Song cover synthesis, performing method and device, equipment, medium and product

Abstract

The application discloses a song cover synthesis, execution method and device, equipment, medium and product. The synthesis method comprises the following steps: obtaining a target song specified by a user through a graphical user interface; obtaining ranking data of a plurality of singing singers matched with a singing feature in the target song from a server; displaying individual controls corresponding to each singing singer according to the ranking data, and determining a corresponding target singing singer by touch control; and in response to a touch event acting on any individual control, obtaining a cover song in which the target singing singer sings the target song from the server according to the individual control. The application makes the production of the cover song more convenient, improves the production efficiency of the cover song, enriches the music auxiliary creation form, and improves the user experience.

Description

Technical Field

[0001] This application relates to the field of music-assisted creation technology, and in particular to a song cover synthesis and execution method and its corresponding apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] Online music has enriched people's spiritual and cultural lives, and has therefore flourished. Music-assisted creation technology, by providing various operational conveniences, makes it easier for people to showcase their musical, literary, and performing talents, opening up greater opportunities for social workers to realize their value and expand social employment.

[0003] As a form of music-assisted creation, song covers rely on the cooperation of backend and frontend technologies. Traditional cover song synthesis methods mostly involve users editing and generating the songs themselves using music editing software, which is cumbersome and the results are not ideal.

[0004] With the development of cover song synthesis technology, the quality of song covers has improved significantly. However, the main drawback is that the technology primarily focuses on algorithmic support rather than practical application. Consequently, there are currently no user-friendly song cover products on the market; obtaining a cover version of a song still requires professional editing using specialized software.

[0005] Based on the above aspects, the music-assisted creation technology corresponding to song covers still needs to be improved. Summary of the Invention

[0006] The primary objective of this application is to solve at least one of the above-mentioned problems by providing a method for synthesizing song covers and related apparatus, computer equipment, computer-readable storage media, and computer program products.

[0007] Another objective of this application is to solve at least one of the above-mentioned problems by providing a song cover performance method and corresponding apparatus, computer equipment, computer-readable storage medium, and computer program product.

[0008] To achieve the various objectives of this application, the following technical solution is adopted:

[0009] A song cover synthesis method provided for one of the purposes of this application includes the following steps:

[0010] Obtain the target song specified by the user through a graphical user interface;

[0011] Retrieve ranking data of multiple singers that match the vocal characteristics in the target song from the server;

[0012] Based on the ranking data, a personal control corresponding to each singer is displayed, which is used to determine the corresponding target singer by touch.

[0013] In response to a touch event applied to any personal control, the system retrieves from the server a cover song of the target song sung by the target singer corresponding to the touched personal control.

[0014] In a more detailed embodiment, displaying individual controls corresponding to each singer based on the ranking data includes the following steps:

[0015] The ranking data is analyzed to obtain the personal information of the singers and their ranking index items in the ranking data. The ranking index item is the similarity between the vocal performance features of the singer and the vocal performance features in the target song. The vocal performance features are either timbre features or pitch features. Alternatively, the ranking index item is the success rate of the singer in synthesizing the target song.

[0016] Based on the sorting results of the ranking index, the graphical user interface can be used to slide and display the personal controls corresponding to each singer. Each personal control loads the personal information of its corresponding singer, which includes the singer's avatar and name.

[0017] In a more detailed embodiment, in response to a touch event acting on any personal control, the system retrieves from the server a cover song sung by the target singer corresponding to the touched personal control, including the following steps:

[0018] In response to a touch event applied to any personal control, the singer corresponding to the touched personal control is taken as the target singer, and a song cover request associated with the target singer and the target song is sent to the server.

[0019] In response to a server push notification, the server downloads the audio data of the cover song generated in response to the song cover request. The audio data is obtained by replacing the corresponding vocal features of the target song with the vocal features of the target singer in the audio data of the target song.

[0020] Display a notification message to the graphical user interface that a cover song has been obtained, and load the audio data of the cover song into the music playback control for playback.

[0021] In some extended embodiments, before the step of downloading the audio data of the cover song generated by the server in response to the song cover request in response to a server push notification, the following steps are included:

[0022] Obtain similar singers corresponding to the target singer from the server. The similar singers and the target singer are determined based on the success rate of obtaining corresponding cover songs by synthesizing the same songs.

[0023] While waiting for the server to synthesize the cover song, the personal control of the similar singers is displayed, allowing the user to select any similar singer to switch the target singer.

[0024] In some extended embodiments, after the step of obtaining from the server a cover song of the target song sung by the target singer corresponding to the touched personal control in response to a touch event acting on any personal control, the following steps are included:

[0025] Play the cover song and display a rating control during playback;

[0026] The scoring data input in the scoring control is obtained and submitted to the server to statistically analyze the cover performance of each singer, so as to calculate the degree of integration of each singer with the original singer of the target song, which is used to correct the matching degree of vocal performance characteristics between the original singer of the target song and the target singer of the cover song.

[0027] A song cover performance method provided for one of the purposes of this application includes the following steps:

[0028] Responding to a singer matching request triggered by a terminal device, obtain the target song corresponding to the request;

[0029] Query the vocal performance feature database to identify multiple singers whose vocal performance features match the original singer of the target song and their matching degree. The vocal performance features are timbre features and / or pitch features.

[0030] The matching degree of each singer is used as the ranking index, and the personal information of each singer is ranked to generate ranking data in response to the singer matching request.

[0031] In response to a song cover request from the terminal device, the target singer specified in the request is determined, and the target singer is any singer in the ranking data;

[0032] A cover song is obtained by replacing the vocal characteristics of the target song with the vocal characteristics of the target singer.

[0033] The cover song is pushed to the terminal device.

[0034] In a more detailed embodiment, the process involves querying a vocal performance feature database to identify multiple singers whose vocal performance features match those of the original singer of the target song, along with their matching degrees. This includes the following steps:

[0035] Obtain the vocal characteristics of the original singer of the target song from the vocal performance feature database;

[0036] Calculate the similarity between the original singer's vocal performance features and the vocal performance features of each singer in the vocal performance feature database, and filter out multiple singers whose similarity exceeds a preset threshold;

[0037] The similarity is adjusted according to the pre-statistical fusion degree between each singer and the original singer to obtain the corresponding matching degree. The fusion degree is the statistical result of user evaluation data obtained by associating the singer and the original singer with the same cover song.

[0038] In some extended embodiments, after the step of replacing the vocal characteristics of the target song with the vocal characteristics of the target singer to obtain the cover song, the following steps are included:

[0039] The number of successful covers by the target singers of the aforementioned cover songs was statistically analyzed.

[0040] The latest copyright fee for the target singer is calculated based on the number of successful cover versions.

