Songwriting method, songwriting device, storage medium, and electronic device

Abstract

The method comprises: in response to a triggering operation on a song creation control, displaying a song recommendation interface; the song recommendation interface comprises M songs to be imitated; in response to selection of a song to be imitated from the song recommendation interface, displaying a song strategy interface; the song strategy interface comprises a plurality of song strategies; in response to selection of a target song strategy from the song strategy interface, displaying a lyrics strategy interface; the lyrics strategy interface is used for selecting or inputting a lyrics strategy; in response to determination of a target lyrics strategy from the lyrics strategy interface, displaying a sound source strategy interface; and in response to determination of a target sound source strategy from the sound source strategy interface, displaying a target song. The present disclosure provides a new interactive form for song creation, which helps users quickly familiarize with the song creation process and generate a good target song.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of human-computer interaction, and more particularly, embodiments of the present disclosure relate to a song creation method, a song creation device, a computer readable storage medium and an electronic device. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the present disclosure and as such description herein can not be construed as an admission that the subject matter disclosed and / or claimed herein is not entitled to antedate such prior art.

[0003] Existing music applications (Apps) mostly only support some mature creators to write songs in the whole link, that is, the steps of lyrics writing, music composing and arrangement included in the creation process can only be relied on the creation ability of the creators themselves. However, the above scheme and product have a high requirement on the creation ability of the user themselves, are not suitable for some new creators, cannot mobilize the creation enthusiasm of the new creators, and have a narrow application range. SUMMARY

[0004] Therefore, there is a great need for a song creation method, which can create a new target song starting from imitating a song, so as to provide a creation idea for new creators and help them learn the creation method of the song.

[0005] In this context, embodiments of the present disclosure aim to provide a song creation method, a song creation device, a computer readable storage medium and an electronic device.

[0006] According to a first aspect of the embodiments of the present disclosure, a song creation method is provided, comprising: in response to a triggering operation of a song creation control, displaying a song recommendation interface; the song recommendation interface includes M songs to be imitated; M is an integer greater than 1; in response to selecting a song to be imitated from the song recommendation interface, displaying a song strategy interface; the song strategy interface includes a plurality of song strategies; in response to selecting a target song strategy from the song strategy interface, displaying a lyrics strategy interface; the lyrics strategy interface is used to select or input a lyrics strategy; in response to determining a target lyrics strategy from the lyrics strategy interface, displaying a sound source strategy interface; the sound source strategy interface includes a plurality of sound source strategies containing different timbres; in response to determining a target sound source strategy from the sound source strategy interface, displaying a target song, which is generated according to the song to be imitated, the target song strategy, the target lyrics strategy and the target sound source strategy.

[0007] In an exemplary embodiment of the present disclosure, the M songs to be imitated are determined according to historical listening data of a user; the historical listening data of the user includes a plurality of historical playback songs and a playback parameter corresponding to each historical playback song; the playback parameter includes the number of plays and / or the playback time.

[0008] In an example embodiment of the present disclosure, the method further comprises: displaying, in the song recommendation interface, a plurality of singer names and N songs to be imitated corresponding to each singer name; the plurality of singer names are obtained according to singer information corresponding to the M songs to be imitated; wherein N is an integer greater than or equal to 1, and N is less than M.

[0009] In an example embodiment of the present disclosure, the displaying, in the song recommendation interface, the plurality of singer names and N songs to be imitated corresponding to each singer name comprises: displaying the plurality of singer names based on a first display order; the first display order is determined according to a similarity between singers corresponding to the plurality of singer names and a user preferred singer, and the user preferred singer is determined according to a user portrait feature and historical listening data; and displaying the N songs to be imitated based on a second display order; the second display order is determined according to a similarity between the N songs to be imitated and a user preferred creation song, and the user preferred creation song is determined according to the user portrait feature and historical creation features.

[0010] In an example embodiment of the present disclosure, the displaying, in the song recommendation interface, the plurality of singer names and N songs to be imitated corresponding to each singer name comprises: displaying the plurality of singer names based on a third display order; the third display order is determined according to an alphabetical order of the plurality of singer names; and displaying the N songs to be imitated based on a fourth display order; the fourth display order is determined according to a ranking of the N songs to be imitated in a preset song list.

