized in that: The filtering of multimedia in the multimedia pool includes: The multimedia to be filtered in the multimedia pool is filtered based on the target audio; wherein, When the multimedia to be filtered is obtained based on recognition, a first number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the first number is less than a first preset number, the multimedia to be filtered is removed.

9. The method according to claim 2, characterized in that: The filtering of multimedia in the multimedia pool includes: When the multimedia to be filtered is obtained based on fingerprint recognition, a second number of identical characters between the target audio and the multimedia to be filtered is obtained, and when the second number is less than a second preset number, the multimedia to be filtered is removed; wherein the second preset number is less than the first preset number.

10. The method according to claim 2, characterized in that The filtering of multimedia in the multimedia pool includes: When the target audio data and the multimedia to be filtered have a starting part with the same characters, the multimedia to be filtered is removed; the starting part includes a first preset number of characters.

11. The method according to claim 2, characterized in that The filtering of multimedia in the multimedia pool includes: When the multimedia to be filtered is obtained by matching the data of the ending part with the target audio data, the multimedia to be filtered is removed; the data of the ending part represents the data of the preset time length before the multimedia to be filtered ends.

12. The method according to claim 1, characterized in that The number of the target multimedia is at least two; the method further comprises: Matching any two of the target multimedia; When the number of identical characters between any two of the target multimedia is less than a third preset number, the recognition similarity between any two of the target multimedia is less than a similarity threshold, and the any two of the target multimedia have different names, the target audio is confirmed to be spliced ​​audio data.

13. The method according to any one of claims 1 to 9, characterized in that: The method further comprises: Obtain the information proportion of the target multimedia in the target audio; wherein the information proportion includes the proportion sequence and proportion duration of each target part of the target multimedia in the target multimedia.

14. An audio recognition device, characterized in that: The device comprises: An audio acquisition module, used to acquire the target audio to be recognized; A multimedia acquisition module, used for acquiring target multimedia matching the target audio; wherein the target multimedia at least includes multimedia obtained by identifying the target audio with multimedia in a target multimedia library; A result determination module is used to obtain a recognition result of whether the target audio is spliced ​​audio data based on the target multimedia.

15. An electronic device, characterized in that: include: at least one processor; a memory for storing the at least one processor-executable instruction; The at least one processor is configured to execute the instructions to implement the method according to any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the method as claimed in any one of claims 1 to 13.

Images