[0041] A song cover synthesis device provided for one of the purposes of this application includes a target acquisition module, a singer matching module, a singer determination module, and a cover song initiation module, wherein: the target acquisition module is used to acquire a target song specified by a user through a graphical user interface; the singer matching module is used to obtain ranking data of multiple singers that match the vocal characteristics in the target song from a server; the singer determination module is used to display personal controls corresponding to each singer according to the ranking data, for determining the corresponding target singer upon touch; and the cover song initiation module is used to respond to a touch event acting on any personal control, and obtain from the server a cover song of the target song sung by the target singer corresponding to the touched personal control.

[0042] A song cover performance device provided for one of the purposes of this application includes a song determination module, a matching execution module, a ranking execution module, a target determination module, a cover performance execution module, and a song push module, wherein: the song determination module is used to respond to a singer matching request triggered by a terminal device and obtain the target song corresponding to the request; the matching execution module is used to query a vocal performance feature database to determine multiple singers whose vocal performance features match the original singer of the target song and their matching degrees, wherein the vocal performance features are timbre features and / or pitch features; the ranking execution module is used to rank the personal information of each singer using the matching degree corresponding to each singer as a ranking index item, and generate ranking data in response to the singer matching request; the target determination module is used to respond to the song cover performance request of the terminal device and determine the target singer specified in the request, wherein the target singer is any singer in the ranking data; the cover performance execution module is used to call the vocal performance features of the target singer to replace the vocal performance features of the target song to obtain a cover song; and the song push module is used to push the cover song to the terminal device.

[0043] A computer device provided for one of the purposes of this application includes a central processing unit and a memory, wherein the central processing unit is used to invoke and run a computer program stored in the memory to execute the steps of the song cover synthesis method or the song cover execution method described in this application.

[0044] A computer-readable storage medium is provided for another purpose of this application, which stores, in the form of computer-readable instructions, a computer program implemented according to the described song cover synthesis method or the described song cover execution method, which, when invoked by a computer, executes the steps included in the method.

[0045] A computer program product provided for another purpose of this application includes a computer program / instructions that, when executed by a processor, implement the steps of the song cover synthesis method or the song cover execution method described in any embodiment of this application.

[0046] Compared to existing technologies, this application offers several technical advantages, including but not limited to: This application obtains a user-defined target song through a graphical user interface, acquires ranking data of multiple singers matching the vocal characteristics of the target song, displays these singers based on the ranking data, and allows the user to easily identify each singer before selecting one as the target singer and notifying the server. The server then combines the vocal characteristics of the target singer with the target song to obtain a corresponding cover song. Accordingly, users on the terminal device do not need to rely on professional knowledge; they can complete the preparation of cover songs simply through interactive operations, greatly improving the production efficiency of cover songs. Furthermore, since the synthesized cover song is matched based on the similarity between the vocal characteristics of the target song and the vocal characteristics of the target singer, high-quality cover songs can be obtained. Attached Figure Description

[0047] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0048] Figure 1 This is a flowchart illustrating a typical embodiment of the song cover synthesis method of this application;

[0049] Figure 2 This is an example of a song cover interface for this application;

[0050] Figure 3 A schematic diagram illustrating the process of selecting a target singer and obtaining cover songs for an embodiment of this application;

[0051] Figure 4 This is an example of a cover song synthesis execution interface for this application;

[0052] Figure 5 This is an example of the interface after synthesizing a cover song in this application;

[0053] Figure 6 for Figure 4 An exemplary interface for synthesizing cover songs by singers with similar vocal styles has been added.

[0054] Figure 7 This is a flowchart illustrating a typical embodiment of the song cover performance method of this application;

[0055] Figure 8 This is a flowchart illustrating the process of determining the required matching degree of ranking data in real time based on the target song in an embodiment of this application;

[0056] Figure 9 and Figure 10These are schematic block diagrams of the song cover synthesis device and the song cover execution device of this application, respectively.

[0057] Figure 11 This is a schematic diagram of the structure of a computer device used in this application. Detailed Implementation

[0058] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0059] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0060] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0061] Those skilled in the art will understand that the terms "client," "terminal," and "terminal device" as used herein include both devices that receive wireless signals, devices that only possess wireless signal receiver capabilities without transmission capabilities, and devices with receiving and transmitting hardware, devices that have receiving and transmitting hardware capable of bidirectional communication over a bidirectional communication link. Such devices may include: cellular or other communication devices such as personal computers or tablets, having single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service) that can combine voice, data processing, fax, and / or data communication capabilities; PDA (Personal Digital Assistant) that may include a radio frequency receiver, pager, internet / intranet access, web browser, notepad, calendar, and / or GPS (Global Positioning System) receiver; and conventional laptops and / or handheld computers or other devices that have and / or include radio frequency receivers. As used herein, "client," "terminal," and "terminal device" can be portable, transportable, installed in a means of transportation (air, sea, and / or land), or suitable and / or configured to operate locally and / or in a distributed manner, operating in any other location on Earth and / or in space. "Client," "terminal," and "terminal device" as used herein can also be a communication terminal, an internet access terminal, or a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or a smart TV, set-top box, etc.

[0062] The hardware referred to by the names "server," "client," and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann architecture, such as a central processing unit (including an arithmetic logic unit and a control unit), memory, input devices, and output devices. The computer program is stored in its memory, and the central processing unit loads the program stored in the secondary storage into the main memory to run it, execute the instructions in the program, and interact with the input and output devices to complete specific functions.

[0063] It should be noted that the concept of "server" used in this application can also be extended to the case of server clusters. Based on the network deployment principles understood by those skilled in the art, the servers should be logically divided. Physically, these servers can be independent of each other but accessible through interfaces, or they can be integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method in this application.

[0064] The hardware infrastructure required for implementing the technical solutions of this application can be deployed according to the architecture shown in the figure. The server referred to in this application is deployed in the cloud and acts as a business server. It can further connect to related data servers and other servers providing related support, thereby forming a logically interconnected service cluster to provide services to related terminal devices, such as smartphones and personal computers shown in the figure, or third-party servers (not shown). The smartphones and personal computers mentioned can both access the Internet through known network access methods to establish data communication links with the cloud server in order to run terminal applications related to the services provided by the server.

[0065] For servers, the application is usually built as a service process, with corresponding program interfaces exposed for remote calls by applications running on various terminal devices. The relevant technical solutions in this application that are suitable for running on servers can be implemented in servers in this way.

[0066] The application mentioned refers to an application running on a server or terminal device. This application implements the relevant technical solutions of this application in a programmed manner. Its program code can be stored in a non-volatile storage medium that can be recognized by a computer in the form of computer-executable instructions, and is loaded into memory by the central processing unit for execution. The relevant device of this application is constructed by the operation of the application on the computer.

[0067] One or more of the technical features of this application, unless explicitly specified herein, can be deployed on a server and accessed by a client remotely calling the online service interface provided by the server, or can be directly deployed and run on a client for access.

[0068] Unless otherwise specified, the neural network models referenced or potentially referenced in this application may be deployed on a remote server and invoked remotely on the client, or deployed on a client with the capability to invoke directly. In some embodiments, when running on the client, the corresponding intelligence may be acquired through transfer learning in order to reduce the requirements on the client's hardware resources and avoid excessive consumption of the client's hardware resources.