[0011] In an example embodiment of the present disclosure, after the song to be imitated is selected from the song recommendation interface, before the song strategy interface is displayed, the method further comprises: displaying a preview control of the song to be imitated in the song recommendation interface; and in response to receiving a triggering operation on the preview control, playing the song to be imitated or a specified segment of the song to be imitated.

[0012] In an example embodiment of the present disclosure, the lyrics strategy interface further comprises a lyrics strategy input control; and the method further comprises: setting the lyrics strategy input control to a disabled state when a number of target lyrics strategies selected from the lyrics strategy interface meets a preset number condition.

[0013] In an example embodiment of the present disclosure, the lyrics strategy comprises a lyrics keyword; and the method further comprises: obtaining an associated keyword of the lyrics keyword, the associated keyword being generated according to a word meaning analysis result of the lyrics keyword; and displaying the associated keyword to the lyrics strategy interface.

[0014] In an example embodiment of the present disclosure, the displaying the target song comprises: displaying a playing interface of the target song, the playing interface comprising a playing control; and in response to receiving a triggering operation on the playing control, playing the target song and dynamically displaying lyrics of the target song on the playing interface.

[0015] In an example embodiment of the present disclosure, the dynamically displaying the lyrics of the target song on the playing interface comprises: differentially displaying lyrics keywords in the lyrics.

[0016] In an example embodiment of the present disclosure, the playing interface further comprises a downloading control for downloading the target song and / or creation information of the target song to a specified storage location; the creation information comprises accompaniment audio and MIDI score files of the target song.

[0017] In an example embodiment of the present disclosure, the playing interface further comprises a sharing control for sharing the target song to a preset application or to a preset contact.

[0018] In an example embodiment of the present disclosure, the target song is a plurality of songs; the method further comprises: displaying a playing interface corresponding to each target song; and in response to receiving a switching operation on the playing interface, switching the target song.

[0019] In an example embodiment of the present disclosure, the playing interface further comprises a song replacement control; the method further comprises: in response to receiving a triggering operation on the song replacement control, displaying a new target song; the new target song is a plurality of songs regenerated according to the to-be-imitated song, the target song strategy, the target lyrics strategy and the target audio source strategy.

[0020] According to a second aspect of the present disclosure, a song creation method is provided, comprising: extracting features of a selected to-be-imitated song to obtain song features of the to-be-imitated song; the song features comprise frequency spectrum features, voice features and rhythm features; generating composition information according to the song features of the to-be-imitated song and a selected target song strategy; generating a music accompaniment based on the composition information; generating target lyrics according to a selected target lyrics strategy and lyrics of the to-be-imitated song; generating a music main melody according to the music accompaniment, the target lyrics and a selected target audio source strategy; and performing mixing processing on the music main melody and the music accompaniment to obtain a created target song.

[0021] In an exemplary embodiment of this disclosure, the mixing process of the main melody and the accompaniment to obtain the target song includes: dividing the main melody into K melody segments according to a preset time interval; and dividing the accompaniment into K accompaniment segments according to the preset time interval; where K is an integer greater than 1; mixing the melody segments and accompaniment segments in the same duration interval to obtain K audio segments; and splicing the K audio segments according to their start and end times to obtain the target song.

[0022] According to a third aspect of the present disclosure, a song creation apparatus is provided, comprising: a song recommendation module, configured to display a song recommendation interface in response to a trigger operation of a song creation control; the song recommendation interface includes M songs to be imitated; M is an integer greater than 1; a song strategy display module, configured to display a song strategy interface in response to selecting a song to be imitated from the song recommendation interface; the song strategy interface includes multiple song strategies; a lyrics strategy display module, configured to display a lyrics strategy interface in response to selecting a target song strategy from the song strategy interface; the lyrics strategy interface is used to select or input a lyrics strategy; a sound source display module, configured to display a sound source strategy interface in response to determining a target lyrics strategy from the lyrics strategy interface; the sound source strategy interface includes multiple sound source strategies containing different timbres; and a song display module, configured to display a target song in response to determining a target sound source strategy from the sound source strategy interface, the target song being generated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target sound source strategy.

