Reversed song identification method and device, electronic equipment, storage medium and product

Abstract

The invention relates to the technical field of information retrieval, and discloses a turning song recognition method and device, electronic equipment, a storage medium and a product, and the method comprises the steps: obtaining a first refrain lyric of a to-be-recognized song and a second refrain lyric of a target song; performing text matching on the first refrain lyrics and the second refrain lyrics to obtain refrain similarity between the to-be-recognized song and the target song; and determining a singing recognition result according to the refrain similarity, wherein the singing recognition result represents whether the song to be recognized belongs to a singing song of the target song. According to the invention, the misjudgment rate of song turning and singing can be effectively reduced, and the accuracy of song turning and singing judgment is improved.

Description

Technical Field

[0001] This invention relates to the field of information retrieval technology, specifically to methods, devices, electronic devices, storage media, and products for identifying cover songs. Background Technology

[0002] In related technologies, song cover identification is mainly performed by judging whether the lyrics of two songs contain the same lyrics. In this method, when both songs contain the same common phrases in their lyrics, they are easily identified as cover songs, but are not actually cover songs. Conversely, when a cover song only slightly modifies the core phrases of the original song's lyrics, but the actual meaning of the lyrics remains unchanged, it is easily identified as a non-cover song, but is actually a cover song.

[0003] Therefore, the song cover recognition methods of related technologies have serious misjudgments, resulting in a low accuracy rate for song cover recognition. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, storage medium, and product for identifying cover songs, in order to improve the problem of low accuracy in cover song recognition in related technologies.

[0005] In a first aspect, the present invention provides a method for identifying cover songs, the method comprising: Obtain the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song; The lyrics of the first chorus are matched with the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song. The cover song recognition result is determined based on the chorus similarity, and the cover song recognition result indicates whether the song to be identified is a cover song of the target song.

[0006] In one optional implementation, the step of performing text matching between the first chorus lyrics and the second chorus lyrics to obtain the chorus similarity between the song to be identified and the target song includes: The lyrics of the first chorus are divided into multiple consecutive phrase segments to obtain the first phrase segment sequence; The lyrics of the second chorus are divided into multiple consecutive phrase segments to obtain a sequence of second phrase segments; The similarity between each first sentence segment subsequence in the first sentence segment sequence and the second sentence segment sequence is obtained respectively, and each first sentence segment subsequence includes multiple consecutive sentence segments in the lyrics of the first chorus; The highest similarity score obtained is taken as the chorus similarity score.

[0007] In an optional implementation, obtaining the similarity between each first clause segment subsequence in the first clause segment sequence and the second clause segment sequence includes: Based on the sliding window algorithm, each subsequence of the first sentence segment in the first sentence segment sequence is traversed sequentially through the sliding window; A preset text similarity algorithm is used to obtain the similarity between the first sentence segment subsequence currently traversed by the sliding window and the second sentence segment sequence.

[0008] In one optional implementation, the text similarity algorithm includes a string edit distance algorithm; the step of using a preset text similarity algorithm to obtain the similarity between the first sentence segment subsequence currently traversed by the sliding window and the second sentence segment sequence includes: The string edit distance algorithm is used to obtain the edit distance between the string of the first clause segment subsequence currently traversed by the sliding window and the string of the second clause segment sequence; The similarity is obtained based on the edit distance, the string length of the first clause segment subsequence currently traversed, and the string length of the second clause segment sequence.

[0009] In one optional implementation, determining the cover song recognition result based on the chorus similarity includes: In response to the chorus similarity being greater than or equal to a first preset threshold, the song to be identified is determined to be a cover of the target song, and the cover recognition result is obtained.

[0010] In one optional implementation, determining the cover song recognition result based on the chorus similarity includes: In response to the chorus similarity being less than a first preset threshold and greater than or equal to a second preset threshold, the lyrics of the first chorus and the lyrics of the second chorus are input into a preset large model for cover song analysis to obtain the cover song recognition result.

[0011] In one optional implementation, obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song includes: The chorus position of the song to be identified is identified from the audio of the song to be identified using an audio-based chorus extraction algorithm, and the chorus position of the target song is identified from the audio of the target song. The lyrics of the first chorus are extracted based on the position of the chorus of the song to be identified; The lyrics of the second chorus are extracted based on the position of the chorus in the target song.