[0069] Unless otherwise specified, all data involved in this application may be stored remotely on a server or on a local terminal device, as long as it is suitable for use by the technical solution of this application.

[0070] Those skilled in the art will understand that although the various methods in this application are described based on the same concept and thus present commonality among them, they can be performed independently unless otherwise specified. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept; therefore, concepts expressed in the same way, as well as concepts that are appropriately changed for convenience but are expressed differently, should be understood equivalently.

[0071] Unless otherwise expressly stated, the various embodiments disclosed in this application can be combined in a cross-cutting manner to flexibly construct new embodiments, as long as such combination does not depart from the inventive spirit of this application and can meet the needs of the prior art or solve a certain deficiency in the prior art. Those skilled in the art should be aware of such modifications.

[0072] This application discloses a song cover synthesis method, which can be programmed into a computer program product and primarily deployed and run on a terminal device. This allows for human-computer interaction via a graphical user interface (GUI) by accessing the interface opened after the computer program product is running. Accordingly, please refer to... Figure 1 As shown, the song cover synthesis method, in its typical embodiment, includes:

[0073] Step S1100: Obtain the target song specified by the user through the graphical user interface:

[0074] In one embodiment, when a user needs to create a cover version of a song, they can select a song from a playlist displayed on the graphical user interface of a terminal device application that implements the technical solution of this application, and then enter... Figure 2 The example song cover interface is used to identify the target song for implementing the song cover.

[0075] In another embodiment, when a user plays a song on a terminal device, the graphical user interface is in the music playback interface. The user can also touch the cover song control provided in the music playback interface to enter... Figure 2 In the example song cover interface, the song being listened to is identified as the target song for implementing the song cover.

[0076] In another embodiment, the user completes the creation of a self-edited song using a music-assisted creation tool. After recording the main melody of the song with human vocals or synthesizing the song through virtual synthesis of the main melody audio, the user can also access the song through a cover song control. Figure 2 The example song cover interface is provided to select this song as the target song. The vocal part of the main melody in the target song can be obtained by the user's own recording, or it can be automatically synthesized by a music-aided creation tool by calling preset timbre features and / or pitch features based on a pre-edited score file.

[0077] The target song, along with its corresponding audio and lyrics files, can be pre-stored on the online music platform's server, or uploaded to the server after the target song is selected. This allows the server to invoke the target song's audio file and implement the corresponding business logic for song cover performance based on a request triggered by the user on their terminal device.

[0078] Step S1200: Obtain ranking data of multiple singers that match the vocal characteristics in the target song from the server.

[0079] After entering the song cover interface, the terminal device requests the server to obtain ranking data of multiple singers suitable for performing the cover of the target song. The server, according to its preset business logic, determines multiple singers whose vocal characteristics match the vocal characteristics of the target song. Then, based on the matching degree between the vocal characteristics of each singer and the vocal characteristics of the target song, the server sorts the multiple singers to generate corresponding ranking data. The ranking data includes descriptive data of the personal information of each singer and a ranking index for each singer, so that the terminal device can display the ranking of each singer in a formatted manner according to the ranking index.

[0080] The vocal performance features mentioned above refer to the timbre and / or pitch features extracted from the audio information of the vocal performance portion of a song. The timbre features distinguish the spectral information corresponding to different sound sources, while the pitch features distinguish the spectral information of sound sources with different singing techniques. Each singer's timbre and pitch features can be extracted from the songs they have sung, typically by those skilled in the art using a pre-trained, convergent neural network model. Therefore, the timbre and pitch features are generally deep semantic information extracted using a neural network model, which can be implemented using traditional methods. Thus, each singer can be associated with their unique timbre and pitch features. When it is necessary to use a singer's timbre and / or pitch features to cover a song, the corresponding timbre and / or pitch features can be invoked.

[0081] Step S1300: Display the personal controls corresponding to each singer based on the ranking data, which are used to determine the corresponding target singer upon touch.

[0082] After obtaining ranking data of multiple singers provided by the server, the ranking data can be parsed to obtain the personal information of each singer and the corresponding ranking index. The personal information of each singer mainly includes their avatar and name, and may also include other information as needed. Accordingly, the avatars and names of each singer from the ranking data provided by the server can be displayed in the song cover interface, allowing users to select one as the target singer and use the vocal characteristics of the target singer to perform a song cover synthesis.

[0083] To visualize the personal information of each singer in the ranking data, in Figure 2 The example song cover interface creates personal controls corresponding to each singer. The personal controls load and display the corresponding singer's avatar and name. The personal controls are sorted according to the ranking index of each singer to ensure that the personal controls are recommended and displayed based on the matching degree between the singer's vocal characteristics and the vocal characteristics of the target song.

[0084] The personal control is configured to respond to user touch operations and use the corresponding singer as the target singer for song cover performances. When there are many personal controls, multiple personal controls can be configured to be displayed in a scrollable manner.

[0085] Step S1400: In response to a touch event applied to any personal control, obtain from the server the cover song of the target song sung by the target singer corresponding to the touched personal control.

[0086] When a user touches any of the aforementioned personal controls, a corresponding touch event is triggered. In response to this event, a song cover request is sent to the server. This request instructs the server to perform a song cover process using the target singer corresponding to that personal control, thereby obtaining the corresponding cover song and returning it to the current terminal device. The cover song is essentially the target song replaced with the vocal characteristics of the target singer, thus the terminal device obtains the corresponding cover song and can play it.

[0087] Compared to existing technologies, this application offers several technical advantages, including but not limited to: This application obtains a user-defined target song through a graphical user interface, acquires ranking data of multiple singers matching the vocal characteristics of the target song, displays these singers based on the ranking data, and allows the user to easily identify each singer before selecting one as the target singer and notifying the server. The server then combines the vocal characteristics of the target singer with the target song to obtain a corresponding cover song. Accordingly, users on the terminal device do not need to rely on professional knowledge; they can complete the preparation of cover songs simply through interactive operations, greatly improving the production efficiency of cover songs. Furthermore, since the synthesized cover song is matched based on the similarity between the vocal characteristics of the target song and the vocal characteristics of the target singer, high-quality cover songs can be obtained.

[0088] In a more detailed embodiment, step S1300, displaying the personal controls corresponding to each singer based on the ranking data, includes the following steps:

[0089] Step S1310: Parse the ranking data to obtain the personal information of the singers and their ranking index items in the ranking data. The ranking index item is the similarity between the vocal performance features of the singer and the vocal performance features in the target song. The vocal performance features are either timbre features or pitch features. Alternatively, the ranking index item is the success rate of the singer in synthesizing the target song.

[0090] Once the terminal device obtains the ranking data that matches the target song, it can parse it to obtain the personal information and ranking index of each singer. The personal information mainly includes the personal avatar and personal name of each singer. The ranking index is mainly used to store the similarity between the vocal characteristics of each singer and the vocal characteristics of the target song. The similarity is calculated and determined by the server.