[0023] According to a fourth aspect of this disclosure, a song creation apparatus is provided, comprising: a feature extraction module for extracting features from a selected song to be imitated to obtain song features of the song to be imitated; the song features include spectral features, speech features, and rhythmic features; a composition module for generating composition information based on the song features of the song to be imitated and a selected target song strategy; an accompaniment generation module for generating a musical accompaniment based on the composition information; a lyrics generation module for generating target lyrics based on a selected target lyrics strategy and the lyrics of the song to be imitated; a melody generation module for generating a musical melody based on the musical accompaniment, the target lyrics, and a selected target sound source strategy; and a mixing processing module for mixing the musical melody and the musical accompaniment to obtain a created target song.

[0024] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements any of the above-described song creation methods.

[0025] According to a sixth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any of the above-described song creation methods by executing the executable instructions.

[0026] According to the song creation method, song creation apparatus, computer-readable storage medium, and electronic device disclosed herein, the interactive process for song creation provided by this disclosure helps creators quickly and conveniently complete related song creation, reducing the requirements on users' own creative abilities. Whether a novice or an experienced creator, they can easily and quickly obtain well-composed target songs through simple interactive operations, and can further create based on these target songs. This avoids the problem of not being able to generate songs due to insufficient user creative ability, increases the creative enthusiasm of novice creators, and also expands the applicability of related music apps. The process from imitation to creation provided by this disclosure allows novice creators to start by imitating songs, learn the song creation process, provide creative inspiration, and thus stimulate their creative potential. Attached Figure Description

[0027] The above and other objects, features, and advantages of this disclosure will become readily apparent from the following detailed description of exemplary embodiments, taken in conjunction with the accompanying drawings. Several embodiments of this disclosure are illustrated in the drawings by way of example and not limitation, in which:

[0028] Figure 1 A flowchart of the song creation method in an embodiment of this disclosure is shown;

[0029] Figure 2 A schematic diagram of the initial interface in an embodiment of this disclosure is shown;

[0030] Figure 3 The flowchart illustrates an embodiment of the present disclosure of displaying multiple singer names and N songs to be imitated for each singer name in a song recommendation interface.

[0031] Figure 4 This illustration shows a diagram of multiple singer names displayed in a first display order and N songs to be imitated displayed in a second display order according to an embodiment of this disclosure.

[0032] Figure 5 This illustration shows a schematic diagram of adjusting the audio-visual control to a playback state in an embodiment of this disclosure;

[0033] Figure 6 This illustration shows another flowchart in an embodiment of the present disclosure of displaying multiple singer names and N songs to be imitated for each singer name in a song recommendation interface;

[0034] Figure 7 A schematic diagram of the song recommendation interface after switching the singer's name and the song to be imitated in an embodiment of this disclosure is shown;

[0035] Figure 8 A schematic diagram of the interface for filtering songs to be imitated based on the singer's name is shown in an embodiment of this disclosure;

[0036] Figure 9 A schematic diagram of the interface for selecting songs to be imitated based on song style is shown in an embodiment of this disclosure;

[0037] Figure 10 A schematic diagram of the song strategy interface in an embodiment of this disclosure is shown;

[0038] Figure 11 A schematic diagram of the lyrics strategy interface in an embodiment of this disclosure is shown;

[0039] Figure 12 A schematic diagram of the sound source strategy interface in an embodiment of this disclosure is shown;

[0040] Figure 13 This illustration shows a schematic diagram of adjusting the playback control to a playback state in an embodiment of the present disclosure;

[0041] Figure 14 A schematic diagram of a transition interface according to an embodiment of this disclosure is shown;

[0042] Figure 15 A flowchart illustrating the generation of the target song in an embodiment of this disclosure is shown;

[0043] Figure 16 A schematic diagram of a playback interface for a target song in an embodiment of this disclosure is shown;

[0044] Figure 17 This illustration shows a schematic diagram of a claims prompt box displayed on the playback interface in an embodiment of this disclosure;

[0045] Figure 18 A schematic diagram of the secondary confirmation interface in an embodiment of this disclosure is shown;

[0046] Figure 19 This illustration shows a schematic diagram of displaying the target song at a designated storage location in an embodiment of this disclosure;

[0047] Figure 20 This illustration shows a schematic diagram of the interface after sharing the target song to the file transfer assistant in an embodiment of this disclosure;

[0048] Figure 21 A schematic diagram of the interface after a preset contact clicks the share link in an embodiment of this disclosure is shown;