[0012] In one optional implementation, obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song includes: The first chorus lyrics are identified from the lyrics information of the song to be identified using a text-based chorus extraction algorithm. The lyrics of the second chorus are identified from the lyrics information of the target song.

[0013] Secondly, the present invention provides a cover song recognition device, the cover song recognition device comprising: The acquisition module is used to acquire the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song; The matching module is used to perform text matching between the lyrics of the first chorus and the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song; The identification module is used to determine the cover song identification result based on the chorus similarity, wherein the cover song identification result indicates whether the song to be identified is a cover song of the target song.

[0014] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the cover song recognition method of the first aspect or any corresponding embodiment described above.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the cover song recognition method described in the first aspect or any corresponding embodiment thereof.

[0016] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the cover song recognition method described in the first aspect or any corresponding embodiment thereof.

[0017] The cover song identification method, apparatus, electronic device, storage medium, and product according to embodiments of the present invention obtain the chorus lyrics of a song to be identified and a target song, perform text matching using the chorus lyrics of the two songs to obtain chorus similarity, and identify whether the song to be identified is a cover of the target song based on the chorus similarity. This can effectively reduce the false positive rate of cover songs, improve the accuracy of judging cover songs, reduce the cost of manual review, improve song operation efficiency, and help improve the accuracy and efficiency of song infringement determination, providing an efficient basis for song infringement determination. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram illustrating an application scenario of an embodiment of the present invention; Figure 2 A flowchart illustrating a method for identifying cover songs provided in an embodiment of the present invention; Figure 3 This is a flowchart illustrating a method for obtaining chorus lyrics in an embodiment of the present invention; Figure 4 This is a flowchart illustrating another method for obtaining chorus lyrics in an embodiment of the present invention; Figure 5 This is a flowchart illustrating a method for obtaining chorus similarity in an embodiment of the present invention; Figure 6 This is a structural block diagram of a cover song recognition device provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0022] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0023] Figure 1This is a schematic diagram of one application scenario of the present invention. As an optional application scenario of the present invention, such as... Figure 1 As shown, application 101 is installed in terminal device 110, and user 130 can interact with application 101 through terminal device 110 and / or access device of terminal device 110.

[0024] For example, application 101 can be any application that provides song cover recognition services. Figure 1 In the application scenario shown, if application 101 is active, the terminal device 110 can display the interface 102 of application 101. The interface 102 may include various pages that application 101 can provide, such as interactive pages, settings pages, query pages, etc.

[0025] In some embodiments, terminal device 110 is communicatively connected to server 120 to provide services to application 101. Terminal device 110 may be a mobile terminal, fixed terminal, or portable terminal, etc., including but not limited to mobile phones, desktop computers, laptop computers, multimedia tablets, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 may also support any type of interface, and server 120 may be various types of computing systems or servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0026] It should be noted that, Figure 1 This is merely an example of an application scenario and does not limit the scope of protection of this invention.

[0027] The embodiments of the present invention will now be described with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations; one or more elements may be omitted or replaced, and one or more other elements may also be present; no limitations are imposed in the embodiments of the present invention. Furthermore, the embodiments described below primarily pertain to terminal device 110. It should be understood that the actions described relative to terminal device 110 can be performed by application 101 on terminal device 110, or can be performed by application 101 in conjunction with its server (e.g., server 120).

[0028] This invention provides a method for identifying song covers. By extracting the chorus lyrics of the song to be identified and the target song, and performing text matching using the chorus lyrics of the two songs to obtain chorus similarity, the method identifies whether the song to be identified is a cover of the target song based on the chorus similarity. This method can effectively reduce the false positive rate of cover songs, improve the accuracy of judging cover songs, reduce the cost of manual review, improve the efficiency of song operation, and help improve the accuracy and efficiency of song infringement determination, providing an efficient basis for song infringement determination.

[0029] According to an embodiment of the present invention, a method for identifying cover songs is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This invention provides a method for recognizing song covers, which can be used in the aforementioned terminal devices or servers. Figure 2 This is a flowchart illustrating a method for identifying cover songs provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the method for identifying cover songs includes the following steps.