[0091] In one embodiment, ranking index items can be determined based on the similarity between the vocal characteristics of the singer and the target song, thereby allowing the user to... Figure 2 In the example song cover interface, users can specify whether to synthesize vocal features based solely on timbre, pitch, or both. This is done by selecting options provided in the interface, which are then sent to the server by the terminal device. Accordingly, the similarity score is determined by matching vocal features based on the user-defined options. The ranking index, determined by the similarity score, represents the degree of similarity between the singer's and the target song's vocal features. Therefore, it can match the target song with singers whose timbre and / or pitch are similar, thereby enhancing the sound quality of the target song's source material. This makes the cover song less noticeable to listeners familiar with the original singer's voice, providing a degree of sound enhancement. Furthermore, due to the similarity in timbre and / or pitch, the synthesized cover song will exhibit greater vocal harmony when played, with the selected singer's vocal features complementing the accompaniment.

[0092] In another embodiment, the ranking index can be determined based on the historical success rate of the singer synthesizing the target song. An exemplary statistical method for the success rate is as follows: the historical success rates of different singers synthesizing the target song are pre-collected and statistically analyzed by the server. Each time a user synthesizes a target song using the vocal characteristics of a specific singer and obtains a corresponding cover song, a user behavior record is generated. Based on this user behavior record, the number of synthesizations of that specific singer relative to the target song can be accumulated. When the user is satisfied with the cover song and publishes it, the number of successful synthesizations of that specific singer relative to the target song can be accumulated. For any singer, dividing the number of successful synthesizations corresponding to the same target song by the number of synthesizations yields their success rate for that target song. Providing ranking indexes based on the success rate of a singer's synthesis relative to the target song relies on historical big data from online music platforms. The advantage of this is that, since the success rate often represents the sound quality achieved by the singer relative to the target song, relying on statistical data can also avoid users repeatedly trying different singers' synthesized sound quality. They can simply use the experience of predecessors to select singers with high success rates for cover song synthesis, thereby improving the efficiency of cover song creation.

[0093] Step S1320: Based on the sorting results of the ranking index, in the graphical user interface, the personal controls corresponding to each singer can be displayed in a sliding manner. Each personal control loads the personal information of its corresponding singer, including the singer's personal avatar and personal name.

[0094] Typically, the server provides information on multiple singers at once in its ranking data, such as 10 or more singers. In this case, if there is enough space in the graphical user interface, the personal controls of all singers can be listed one by one. Otherwise, as recommended in this embodiment, these personal controls of singers can be configured to be displayed in a sliding manner. When displaying, each singer is still arranged according to the ranking index item, and several singers, such as four singers, are displayed on the first screen. When the user needs to select other singers that are not displayed, they only need to slide to one side to display the other singers that are not displayed.

[0095] Since the ranking data pushed by the server also includes the personal information of each singer, including their avatar and name, after creating a corresponding personal control for each singer, their avatar is loaded and displayed in the personal control, and their name is displayed below the personal control for easy identification. Figure 2 As shown.

[0096] In this embodiment, the candidate singers are displayed based on the ranking data provided by the server, making it convenient for users to quickly select one of them to perform a cover version of the target song. The provision of a human control for each singer makes it easy to identify and facilitates human-computer interaction. Users can determine the target singer without performing professional operations, thus improving the efficiency of song cover operations.

[0097] Please see Figure 3 In a further embodiment, step S1400, responding to a touch event acting on any personal control, and obtaining from the server a cover song of the target song sung by the target singer corresponding to the touched personal control, includes the following steps:

[0098] Step S1410: In response to a touch event acting on any personal control, the singer corresponding to the touched personal control is taken as the target singer, and a song cover request associated with the target singer and the target song is sent to the server.

[0099] After the personal controls of each singer are displayed in the graphical user interface based on the ranking data, the user can touch to select the personal control corresponding to one of the singers, thereby triggering a touch event associated with that singer.

[0100] In response to the touch event, the singer associated with the touched personal control is identified as the target singer for the cover version of the target song. A song cover request is then sent to the server, containing specified information about the target singer. This instructs the server to utilize the corresponding vocal characteristics of the target singer to synthesize a cover version of the song. Figure 2 If the song cover interface shows that options for timbre, pitch, or a combination thereof have been selected, these can be encapsulated in this request to instruct the server to invoke the corresponding vocal characteristics for cover synthesis. If the target song has not been explicitly specified to the server beforehand, it can also be specified in this request.

[0101] In response to the touch event, to help users understand the process of acquiring the cover song, a graphical user interface representing the song being synthesized can be displayed, such as... Figure 4 As shown.

[0102] Step S1420: In response to the server push notification, download the audio data of the cover song generated by the server in response to the song cover request. The audio data is obtained by replacing the corresponding vocal features of the target song with the vocal features of the target singer in the audio data of the target song.

[0103] When the server synthesizes the target song based on the singer and vocal characteristics specified in the song cover request, it obtains a cover song. The main melody and accompaniment in the cover song's audio data are the same as the target song, but the vocal characteristics of the vocal parts in the main melody section have been replaced by the vocal characteristics of the user-specified target singer, replacing the original singer (original audio source). Theoretically, when the cover song is played, some differences between the two songs can be perceived; for example, the cover song may have improved or different timbre or singing technique compared to the target song.

[0104] Once the server has completed the preparation of the cover song, it sends a notification to the current terminal device. The terminal device can then download the corresponding audio data of the cover song in the background and cache it locally for playback.

[0105] Step S1430: Display a notification message that the cover song has been obtained to the graphical user interface and load the audio data of the cover song into the music playback control for playback.

[0106] After the terminal device acquires the cover song, it can display a notification message indicating that the cover song has been acquired to the graphical user interface, thereby notifying the current user. Then, as... Figure 5 As shown in the example, the playback control of the open music player loads the audio data of the cover song downloaded from the server into the player so that the user can play the cover song through the player to test its synthesis effect.

[0107] This embodiment responds to touch events triggered by personal controls, automatically instructing the server to perform a song cover, and ultimately obtains the corresponding cover song. The entire process requires no manual intervention, simplifying the business logic of the song cover process and improving the efficiency of song cover production.

[0108] In some extended embodiments, before step S1420, the step of downloading the audio data of the cover song generated by the server in response to the song cover request in response to the server push notification, the following steps are included:

[0109] Step S1421: Obtain similar singers corresponding to the target singer from the server. The similar singers and the target singer are determined based on the success rate of obtaining corresponding cover songs by synthesizing the same songs.

[0110] To provide users with more comprehensive reference information, during the execution of step S1420, this embodiment utilizes the success rate of each song in covering the target song to further provide alternative options for the target singer currently participating in the cover song synthesis in the graphical user interface.