[0049] Figure 22 A schematic diagram of the playback interface of another target song in an embodiment of this disclosure is shown;

[0050] Figure 23 A schematic diagram of a playback interface for another target song in an embodiment of this disclosure is shown;

[0051] Figure 24 A schematic diagram of another transition interface in an embodiment of this disclosure is shown;

[0052] Figure 25 A schematic diagram of a song creation apparatus according to an embodiment of the present disclosure is shown;

[0053] Figure 26 A schematic diagram of another song creation apparatus according to an embodiment of the present disclosure is shown; and

[0054] Figure 27 A structural diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0055] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0056] The principles and spirit of this disclosure will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement this disclosure, and are not intended to limit the scope of this disclosure in any way. Rather, these embodiments are provided to make this disclosure more thorough and complete, and to fully convey the scope of this disclosure to those skilled in the art.

[0057] Those skilled in the art will recognize that embodiments of this disclosure can be implemented as a system, apparatus, device, method, or computer program product. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0058] According to embodiments of this disclosure, a song creation method, a song creation apparatus, a computer-readable storage medium, and an electronic device are provided.

[0059] In this document, any number of elements in the accompanying figures is for illustrative purposes and not for limitation, and any naming is for distinction only and has no limiting meaning.

[0060] The principles and spirit of this disclosure are explained in detail below with reference to several representative embodiments. SUMMARY

[0062] The inventors have discovered that most existing music apps only support established songwriters to write songs throughout the entire process, and are not suitable for new songwriters. This results in a narrow audience, fails to motivate new songwriters, and has a limited scope of application.

[0063] In view of the above, the basic idea of ​​this disclosure is that the interactive song creation process provided by this disclosure can help creators quickly and conveniently complete the creation of related songs, reducing the requirements on users' own creative abilities. Whether a novice or an experienced creator, they can easily and quickly obtain well-composed target songs through simple interactive operations, and can further create based on these target songs. This avoids the problem of not being able to generate songs due to insufficient user creative ability, increases the creative enthusiasm of novice creators, and also expands the applicability of related music apps. The process from imitation to creation provided by this disclosure allows novice creators to start by imitating songs, learn the song creation process, provide creative inspiration, and thus stimulate their creative potential.

[0064] After introducing the basic principles of this disclosure, various non-limiting embodiments of this disclosure will be described in detail below.

[0065] OVERVIEW OF APPLICATION SCENARIOS

[0066] It should be noted that the following application scenarios are shown only to facilitate understanding of the spirit and principles of this disclosure, and the implementation of this disclosure is not limited in any way. On the contrary, the implementation of this disclosure can be applied to any applicable scenario.

[0067] The embodiments of this disclosure support the creation of target songs based on songs selected by the user. For example, in a music app, after detecting a user's trigger operation on the song creation control, a song recommendation interface can be displayed. After the user selects a song to be imitated from the song recommendation interface, a song strategy interface can be displayed. After obtaining the target song strategy selected by the user from the song strategy interface, a lyrics strategy interface can be displayed. After the user selects a target lyrics strategy from the lyrics strategy interface, a sound source strategy interface can be displayed. After obtaining the target sound source strategy selected by the user from the sound source strategy interface, the user terminal can upload the song to be imitated, the target song strategy, the target lyrics strategy, and the target sound source strategy to the server. Then, the user terminal receives the target song generated by the server based on the above information and displays the target song for the user to play, share, download, etc.

[0068] EXEMPLARY METHOD

[0069] The exemplary embodiments of this disclosure first provide a song creation method. Figure 1A flowchart of a song creation method according to an embodiment of this disclosure is shown, which may include the following steps S110 to S150:

[0070] It should be noted that before step S110, a song creation entry point can be displayed on the music app. This entry point can display relevant introductory information or recommendations for song creation. Therefore, when the user clicks on the song creation entry point, an initial interface containing song creation controls can be displayed. This initial interface includes the song creation controls that trigger the song creation process. (Reference) Figure 2 , Figure 2 The diagram shows the initial interface in this embodiment of the present disclosure. The function corresponding to the above-mentioned song creation method can also be named "AI One-Click Songwriting Assistant," and the name of the song creation method can be displayed on the initial interface. Figure 2 The circles in the diagram represent the song creation controls mentioned above. These controls can be designed in different shapes according to actual needs, such as triangles, rhombuses, irregular shapes, etc. They can be set according to the actual situation, and this disclosure does not impose any special limitations on them.