[0031] Step S201: Obtain the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song.

[0032] In this embodiment of the invention, lyrics are the textual content contained in a song, typically written by a lyricist and composer. Lyrics are sung with a certain musical rhythm and melody, expressing emotions, viewpoints, storylines, or themes through language. Lyrics play a crucial role in the understanding and expression of a song; they allow listeners to better understand the song's meaning, resonate with it, and together with the music, constitute a complete work of art.

[0033] The chorus is a fixed, repetitive section of a song's lyrics, usually serving as the climax of the song. It is repetitive and summarizing. The structural characteristics of the chorus are: 1. Repetition: The chorus appears multiple times throughout the song; 2. Conciseness: The chorus is typically short and refined; 3. Summarization: It summarizes the narrative content of the verses. Through repetition, summarization, and emotional reinforcement, the chorus becomes the core vehicle for the song's communication.

[0034] A cover song is a reinterpretation of an original song. It usually retains the melody and lyrics of the original song, or only slightly adjusts some of the melody and lyrics, and presents a new version of the song through different singing techniques, arrangement styles or timbre.

[0035] The target song is the original song, and the song to be identified is a cover song that needs to be identified as belonging to the original song.

[0036] Step S202: Perform text matching between the lyrics of the first chorus and the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song.

[0037] In this embodiment of the invention, the text similarity between the lyrics of the first chorus and the lyrics of the second chorus is obtained by text matching, and is used as the chorus similarity between the song to be identified and the target song. The chorus similarity indicates the degree of similarity between the chorus of the song to be identified and the chorus of the target song.

[0038] Step S203: Determine the cover song recognition result based on the chorus similarity. The cover song recognition result indicates whether the song to be identified is a cover of the target song.

[0039] In this embodiment of the invention, the similarity of the chorus between the song to be identified and the target song is used as the basis for determining whether the song to be identified is a cover song of the target song based on the similarity of the chorus, and the cover song identification result is obtained.

[0040] The cover song identification method provided by the present invention extracts the chorus lyrics of the song to be identified and the target song, performs text matching using the chorus lyrics of the two songs to obtain chorus similarity, and identifies whether the song to be identified is a cover of the target song based on the chorus similarity. This method can effectively reduce the misjudgment rate of cover songs, improve the accuracy of judging cover songs, reduce the cost of manual review, improve the efficiency of song operation, and help improve the accuracy and efficiency of song infringement determination, thus providing an efficient basis for song infringement determination.

[0041] Figure 3 This is a flowchart illustrating a method for obtaining chorus lyrics in an embodiment of the present invention. In some optional implementations, such as... Figure 3 As shown, in step S201 above, obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song may further include: steps S301 to S303.

[0042] Step S301: Using a preset audio-based chorus extraction algorithm, identify the chorus position of the song to be identified from the audio of the song to be identified, and identify the chorus position of the target song from the audio of the target song.

[0043] The chorus of a song typically features high repetition, long intervals, and prominent melodic characteristics. Audio-based chorus extraction algorithms can locate the chorus in a song's audio by analyzing repetition patterns. For example, they can determine the chorus's position by calculating the similarity between audio segments and identifying segments that repeat frequently with large intervals.

[0044] In some alternative implementations, the start and end positions of the chorus can be determined by combining the song's lyrics timeline information with an audio-based chorus extraction algorithm. The chorus position includes the start and end positions of the chorus.

[0045] Step S302: Extract the lyrics of the first chorus based on the position of the chorus of the song to be identified.

[0046] After determining the position of the chorus of the song to be identified, the lyrics of the first chorus are extracted from the audio or lyrics information of the song to be identified based on the chorus position.

[0047] Step S303: Extract the lyrics of the second chorus based on the position of the chorus in the target song.

[0048] After determining the position of the chorus in the target song, the lyrics of the second chorus are extracted from the audio or lyrics information of the target song based on the chorus position.

[0049] By using an audio-based chorus extraction algorithm to extract chorus lyrics, the position of the chorus in a song can be accurately analyzed, thereby accurately extracting the chorus lyrics.