[0111] For example, in Figure 4 Based on the interface shown, as Figure 6 As shown in the example, similar singers corresponding to the target singer are displayed at the bottom of the interface, obtained from the server. These similar singers are determined by the server, and the terminal device can send a request to the server to obtain these similar singers after a touch event triggers the personal control. One way to determine these similar singers is based on the success rate of the singers relative to a target song, as mentioned earlier. Specifically, the server can retrieve historical statistics on the success rates of all singers who have covered the target song, select the top few with higher success rates, and push them to the terminal device in descending order of success rate so that the terminal device can parse and process them. Figure 6 The graphical user interface shown allows you to remove the target singer currently participating in the cover song synthesis.

[0112] Step S1422: While waiting for the server to synthesize the cover song, display the personal controls of the similar singers, so that the user can select any similar singer to switch the target singer:

[0113] When the server synthesizes a cover version of the target song, it generally requires a certain amount of time, such as 2 to 5 seconds. However, the process of determining the similar singers takes even less time. Therefore, before obtaining the cover song, the terminal device first obtains the similar singers. Thus, referring to the previous embodiment, each similar singer can be displayed by constructing individual controls for each similar singer, with the following effect: Figure 6 As shown, if a user needs to replace a similar singer, they only need to touch the personal control corresponding to a similar singer to trigger the corresponding touch event, thereby identifying the similar singer as the new target singer and sending a request to the server to interrupt the server's process of synthesizing the cover song, and then re-synthesizing the cover song of the target song with the vocal characteristics of the new target singer.

[0114] In this embodiment, during the process of a user initiating a song cover synthesis, the user is provided with options for similar singers, giving the user a wider selection of singing targets and making it easier for the user to switch target singers in a timely manner, thereby improving the user's success in obtaining the desired cover song.

[0115] In some extended embodiments, after step S1400, which involves responding to a touch event acting on any personal control and obtaining from the server the cover song sung by the target singer corresponding to the touched personal control, the following steps are included:

[0116] Step S1500: Play the cover song and display a rating control during playback.

[0117] After the user obtains the aforementioned cover song, in such a way... Figure 5 The graphical user interface shown can include corresponding playback controls, allowing users to play cover songs by operating these controls. Alternatively, in another embodiment, it can be configured to automatically play cover songs obtained from a server.

[0118] During the playback of the cover song, a rating control can be loaded and displayed in the graphical user interface to obtain the user's evaluation information of the current cover song. The evaluation information can be quantified into corresponding evaluation data, i.e., evaluation score, by the terminal device or server.

[0119] Step S1600: Obtain the scoring data input in the scoring control and submit it to the server to statistically analyze the cover performance of each singer, so as to calculate the degree of integration of each singer with the original singer of the target song, which is used to correct the matching degree of vocal characteristics between the original singer of the target song and the target singer of the cover song.

[0120] After the user completes the rating operation in the rating control, the rating data is generated and submitted to the server.

[0121] After receiving the rating data for the cover song, the server can use it to calculate the degree of integration between the target singer and the original singer. Therefore, the degree of integration can characterize the perceived effectiveness of a singer's cover of an original singer's song. The method for calculating this degree of integration can be flexibly implemented by those skilled in the art. In one exemplary method, let the highest score corresponding to the rating data of each cover song be S, and the evaluation score in the user-determined rating data be S... i The single-song integration degree obtained for this cover song is:

[0122]

[0123] The target singer and the original singer may be linked through multiple cover songs, resulting in multiple single-song integration scores. Therefore, by simply averaging the integration scores of all cover songs, the overall integration score between the target singer and the original singer can be obtained. It's easy to understand that a higher integration score indicates a better sound quality in the cover song after replacing the original singer's vocal features with those of the target singer. This integration score can then be used to adjust the matching degree of vocal features between the original singer of the target song and the target singer of the cover song. When the server provides candidate singers for song covers to terminal devices, it determines the ranking of each singer based on the adjusted matching degree, thus determining the corresponding ranking data for each singer. This not only considers the similarity of vocal features between the singer and the original singer of the target song but also fully considers the effectiveness data generated by user reviews. This allows for a more accurate identification of a singer more suitable for the user's target song.

[0124] This embodiment can further improve the recommendation of singers who are more accurately matched with the original singer of the target song to users of terminal devices for song cover performance. This makes the correspondence between the target singer determined by the user and the original singer of the target song reflect both the similarity of vocal characteristics and the effectiveness of historical user ratings.

[0125] This application discloses a song cover performance method, which can be programmed into a computer program product and primarily deployed and run on a server. This allows for human-computer interaction via a graphical user interface (GUI) by accessing the interface opened by the running computer program product. Accordingly, please refer to... Figure 7 As shown, the song cover synthesis method, in its typical embodiment, includes:

[0126] Step S2100: Respond to the singer matching request triggered by the terminal device and obtain the target song corresponding to the request:

[0127] When a terminal device triggers a singer matching request, the server receives and responds to the request. First, it determines the target song specified by the terminal device based on the request. This target song is typically an existing song already stored in the server's music library, or a song pre-uploaded by the terminal device. The unique characteristic information of the target song can be directly specified in the request. Therefore, the server can directly determine the target song based on this unique characteristic information.

[0128] Step S2200: Query the vocal performance feature database to determine multiple singers whose vocal performance features match the original singer of the target song and their matching degree. The vocal performance features are timbre features and / or pitch features.

[0129] The server has a pre-built vocal performance feature database to store a large number of vocal performance features of singers. These vocal performance features may include the corresponding singer's timbre and pitch features. When called, any one or all of these features can be flexibly called according to the request of the terminal device to perform song cover synthesis.

[0130] The vocal performance features can be obtained by those skilled in the art by extracting the audio data of the songs generated by each singer using traditional techniques. For example, a neural network model pre-trained to convergence can be used for extraction, including a neural network model specifically for extracting the timbre features and / or a neural network model specifically for extracting the pitch features, which can be called as needed.

[0131] For this vocal performance feature database, the server pre-calculates the similarity based on shared vocal performance features between pairs of singers, thus obtaining a timbre similarity mapping table and a pitch similarity mapping table. These tables are used to store the similarity of timbre and pitch between pairs of singers, respectively. Furthermore, the similarities in the timbre and pitch similarity mapping tables can be combined across pairs of singers. For example, the average of the timbre and pitch similarities between pairs of singers can be calculated to obtain the overall similarity of vocal performance features, which is stored in another similarity mapping table for querying the similarity between pairs of singers that simultaneously possess both timbre and pitch features.

[0132] Since the original singer of the target song can also be one of the singers whose timbre and pitch characteristics are obtained in advance, the original singer's vocal characteristics and similarity data are also stored in the vocal performance feature data and its corresponding mapping tables. That is, the original singer can also be regarded as one of the singers.