[0071] In step S110, in response to the trigger operation of the song creation control, the song recommendation interface is displayed.

[0072] In this step, after detecting the user's trigger operation on the above-mentioned song creation control, a song recommendation interface containing M (an integer greater than 1, which can be set according to the actual situation, and this disclosure does not make any special restrictions on it) songs to be imitated can be displayed.

[0073] The triggering operation mentioned above can be a single click, double click, long press, etc., and can be set according to the actual situation. This disclosure does not impose any special restrictions on it.

[0074] The aforementioned M songs to be imitated can be determined by the server based on the user's historical listening data. Specifically, the server can obtain multiple historical songs played by the user and the playback parameters corresponding to each historical song, and select M songs to be imitated from the multiple historical songs based on the playback parameters of each historical song.

[0075] In one optional implementation, the aforementioned multiple historical playback songs can be historical playback songs used in the past two months (which can be set according to actual conditions, and this disclosure does not make any special limitation on this). The aforementioned playback parameter can be the number of times the songs have been played. Thus, the server can sort the aforementioned multiple historical playback songs in descending order of the number of times the historical playback songs have been played, and select the top M historical playback songs from the sorted sequence as the aforementioned M songs to be imitated.

[0076] In another optional implementation, the playback parameter can be the playback duration. Thus, the server can sort the multiple historically played songs in descending order of their playback durations, and select the top M historically played songs from the sorted sequence as the M songs to be imitated.

[0077] In another alternative implementation, the playback parameters can be the number of playbacks and the playback duration. For example, the number of playbacks and the playback duration of each historically played song can be weighted to obtain a comprehensive value. Then, the multiple historically played songs can be sorted in descending order of the comprehensive value, and the top M historically played songs in the sorted sequence can be selected as the M songs to be imitated.

[0078] After the server selects the above M songs to be imitated, it can also count the multiple singer names corresponding to the above M songs to be imitated. Then, it can categorize the N (N is an integer greater than or equal to 1, and N is less than M) songs to be imitated corresponding to each singer name. Furthermore, it can send the above multiple singer names and the N songs to be imitated corresponding to each singer name to the user terminal so that the above multiple singer names and the N songs to be imitated corresponding to each singer name can be displayed in the song recommendation interface of the user terminal.

[0079] refer to Figure 3 , Figure 3 This illustration shows a flowchart of an embodiment of the present disclosure of displaying multiple singer names and N songs to be imitated for each singer name in a song recommendation interface, including steps S301-S302:

[0080] In step S301, multiple singer names are displayed based on the first display order.

[0081] In this step, the first display order mentioned above can be determined by the server based on the similarity between the singers corresponding to multiple singer names and the singers preferred by the user. The singers preferred by the user are determined based on the user's profile characteristics and historical listening data.

[0082] The aforementioned profile features may include the user's basic information (e.g., age, gender, occupation, etc.), demographic characteristics (e.g., city of residence), app usage preferences (e.g., listening time period, average daily listening time, etc.), and historical listening data, namely the aforementioned historical songs and the playback duration and / or playback parameters of each historical song.

[0083] Furthermore, the server can identify users' preferred singers based on the aforementioned profile features and historical listening data. After identifying these singers, the similarity score between each singer's name and the aforementioned preferred singers can be calculated. The order of similarity scores from highest to lowest is then used as the first display order. If there are multiple preferred singers, the average similarity score between each singer and all the preferred singers can be calculated, and the order of average similarity scores from highest to lowest is then used as the first display order.

[0084] In step S302, N songs to be imitated are displayed based on the second display order.

[0085] In this step, the second display order is determined based on the similarity between the N songs to be imitated and the user's preferred creation songs. The user's preferred creation songs are determined based on the user's profile characteristics and historical creation characteristics.

[0086] The aforementioned historical creative characteristics can include songs selected by the user within a preset time period. The server can then identify the user's preferred songs based on these profile characteristics and historical creative characteristics. After identifying these preferred songs, the similarity between the N songs to be imitated corresponding to each artist's name and the user's preferred songs can be calculated. The order of similarity from highest to lowest is determined as the second display order. If there are multiple user-preferred songs, the average similarity between each song to be imitated and these multiple user-preferred songs can be calculated, and the order of average similarity from highest to lowest is determined as the second display order.