[0050] Figure 4 This is a flowchart illustrating another method for obtaining chorus lyrics in an embodiment of the present invention. In some optional implementations, such as... Figure 4 As shown, in step S201 above, obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song may further include: steps S401 to S402.

[0051] Step S401: The lyrics of the first chorus are identified from the lyrics information of the song to be identified using a text-based chorus extraction algorithm.

[0052] Step S402: Identify the lyrics of the second chorus from the lyrics information of the target song.

[0053] Text-based chorus extraction algorithms can locate the chorus lyrics by searching for the longest and most frequently occurring consecutive string in the lyrics information through text retrieval. The corresponding paragraph is the chorus lyrics.

[0054] In some alternative implementations, before obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song, the cover song identification method may further include: obtaining the audio and / or lyrics information of the song to be identified input by the user, and the audio and / or lyrics information of the target song.

[0055] In some optional implementations, before obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song, the cover song identification method may further include: preprocessing the lyrics information of the song to be identified and the lyrics information of the target song, including but not limited to: special word filtering, specific symbol filtering and lyrics timeline information filtering.

[0056] Special words may include, but are not limited to: lyric information, composition information, arrangement information, performance information, instrument information, etc. Specific symbols may include, but are not limited to: parentheses in lyrics, special characters, etc.

[0057] It should be noted that the embodiments of the present invention do not impose special restrictions on the implementation method of preprocessing. For example, regular expressions can be used to preprocess special words, specific symbols and lyric timeline information in the lyrics information.

[0058] Before extracting the lyrics of the chorus of a song for text matching, preprocessing the lyrics information can help reduce the interference caused by invalid content in the lyrics to the text matching.

[0059] Figure 5 This is a flowchart illustrating a method for obtaining chorus similarity in an embodiment of the present invention. In some optional implementations, such as... Figure 5 As shown, in step S202 above, the lyrics of the first chorus and the lyrics of the second chorus are matched to obtain the chorus similarity between the song to be identified and the target song. This may further include steps S501 to S504.

[0060] Step S501: Divide the lyrics of the first chorus into multiple consecutive phrase segments to obtain the sequence of the first phrase segments.

[0061] In the first sentence segment sequence, each sentence segment is arranged in chronological order according to the timeline in the first chorus lyrics.

[0062] Step S502: Divide the lyrics of the second chorus into multiple consecutive phrase segments to obtain the second phrase segment sequence.

[0063] In the second sentence segment sequence, the sentence segments are arranged in chronological order according to the timeline in the lyrics of the second chorus.

[0064] In some alternative implementations, the lyrics of the chorus of a song are usually composed of multiple phrases, and multiple consecutive phrase segments in the chorus lyrics can be obtained by segmenting the chorus lyrics into phrases.

[0065] In some alternative implementations, text segmentation tools can be used to identify individual clauses in the chorus lyrics according to punctuation marks, paragraphs, spaces, line breaks, etc., thereby dividing the lyrics into multiple consecutive clause segments.

[0066] Step S503: Obtain the similarity between each first sentence segment subsequence and the second sentence segment sequence in the first sentence segment sequence. Each first sentence segment subsequence includes multiple consecutive sentence segments from the lyrics of the first chorus.

[0067] In some optional implementations, the number of sentence segments in the second sentence segment sequence can be used as the division length of the subsequence. Each first sentence segment subsequence of the corresponding length is selected from the first sentence segment sequence. The first sentence segment subsequence includes multiple consecutive sentence segments from the lyrics of the first chorus. The number of sentence segments in each first sentence segment subsequence is the same as the number of sentence segments in the second sentence segment sequence. There may be repeated sentence segments between different first sentence segment subsequences, and there must be at least one different sentence segment.

[0068] For example, the lyrics of the first chorus are "Write this feeling into a photo; No need to doubt, the love I give you; I'm not too bad; I won't let you keep waiting; You're my type; The reliance I most want to have; Don't be surprised; Intoxicated by a future with only you," which contains eight consecutive clause segments. The sequence of the first clause segment can be represented as {Write this feeling into a photo; No need to doubt, the love I give you; I'm not too bad; I won't let you keep waiting; You're my type; The reliance I most want to have; Don't be surprised; Intoxicated by a future with only you}.