[0133] As mentioned earlier, when a user triggers a singer matching request, they can provide specific options for the vocal features to be replaced during the cover song. This includes selecting either a single timbre feature or a pitch feature, or both. Therefore, the server can determine the range of vocal features to be used from this request. Accordingly, when the server queries its vocal feature database, it looks up the corresponding mapping table for each option in the request. Based on the original singer of the target song specified by the user, the server can find the similarity between the vocal features of each singer and the corresponding singer in the mapping table. In this embodiment, this similarity directly determines the matching degree between the original singer and the corresponding singer. In embodiments disclosed later in this application, this matching degree can be corrected using user evaluation data based on the similarity.

[0134] Therefore, based on the target song in the singer matching request, multiple singers whose vocal characteristics match those of the original singer of the target song can be identified, and the matching degree of each singer can be obtained.

[0135] Step S2300: Using the matching degree corresponding to each singer as a ranking index, rank the personal information of each singer and generate ranking data in response to the singer matching request:

[0136] The matching degree of each singer can measure the closeness of the singer's performance relative to the original singer when covering a song. Therefore, the matching degree can be directly used as a ranking index for each singer, so that the server and terminal devices can sort the singers according to the ranking index. The server first ranks each singer according to their matching degree to determine the order of the singers, and then associates the personal information of each singer, mainly including their personal avatar and personal name, to generate ranking data. The server then pushes the singer matching request to the terminal device, which further parses and displays it in its graphical user interface so that the user can select one singer as the target singer for preparing a cover song.

[0137] Step S2400: Respond to the song cover request from the terminal device, and determine the target singer specified in the request. The target singer is any singer in the ranking data.

[0138] After a user identifies a target singer on their terminal device and sends a song cover request, the server responds to the request by identifying the target singer. It is easy to understand that since the user identifies the target singer based on the ranking data pushed by the server, the target singer is also a member of the ranking data, and their vocal characteristics have been stored in the vocal characteristics database in advance and can be accessed by the server.

[0139] Step S2500: Replace the vocal characteristics of the target song with the vocal characteristics of the target singer to obtain a cover song.

[0140] The server can pre-train a neural network model suitable for synthesizing the audio data of the target song using the vocal characteristics of the target singer, thereby generating the corresponding cover song. The design and training process of the neural network model can be flexibly implemented by those skilled in the art, thus enabling the neural network model to specifically replace the vocal characteristics of the target song with the vocal characteristics.

[0141] Accordingly, the server retrieves the vocal features of the target singer from the vocal feature database, performs speech preprocessing on the audio data of the target song to obtain the corresponding speech information, and inputs it into the neural network model. The neural network model then synthesizes the corresponding audio data of the cover song based on its learned capabilities. Thus, the vocal features of the original singer in the cover song have been corrected to those of the target singer compared to the original song.

[0142] Step S2600: Push the cover song to the terminal device:

[0143] Once the audio data of the cover song is obtained, it can be pushed to the terminal device for the user to play.

[0144] In this embodiment, the server, based on the singer matching request, can quickly match multiple singers as candidate singers for the terminal device based on the matching degree of vocal characteristics between the original singer of the target song and each pre-collected singer. After the terminal device determines the target singer from the candidate singers, the server can quickly synthesize the corresponding cover song for the user based on the vocal characteristics of the target singer. The target song is corrected using the vocal characteristics of the target singer, so that the singing quality and singing skills of the target song can be corrected and improved. The whole process does not require professional knowledge intervention, which is convenient for users to operate in a user-friendly way. It innovates the form of assisted music creation and expands the way works are generated on online music platforms. It is expected to achieve optimistic economies of scale.

[0145] Please see Figure 8 In a further embodiment, step S2200, querying a vocal performance feature database to determine multiple singers whose vocal performance features match the original singer of the target song and their matching degree, includes the following steps:

[0146] Step S2210: Obtain the vocal characteristics of the original singer of the target song from the vocal performance feature database:

[0147] As mentioned earlier, the vocal performance feature database pre-stores the vocal performance features of various singers, including the original singer of the target song. Based on this, the vocal performance features of the original singer of the target song can be directly accessed.

[0148] Step S2220: Calculate the similarity between the original singer's vocal features and the vocal features of each singer in the vocal features database, and filter out multiple singers whose similarity exceeds a preset threshold.

[0149] In this embodiment, in response to a singer matching request, the similarity between the original singer's vocal features and the vocal features of various singers in the vocal feature database is calculated in real time. Therefore, based on the same vocal features, a preset data distance algorithm is used to calculate the similarity between the original singer's vocal features and the vocal features of various singers in the vocal feature database. The data distance algorithm can be any one of the following: cosine similarity algorithm, Pearson correlation coefficient algorithm, Euclidean distance algorithm, Jaccard algorithm, etc. After calculation, a similarity sequence can be obtained, where each element represents the similarity between the original singer and another singer. Accordingly, considering the need for selecting the best singer, a preset threshold can be used to optimize each element in the similarity sequence, filtering out multiple singers whose similarity exceeds the preset threshold, and determining the corresponding similarity of each filtered singer.

[0150] Step S2230: Adjust the corresponding similarity based on the pre-statistical fusion degree between each singer and the original singer to obtain the corresponding matching degree. The fusion degree is the statistical result of user evaluation data obtained by associating the singer and the original singer with the same cover song.

[0151] Furthermore, to correct the similarity determined in the previous step using historical user rating data, the fusion degree of each singer corresponding to the original singer, as described above, can be used. Using the fusion degree of each singer as a weight, it is multiplied by the corresponding similarity degree to obtain the matching degree of the corresponding singer. This matching degree is the result of correcting the fusion degree obtained statistically from user rating data based on the aforementioned similarity degree. The calculation method for the fusion degree has been disclosed above and will not be repeated here.

[0152] As mentioned above, the matching degree is used as a ranking index for candidate singers of the target song. Therefore, the selected singers can be further re-sorted based on the matching degree to form ranking data and pushed to the terminal device.

[0153] This embodiment calculates and determines singers who are similar to the original singer in terms of vocal characteristics for each target song in real time. In the process of calculating the matching degree between the original singer and the singer based on the ranking criteria, it not only considers the similarity of their vocal characteristics at the high-level semantic level, but also integrates historical user evaluation data. Therefore, the matching degree between the candidate singers in the obtained ranking data and the original singer in terms of sound effect will be better. That is, it can match candidate singers who are more suitable for the target song, which can improve the success rate of users synthesizing cover songs.

[0154] In some extended embodiments, after step S2500, which involves replacing the vocal characteristics of the target song with the vocal characteristics of the target singer to obtain the cover song, the following steps are included:

[0155] Step S2510: Count the number of successful covers of the target singers used in the obtained cover songs:

[0156] To protect version rights and incentivize singers to increase user traffic on online music platforms, this embodiment counts the number of successful covers by the target singer for each cover song synthesized by the server. Among the vast number of users on the online music platform, each time a user calls upon a target singer to synthesize a cover song, the number of successful covers for that target singer is incremented by 1. Thus, over time, outstanding target singers emerge, resulting in a relatively substantial number of successful covers.