[0087] For example, refer to Figure 4 , Figure 4 The illustration shows a schematic diagram of displaying multiple singer names based on a first display order and N songs to be imitated based on a second display order in an embodiment of this disclosure. For example, an audio preview control for each song to be imitated can also be displayed after it. Thus, when a trigger operation on the audio preview control is detected, the song to be imitated or a climax segment of the song to be imitated can be played. This can be set according to the actual situation, and this disclosure does not impose any special limitations on it.

[0088] For example, after detecting a user's triggering operation on the audio-visual control, the display state of the audio-visual control can be updated to adjust it to a playback state, as shown in the reference. Figure 5 , Figure 5 The illustration shows a schematic diagram of adjusting the audio-visual control to the playback state in an embodiment of this disclosure. For example, if the user clicks the audio-visual control again, the playback can be stopped and the audio-visual control can be restored to its initial state. If the user clicks it again thereafter, the playback will start from the beginning.

[0089] refer to Figure 6 ,Figure 6 This illustration shows another flowchart in an embodiment of the present disclosure of displaying multiple singer names and N songs to be imitated for each singer name in a song recommendation interface, including steps S601-S602:

[0090] In step S601, multiple singer names are displayed based on the third display order.

[0091] In this step, the third display order can be determined based on the alphabetical order of the first letters of the singers' names. For example, the server can count the first letters of the singers' names and then display them in order from A to Z.

[0092] In step S602, N songs to be imitated are displayed based on the fourth display order.

[0093] In this step, the fourth display order can be determined based on the ranking of the N songs to be imitated in a preset song chart. Specifically, the server can obtain a preset song chart, such as a weekly popular song chart or a monthly popular song chart, and can set it according to the actual situation. This disclosure does not impose any special restrictions on this. After obtaining the preset song chart, the ranking of the aforementioned N songs to be imitated in the preset song chart can be obtained separately, and the aforementioned N songs to be imitated can be displayed in order of ranking from first to last.

[0094] It should be noted that after displaying the multiple singer names and the N songs to be imitated for each singer name, users can swipe up and down on the multiple singer names to switch between them, and also swipe up and down on the N songs to be imitated for each singer name to switch between them. It should be noted that if song ABCD is currently playing, and the user swipes up or down to song ACCD, playback of song ABCD will stop. (Reference) Figure 7 , Figure 7 This illustration shows a schematic diagram of the song recommendation interface after switching the singer's name and the song to be imitated in an embodiment of this disclosure. Specifically, Figure 7 Showing will Figure 4 The singer's name "Zhang San" in the video was changed to "Wang Wu". Figure 4 This is a diagram of the song recommendation interface after the song to be imitated, "ABCD", is switched to "ADCD".

[0095] It should be noted that users can also click on the "Artist" or "Style" controls on the song recommendation interface to quickly filter the songs they want to imitate based on the artist's name or the song's style.

[0096] refer to Figure 8 , Figure 8The diagram shows an interface for filtering songs to be imitated based on the singer's name in this embodiment of the present disclosure. "Cao Da-Guan Qi" on the left is the singer's name, and "ABC-ABZ" on the right is the N songs to be imitated that are included in the singer's name "Li Si". The user can switch singer names by swiping up and down and select the song to be imitated from the N songs to be imitated corresponding to the selected singer's name.

[0097] refer to Figure 9 , Figure 9 The diagram shows an interface for filtering songs to be imitated based on song style in an embodiment of this disclosure. "Electronic-Jazz" on the left represents the song style, and "DD-Cao Da" to "GG-Ma Ba" on the right represent different songs and their artists. Users can switch song styles by swiping up and down and select the song to be imitated from the selected artist style.

[0098] After selecting a song to imitate, the user can click the "Next" control, and then proceed to step S120, where the song strategy interface is displayed in response to selecting a song to imitate from the song recommendation interface.

[0099] In this step, in response to the user selecting a song to imitate from the song recommendation interface, the user terminal can display a song strategy interface, which can include a variety of song strategies.

[0100] The aforementioned song strategy refers to a song imitation strategy. For example, an imitation strategy may include two types: imitating the singer or imitating the song style. These can be set according to the actual situation, and this disclosure does not impose any special limitations on them.