[0069] The lyrics of the second chorus are "Don't doubt what I give you; I'm not too bad; I won't keep you waiting; you are my love; you are the reliance I most want to have," which contains five consecutive phrases. The sequence of the second phrase can be represented as {Don't doubt what I give you; I'm not too bad; I won't keep you waiting; you are my love; you are the reliance I most want to have}.

[0070] Using the number of phrases and segments (5) in the lyrics of the second chorus as the subsequence length, select the corresponding length of each first phrase segment subsequence from the first phrase segment sequence. Each first phrase segment subsequence can be represented as: {Write this feeling into a photo; No need to doubt, the love I give you; I'm not too bad; I won't let you keep waiting; You're my type}, {No need to doubt, the love I give you; I'm not too bad; I won't let you keep waiting; You're my type; The reliance I most want to have}, {I'm not too bad; I won't let you keep waiting; You're my type; The reliance I most want to have; Don't be surprised}, {I won't let you keep waiting; You're my type; The reliance I most want to have; Don't be surprised; Intoxicated in a future with only you}, a total of 4 first phrase segment subsequences.

[0071] In step S503, by performing text matching between each first phrase segment subsequence of the first chorus lyrics and the second phrase segment sequence of the second chorus lyrics, the similarity between each first phrase segment subsequence and the second phrase segment sequence of the second chorus lyrics is obtained. This helps to find the parts of the first chorus lyrics that are similar to the second chorus lyrics and determine the similarity.

[0072] Step S504: The highest similarity score obtained is taken as the chorus similarity score.

[0073] From the similarity between each obtained first sentence segment sequence and the second sentence segment sequence of the second chorus lyrics, the highest similarity is selected as the chorus similarity between the song to be identified and the target song.

[0074] In some optional implementations, in step S503 above, obtaining the similarity between each first clause segment subsequence in the first clause segment sequence and the second clause segment sequence may further include: based on a sliding window algorithm, sequentially traversing each first clause segment subsequence in the first clause segment sequence through a sliding window; and using a preset text similarity algorithm to obtain the similarity between the first clause segment subsequence currently traversed by the sliding window and the second clause segment sequence.

[0075] Specifically, the second phrase segment sequence of the second chorus lyrics includes N consecutive phrase segments, where N is an integer greater than or equal to 2. The starting pointer of the sliding window is set to the first phrase segment in the first phrase segment sequence, and the ending pointer of the sliding window is set to the Nth phrase segment in the first phrase segment sequence. The first to Nth phrase segments in the first phrase segment sequence represent the first traversed first phrase segment subsequence. A preset text similarity algorithm is used to obtain the similarity between the first phrase segment subsequence currently traversed by the sliding window and the second phrase segment sequence. The starting and ending pointers of the sliding window are simultaneously moved to the right by one phrase segment, and the process returns to the step of obtaining the similarity between the first phrase segment subsequence currently traversed by the sliding window and the second phrase segment sequence using the preset text similarity algorithm. This process continues until all possible first phrase segment subsequences have been traversed.

[0076] In some optional implementations, the text similarity algorithm includes, but is not limited to, the string edit distance algorithm. Other text similarity algorithms may also be used, such as cosine similarity, Word2Vec, deep learning neural network models, etc. The embodiments of the present invention do not impose any special limitations on this.

[0077] The string edit distance algorithm refers to the minimum number of editing operations required to transform one string into another. Editing operations can include character substitution, character insertion, and character deletion. Generally, the smaller the edit distance, the greater the similarity between the two strings.

[0078] In some optional implementations, a preset text similarity algorithm is used to obtain the similarity between the first clause segment subsequence and the second clause segment sequence currently traversed by the sliding window, including: using a string edit distance algorithm to obtain the edit distance between the strings of the first clause segment subsequence and the second clause segment sequence currently traversed by the sliding window; and obtaining the similarity based on the edit distance, the string length of the first clause segment subsequence currently traversed, and the string length of the second clause segment sequence.

[0079] The similarity calculation formula based on the string edit distance algorithm is as follows: Similarity =

[0080] Where distance represents the edit distance between the string of the first clause segment subsequence and the string of the second clause segment sequence currently being traversed, and left size This indicates the string length of the first clause segment subsequence currently being traversed. size This indicates the string length of the second clause segment sequence.