[0157] Step S2520: Calculate the latest copyright fee for the target singer based on the statistically analyzed number of successful cover versions.

[0158] Online music platforms can preset the unit price and pricing algorithm corresponding to the number of successful cover songs. When the corresponding settlement time arrives, the pricing algorithm and unit price can be applied to automatically calculate the latest copyright fee for each target singer. Then, based on the billing result, the corresponding fee is paid to the target singer, thereby completing the backend business loop.

[0159] This embodiment further improves the business process of the song cover project, comprehensively takes into account the business needs of both consumers and singers, improves the backend support for the operation of the song cover project, enables the song cover project to continuously generate platform benefits, and plays a role in activating platform user traffic and user retention rate, ensuring that the project brings economies of scale to the platform.

[0160] Please see Figure 9In accordance with the aforementioned graphical user interface, a song cover synthesis device is provided to suit one of the purposes of this application. This device is a functionalized deployment of the song cover synthesis method, comprising a target acquisition module 1100, a singer matching module 1200, a singer determination module 1300, and a cover song initiation module 1400. Specifically: the target acquisition module 1100 is used to acquire a target song specified by the user through the graphical user interface; the singer matching module 1200 is used to obtain ranking data of multiple singers matching the vocal characteristics of the target song from the server; the singer determination module 1300 is used to display the corresponding personal controls of each singer based on the ranking data, for determining the corresponding target singer upon touch; and the cover song initiation module 1400 is used to respond to a touch event acting on any personal control, and obtain from the server a cover song sung by the target singer corresponding to the touched personal control, based on the target song.

[0161] In a further embodiment, the singer determination module 1300 includes: a data parsing unit, used to parse the ranking data, obtain the personal information of the singers in the ranking data and their ranking index items, wherein the ranking index item is the similarity between the vocal performance features of the singer and the vocal performance features in the target song, wherein the vocal performance features are any one of timbre features and pitch features, or the ranking index item is the success rate of the singer in synthesizing the target song; and a ranking display unit, used to display the personal controls corresponding to each singer in a graphical user interface according to the sorting results of the ranking index items, wherein each personal control loads the personal information of its corresponding singer, wherein the personal information includes the singer's personal avatar and personal name.

[0162] In a further embodiment, the cover song initiation module 1400 includes: a touch response unit, used to respond to a touch event acting on any personal control, and send a song cover request associated with the target singer and the target song to the server, using the singer corresponding to the touched personal control as the target singer; a cover song download unit, used to download the audio data of the cover song generated by the server in response to the song cover request, the audio data being obtained by replacing the corresponding vocal features of the target song with the vocal features of the target singer in the audio data of the target song; and a cover song display unit, used to display a notification message that the cover song has been obtained to the graphical user interface and load the audio data of the cover song into a music playback control for playback.

[0163] In some extended embodiments, the cover song initiation module 1400 includes the following units preceding the cover song download unit: a similarity matching unit, used to obtain similar singers corresponding to the target singer from the server, wherein the similar singers and the target singer are determined based on the success rate of obtaining corresponding cover songs by synthesizing the same songs; and a similarity display unit, used to display the personal controls of the similar singers while waiting for the server to synthesize the cover songs, so that the user can select any similar singer to switch the target singer.

[0164] In some extended embodiments, the song cover synthesis device of this application includes the following modules that run after the cover start module 1400: a playback and scoring module, used to play the cover song and display a scoring control during playback; and a scoring processing module, used to obtain the scoring data input in the scoring control and submit it to the server to statistically analyze the cover performance of each singer, so as to calculate the degree of integration of each singer with the original singer of the target song, and to correct the matching degree of vocal characteristics between the original singer of the target song and the target singer of the cover song.

[0165] Please see Figure 10 In accordance with the aforementioned graphical user interface, a song cover execution device is provided to suit one of the purposes of this application. This device is a functionalized deployment of the song cover execution method, comprising a song determination module 2100, a matching execution module 2200, a ranking execution module 2300, a target determination module 2400, a cover execution module 2500, and a song push module 2600. Specifically: the song determination module 2100 is used to respond to a singer matching request triggered by a terminal device and obtain the target song corresponding to the request; the matching execution module 2200 is used to query a vocal performance feature database to determine multiple singers whose vocal performance features match the original singer of the target song and their matching degrees. The vocal performance features are timbre features and / or pitch features; the ranking execution module 2300 is used to rank the personal information of each singer by using the matching degree corresponding to each singer as a ranking index item, and generate ranking data in response to the singer matching request; the target determination module 2400 is used to respond to the song cover request of the terminal device, determine the target singer specified by the request, and the target singer is any singer in the ranking data; the cover execution module 2500 is used to call the vocal performance features of the target singer to replace the vocal performance features of the target song to obtain a cover song; the song push module 2600 is used to push the cover song to the terminal device.

[0166] In a further embodiment, the matching execution module 2200 includes: a feature acquisition unit, used to acquire the vocal features of the original singer of the target song from a vocal feature database; a similarity calculation unit, used to calculate the similarity between the vocal features of the original singer and the vocal features of each singer in the vocal feature database, and filter out multiple singers whose similarity exceeds a preset threshold; and a matching degree calculation unit, used to correct the corresponding similarity based on a pre-statistical fusion degree between each singer and the original singer to obtain a corresponding matching degree, wherein the fusion degree is the statistical result of user evaluation data obtained by associating the singer and the original singer with the same cover song.

[0167] In some extended embodiments, the song cover execution device of this application further includes the following modules that run after the cover execution module 2500: a cover statistics module, used to count the number of successful covers by the target singer of the cover song; and a singer billing module, used to calculate the latest copyright fee of the target singer based on the count of successful covers.

[0168] To address the aforementioned technical problems, embodiments of this application also provide computer equipment. For example... Figure 11 The diagram shows the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. The computer-readable storage medium stores an operating system, a database, and computer-readable instructions. The database may store a sequence of control information. When the computer-readable instructions are executed by the processor, they can cause the processor to implement a song cover synthesis method or a song cover execution method. The processor of the computer device provides computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When these computer-readable instructions are executed by the processor, they can cause the processor to execute the song cover synthesis method or the song cover execution method of this application. The network interface of the computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0169] In this embodiment, the processor is used to execute... Figure 9 , Figure 10The system contains the specific functions of each module and its sub-modules. The memory stores the program code and various data required to execute these modules or sub-modules. The network interface is used for data transmission between the user terminal and the server. In this embodiment, the memory stores the program code and data required to execute all modules / sub-modules in the song cover synthesis device or song cover execution device of this application. The server can call the server's program code and data to execute the functions of all sub-modules.

[0170] This application also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the song cover synthesis method or song cover execution method of any embodiment of this application.

[0171] This application also provides a computer program product, including a computer program / instructions, which, when executed by one or more processors, implement the steps of the song cover synthesis method or song cover execution method described in any embodiment of this application.