[0101] refer to Figure 10 , Figure 10 A schematic diagram of the song strategy interface in this embodiment is shown. Users can click on "Singer" or "Style" on the song strategy interface to imitate the song from two different imitation strategies in order to create the target song.

[0102] After the user selects a song strategy from the song strategy interface, the song strategy can be designated as the target song strategy. Then, step S130 can be entered, and in response to selecting the target song strategy from the song strategy interface, the lyrics strategy interface is displayed; the lyrics strategy interface is used to select or input lyrics strategy.

[0103] In this step, in response to the user having selected a target song strategy from the aforementioned song strategy interface, the user terminal can display the lyrics strategy interface. The lyrics strategy interface is used to select or input lyrics strategies. Lyric strategies can be lyrics keywords or lyrics sentences, etc., and can be set according to actual circumstances; this disclosure does not impose any special limitations on this.

[0104] For example, refer to Figure 11 , Figure 11 A schematic diagram of the lyrics strategy interface in this embodiment is shown. The center of the lyrics strategy interface can display multiple preset lyrics keyword labels. When a user clicks on a preset keyword, that keyword can be selected as the target lyrics strategy. At this time, the label of the preset keyword can be grayed out to prevent it from being selected repeatedly. When the user long-presses on the label of the preset lyrics keyword, or drags the label of the preset lyrics keyword to the bottom of the lyrics strategy interface, the selection of that lyrics keyword can be deselected.

[0105] The lyrics strategy interface may also include a lyrics strategy input control (i.e. Figure 11 The circled plus sign control allows users to input lyrics keywords after clicking the lyrics input control. After inputting the lyrics keywords, the keywords can be added as tags to the multiple preset lyrics keyword tags.

[0106] Optionally, after a user inputs a lyric keyword, the user terminal can send the keyword to the server. The server can then perform semantic analysis on the keyword, generate related keywords based on the analysis results, and return these related keywords to the user terminal for display in the lyrics strategy interface. The number of related keywords can be set according to actual needs, and this disclosure does not impose any special limitations on it.

[0107] When the number of target lyrics strategies selected by the user meets the preset threshold (e.g., 4, which can be set according to the actual situation, and this disclosure does not make any special limitation), the above lyrics strategy input control can be set to the disabled state.

[0108] After the user has selected the target lyrics strategy from the lyrics strategy interface, they can click... Figure 11 The "Next" control in the text allows you to proceed to step S140, where the sound source strategy interface is displayed in response to determining the target lyrics strategy from the lyrics strategy interface.

[0109] In this step, in response to the user determining the target lyrics strategy from the lyrics strategy interface, the sound source strategy interface can be displayed. The sound source strategy interface includes a variety of sound source strategies containing different timbres. The sound source strategy can be multiple different virtual singers (each virtual singer corresponds to a different timbre). For example, in this disclosure, multiple virtual singers can be pre-set and displayed in the above-mentioned sound source strategy interface.

[0110] For example, refer to Figure 12 , Figure 12A schematic diagram of the audio source strategy interface in an embodiment of this disclosure is shown. The audio source strategy interface can display information on three virtual singers at a time (these can be avatars or names, and can be set according to actual conditions). Figure 12 The virtual singers "Xiao Wang," "Xiao Bai," and "Xiao Li" in the middle of the list can display a playback control on their information screen. When a user clicks this playback control, they can then refer to... Figure 13 , Figure 13 The diagram illustrates how the playback control is adjusted to the playback state in an embodiment of this disclosure. When the playback control is adjusted to the playback state, the virtual singer's voice can be played, such as playing the virtual singer's voice saying a sentence, or playing a segment of the virtual singer singing a song. These can all be set according to the actual situation, and this disclosure does not impose any special limitations on them.

[0111] Next, refer to Figure 12 It should be noted that users can switch between different virtual singers by swiping left and right. When the virtual singer's avatar is moved to the center, the avatar can be enlarged and the aforementioned playback controls can be displayed on the avatar.

[0112] Furthermore, after the user swipes left and right and listens to the voices of different virtual singers, the user can select the voice of a particular virtual singer as the target sound source strategy. After determining the target sound source strategy, the process proceeds to step S150, where, in response to determining the target sound source strategy from the sound source strategy interface, the target song is displayed. The target song is generated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target sound source strategy.