[0081] In the process of cover song recognition, the string edit distance algorithm is used to calculate the similarity between the first sentence segment subsequence and the second sentence segment sequence. Since the string edit distance algorithm is more sensitive to the relative order between characters, it can more accurately calculate the similarity results between the two sentence segment sequences compared with other similarity algorithms, which is beneficial to improving the cover song recognition effect.

[0082] In some optional implementations, in step S203 above, determining the cover song recognition result based on the chorus similarity may further include: in response to the chorus similarity being greater than or equal to a first preset threshold, identifying the song to be identified as a cover song of the target song, and obtaining the cover song recognition result.

[0083] When the chorus similarity is greater than or equal to the first preset threshold, it indicates that the chorus lyrics of the song to be identified are highly similar to the chorus lyrics of the target song. Therefore, the song to be identified is determined to be a cover of the target song, and the cover recognition result is obtained.

[0084] The embodiments of the present invention do not impose special restrictions on the specific value of the first preset threshold, which can be set according to actual needs. For example, the first preset threshold can be set to 70%.

[0085] In some optional implementations, in step S203 above, determining the cover song recognition result based on the chorus similarity may further include: in response to the chorus similarity being less than a first preset threshold and greater than or equal to a second preset threshold, inputting the lyrics of the first chorus and the lyrics of the second chorus into a preset large model for cover song analysis to obtain the cover song recognition result.

[0086] When the similarity of the chorus between the song to be identified and the target song is less than the first preset threshold but greater than or equal to the second preset threshold, it indicates that there is a certain similarity between the choruses with similarity between the first and second preset thresholds. In order to improve the accuracy of cover song identification, a large model is further used to analyze whether there is a possibility of semantic similarity between the lyrics of the first and second choruses, thereby analyzing and judging whether the song to be identified is a cover of the target song, and obtaining the cover song identification result.

[0087] In this embodiment of the invention, no special restrictions are placed on the specific value of the second preset threshold. The second preset threshold is a value that is less than the first preset threshold and can be set according to actual needs. For example, the second preset threshold can be set to 50%.

[0088] In some alternative implementations, the large model can adopt the Deepseek model, and the prompt words used for cover song analysis can be set according to practical experience. This embodiment of the invention does not impose any special restrictions on this.

[0089] For example, the prompt for cover song analysis could be set as: "You are a professional music copyright practitioner who needs to determine whether there is a cover version of the following two songs based on their chorus lyrics. The following are the chorus lyrics of the two songs to be compared. You can only output two results: 'It is a cover' or 'It is not a cover,' and provide the basis for the judgment of the 'It is a cover' result."

[0090] Chorus Lyrics 1: No need to doubt, the love I give you; I'm not too bad; I won't make you keep waiting; you're my type; you're the reliance I most want to have.

[0091] Chorus Lyrics 2: Don't doubt what I give you; I'm not too bad; I won't keep you waiting; you are my love; you are the support I most want to have.

[0092] The lyrics of the two choruses above and the set prompt words for cover song analysis are input into the large model for cover song analysis, thereby obtaining the cover song recognition result. The cover song recognition result output by the large model can include information on whether it is a cover song or not, as well as the basis for judgment.

[0093] Taking the above chorus lyrics 1 and chorus lyrics 2 as an example, the cover song recognition result output by the large model can be: Cover Song Identification Result: Cover Song; Judgment Criteria: 1. High Similarity in Overall Structure and Framework: The two lyrics are almost identical in paragraph division, sentence structure, number of lines, and rhythm. This similarity in the overall framework is an important basis for judging plagiarism; 2. Substantial Similarity in Specific Sentences: Key sentences such as "Don't doubt, the love / things I give you," "I'm not too bad," and "I won't let you continue to wait / I won't let you continue to wait" have only minor changes in expression. However, "You are my type / love" and "You are the dependence / reliance I most want to have" highly overlap in core imagery and expression logic, exceeding the scope of coincidences commonly found in creative works; 3. Consistency in Core Theme and Emotional Expression: Both lyrics revolve around the theme of "directly expressing love and dispelling the other person's doubts," with a highly consistent emotional tone and progression. In summary, these similarities, especially the substantial similarity in overall structure and multiple core expressions, are sufficient to determine that it constitutes a cover song.