[0172] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0173] In conclusion, this application simplifies the production of cover songs, improves the production efficiency of cover songs, enriches the forms of music-assisted creation, and enhances the user experience.

[0174] Those skilled in the art will understand that the steps, measures, and solutions in the various operations, methods, and processes discussed in this application can be alternated, modified, combined, or deleted. Furthermore, other steps, measures, and solutions in the various operations, methods, and processes discussed in this application can also be alternated, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and solutions in the prior art that are similar to those disclosed in this application can also be alternated, modified, rearranged, decomposed, combined, or deleted.

[0175] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for synthesizing song covers, characterized in that, Includes the following steps: Obtain the target song specified by the user through a graphical user interface; Retrieve ranking data of multiple singers that match the vocal characteristics in the target song from the server; Based on the ranking data, a personal control corresponding to each singer is displayed, which is used to determine the corresponding target singer by touch. In response to a touch event applied to any personal control, the system retrieves from the server a cover song sung by the target singer corresponding to the touched personal control, including: In response to a touch event applied to any personal control, the singer corresponding to the touched personal control is taken as the target singer, and a song cover request associated with the target singer and the target song is sent to the server. In response to a server push notification, the server downloads the audio data of the cover song generated in response to the song cover request. The audio data is obtained by replacing the corresponding vocal features of the target song with the vocal features of the target singer in the audio data of the target song. Display a notification message to the graphical user interface that a cover song has been obtained, and load the audio data of the cover song into the music playback control for playback.

2. The song cover synthesis method according to claim 1, characterized in that, The process of displaying individual controls for each singer based on the ranking data includes the following steps: The ranking data is analyzed to obtain the personal information of the singers and their ranking index items in the ranking data. The ranking index item is the similarity between the vocal performance features of the singer and the vocal performance features in the target song. The vocal performance features are either timbre features or pitch features. Alternatively, the ranking index item is the success rate of the singer in synthesizing the target song. Based on the sorting results of the ranking index, the graphical user interface can be used to slide and display the personal controls corresponding to each singer. Each personal control loads the personal information of its corresponding singer, which includes the singer's avatar and name.

3. The song cover synthesis method according to claim 1, characterized in that, Before the step of downloading the audio data of the cover song generated by the server in response to the song cover request in response to the server push notification, the following steps are included: Obtain similar singers corresponding to the target singer from the server. The similar singers and the target singer are determined based on the success rate of obtaining corresponding cover songs by synthesizing the same songs. While waiting for the server to synthesize the cover song, the personal control of the similar singers is displayed, allowing the user to select any similar singer to switch the target singer.

4. The song cover synthesis method according to any one of claims 1 to 3, characterized in that, After responding to a touch event applied to any personal control, and obtaining from the server the cover song of the target song sung by the target singer corresponding to the touched personal control, the process includes the following steps: Play the cover song and display a rating control during playback; The scoring data input in the scoring control is obtained and submitted to the server to statistically analyze the cover performance of each singer, so as to calculate the degree of integration of each singer with the original singer of the target song, which is used to correct the matching degree of vocal performance characteristics between the original singer of the target song and the target singer of the cover song.

5. A method for performing a song cover, characterized in that, It is implemented on a server to complete the collaboration with the song cover synthesis method according to any one of claims 1 to 4, including the following steps: Responding to a singer matching request triggered by a terminal device, obtain the target song corresponding to the request; Query the vocal performance feature database to identify multiple singers whose vocal performance features match the original singer of the target song and their matching degree. The vocal performance features are timbre features and / or pitch features. The matching degree of each singer is used as the ranking index, and the personal information of each singer is ranked to generate ranking data in response to the singer matching request. In response to a song cover request from the terminal device, the target singer specified in the request is determined, and the target singer is any singer in the ranking data; A cover song is obtained by replacing the vocal characteristics of the target song with the vocal characteristics of the target singer. The cover song is pushed to the terminal device.

6. The song cover singing method according to claim 5, characterized in that, The process of querying a vocal performance feature database to identify multiple singers whose vocal performance features match those of the original singer of the target song and their matching degrees includes the following steps: Obtain the vocal characteristics of the original singer of the target song from the vocal performance feature database; Calculate the similarity between the original singer's vocal performance features and the vocal performance features of each singer in the vocal performance feature database, and filter out multiple singers whose similarity exceeds a preset threshold; The similarity is adjusted according to the pre-statistical fusion degree between each singer and the original singer to obtain the corresponding matching degree. The fusion degree is the statistical result of user evaluation data obtained by associating the singer and the original singer with the same cover song.

7. The song cover singing method according to claim 5, characterized in that, After the step of replacing the vocal characteristics of the target song with the vocal characteristics of the target singer to obtain the cover song, the following steps are included: The number of successful covers by the target singers of the aforementioned cover songs was statistically analyzed. The latest copyright fee for the target singer is calculated based on the number of successful cover versions.

8. A song cover synthesis device, characterized in that, It includes: The target acquisition module is used to acquire the target song specified by the user through a graphical user interface. The singer matching module is used to obtain ranking data of multiple singers that match the vocal characteristics in the target song from the server. The singer identification module is used to display the personal controls corresponding to each singer based on the ranking data, and to identify the corresponding target singer upon touch. The cover song launch module is used to respond to touch events applied to any user control, and to retrieve from the server a cover song of the target song sung by the target singer corresponding to the touched user control, including: In response to a touch event applied to any personal control, the singer corresponding to the touched personal control is taken as the target singer, and a song cover request associated with the target singer and the target song is sent to the server. In response to a server push notification, the server downloads the audio data of the cover song generated in response to the song cover request. The audio data is obtained by replacing the corresponding vocal features of the target song with the vocal features of the target singer in the audio data of the target song. Display a notification message to the graphical user interface that a cover song has been obtained, and load the audio data of the cover song into the music playback control for playback.

9. A song cover performance device, characterized in that, It is implemented in a server to complete the collaboration with the song cover synthesis device of claim 8, including: The song determination module is used to respond to the singer matching request triggered by the terminal device and obtain the target song corresponding to the request; The matching execution module is used to query the vocal performance feature database to determine multiple singers whose vocal performance features match the original singer of the target song and their matching degree. The vocal performance features are timbre features and / or pitch features. The ranking execution module is used to rank the personal information of each singer by using the matching degree of each singer as the ranking index item, and generate ranking data in response to the singer matching request. The target determination module is used to respond to the song cover request of the terminal device and determine the target singer specified in the request. The target singer is any singer in the ranking data. The cover song execution module is used to replace the vocal characteristics of the target song with the vocal characteristics of the target singer to obtain a cover song; The song push module is used to push the cover song to the terminal device.

10. A computer device comprising a central processing unit and a memory, characterized in that, The central processing unit is used to invoke and run a computer program stored in the memory to perform the steps of the method as described in any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that, It stores, in the form of computer-readable instructions, a computer program implemented according to any one of claims 1 to 7, which, when invoked by a computer, executes the steps included in the corresponding method.

12. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1 to 7.

Images