[0094] This invention also provides a cover song recognition device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0095] Figure 6This is a structural block diagram of a cover song recognition device provided in an embodiment of the present invention. The present invention provides a cover song recognition device, such as... Figure 6 As shown, the cover song recognition device includes, but is not limited to: acquisition module 601, matching module 602 and recognition module 603.

[0096] The acquisition module 601 is used to acquire the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song.

[0097] The matching module 602 is used to perform text matching between the lyrics of the first chorus and the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song.

[0098] The recognition module 603 is used to determine the cover song recognition result based on the chorus similarity. The cover song recognition result indicates whether the song to be identified is a cover song of the target song.

[0099] The cover song recognition device provided in this embodiment of the invention can execute the cover song recognition method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0100] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0101] The following is a detailed reference. Figure 7 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0102] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0103] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 7702. When the computer program is executed by the processor 701, it performs the functions defined in the cover song recognition method of the embodiments of the present invention.

[0104] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0105] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the cover song recognition method shown in the above embodiments is implemented.

[0106] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0107] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for identifying cover songs, characterized in that, The method includes: Obtain the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song; The lyrics of the first chorus are matched with the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song. The cover song recognition result is determined based on the chorus similarity, and the cover song recognition result indicates whether the song to be identified is a cover song of the target song.

2. The method according to claim 1, characterized in that, The step of performing text matching between the first chorus lyrics and the second chorus lyrics to obtain the chorus similarity between the song to be identified and the target song includes: The lyrics of the first chorus are divided into multiple consecutive phrase segments to obtain the first phrase segment sequence; The lyrics of the second chorus are divided into multiple consecutive phrase segments to obtain a sequence of second phrase segments; The similarity between each first sentence segment subsequence in the first sentence segment sequence and the second sentence segment sequence is obtained respectively, and each first sentence segment subsequence includes multiple consecutive sentence segments in the lyrics of the first chorus; The highest similarity score obtained is taken as the chorus similarity score.

3. The method according to claim 2, characterized in that, The step of obtaining the similarity between each first clause segment subsequence in the first clause segment sequence and the second clause segment sequence includes: Based on the sliding window algorithm, each subsequence of the first sentence segment in the first sentence segment sequence is traversed sequentially through the sliding window; A preset text similarity algorithm is used to obtain the similarity between the first sentence segment subsequence currently traversed by the sliding window and the second sentence segment sequence.

4. The method according to claim 1, characterized in that, The step of determining the cover song recognition result based on the chorus similarity includes: In response to the chorus similarity being greater than or equal to a first preset threshold, the song to be identified is determined to be a cover of the target song, and the cover recognition result is obtained.

5. The method according to claim 1, characterized in that, The step of determining the cover song recognition result based on the chorus similarity includes: In response to the chorus similarity being less than a first preset threshold and greater than or equal to a second preset threshold, the lyrics of the first chorus and the lyrics of the second chorus are input into a preset large model for cover song analysis to obtain the cover song recognition result.

6. The method according to claim 1, characterized in that, The process of obtaining the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song includes: The chorus position of the song to be identified is identified from the audio of the song to be identified using an audio-based chorus extraction algorithm, and the chorus position of the target song is identified from the audio of the target song. The lyrics of the first chorus are extracted based on the position of the chorus of the song to be identified; The lyrics of the second chorus are extracted based on the position of the chorus in the target song.

7. A cover song recognition device, characterized in that, The device includes: The acquisition module is used to acquire the lyrics of the first chorus of the song to be identified and the lyrics of the second chorus of the target song; The matching module is used to perform text matching between the lyrics of the first chorus and the lyrics of the second chorus to obtain the chorus similarity between the song to be identified and the target song; The identification module is used to determine the cover song identification result based on the chorus similarity, wherein the cover song identification result indicates whether the song to be identified is a cover song of the target song.

8. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the cover song recognition method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the cover song recognition method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the cover song recognition method according to any one of claims 1 to 6.

Images