[0113] In this step, in response to the user specifying the target audio source strategy from the audio source strategy interface, the user terminal can send the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy to the server. Then, the server can generate the created target song based on the information such as the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy.

[0114] It should be noted that after the user terminal sends the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy to the server, the user terminal can display a transition interface before the server returns the target song. (See reference...) Figure 14 , Figure 14 The diagram shows a transition interface according to an embodiment of the present disclosure. For example, a progress circle can be displayed in the middle of the transition interface. The center of the progress circle displays the generation progress of the target song, for example, 58%. The area around the progress circle can display information such as the target lyrics strategy or the target song strategy selected by the user. These can be set according to the actual situation, and the present disclosure does not impose any special limitations on them.

[0115] The server can input the aforementioned song to be imitated, target song strategy, target lyrics strategy, and target audio source strategy into a pre-trained song creation model. The model will then perform the following processing steps to generate the target song:

[0116] refer to Figure 15 , Figure 15 A flowchart illustrating the generation of the target song in this embodiment of the present disclosure is shown, including steps S1501-S1506:

[0117] In step S1501, feature extraction is performed on the selected song to be imitated to obtain the song features of the song to be imitated.

[0118] In this step, the song creation model described above can extract features from the song to be imitated, obtaining the spectral features, speech features, and rhythmic features of the song to be imitated.

[0119] In step S1502, composition information is generated based on the song characteristics of the song to be imitated and the selected target song strategy.

[0120] In this step, the song creation model described above can use the selected target song strategy to imitate the song characteristics of the song to be imitated, generating well-imitated composition information. Composition is the foundation of arrangement; composition refers to creating the score for a song.

[0121] In step S1503, a musical accompaniment is generated based on the composition information.

[0122] In this step, the song creation model described above can generate a musical accompaniment based on the composition information. The musical accompaniment is the arrangement information; arrangement is the process of adding drum beats, harmonies, and various electronic effects to the composition at appropriate points.

[0123] In step S1504, target lyrics are generated based on the selected target lyrics strategy and the lyrics of the song to be imitated.

[0124] In this step, the song creation model described above can generate a target song based on the selected target lyrics strategy and the lyrics of the song to be imitated. For example, the lyrics of the song to be imitated can be processed by performing related synonym or near-synonym substitutions to generate the target lyrics.

[0125] In step S1505, the main melody of the music is generated based on the musical accompaniment, the target lyrics, and the selected target sound source strategy.

[0126] In this step, the above-mentioned song creation and imitation strategy can control the selected target sound source strategy to sing the target lyrics based on the above-mentioned musical accompaniment in order to generate the main melody of the music.

[0127] In step S1506, the main melody and accompaniment of the music are mixed to obtain the created target song.

[0128] In this step, the song creation model described above can mix the main melody and accompaniment of the music to obtain the created target song.

[0129] Mixing is a step in music production that combines sounds from multiple sources into a single stereo or mono track. These mixed sound signals may originate from different instruments, vocals, or orchestral instruments, and may have been recorded live or in a recording studio.

[0130] Specifically, the song creation model can divide the main melody of the music into K (K is an integer greater than 1) main melody segments according to a preset time interval, and divide the music accompaniment into K accompaniment segments according to a preset time interval. Then, the main melody segments and accompaniment segments in the same duration interval are mixed to obtain K audio segments. The K audio segments are spliced ​​together according to the start and end times of the K audio segments to obtain the target song.

[0131] For example, taking a 3-minute duration for both the main melody and accompaniment, and using K as an example (3), the main melody can be divided into three segments: (0-1, 1-2, 2-3). The accompaniment can also be divided into three segments: (0-1, 1-2, 2-3). First, the melody and accompaniment segments in the 0-1 duration range can be mixed to obtain the audio segment for that range. Then, the melody and accompaniment segments in the 1-2 duration range can be mixed again to obtain the audio segment for that range. Finally, the melody and accompaniment segments in the 2-3 duration range can be mixed to obtain the audio segment for that range. Finally, these three audio segments can be spliced ​​together according to their start and end times to obtain the target song.

[0132] Based on the above-described segmented mixing method in this disclosure, the target song can be played after the first or first few audio segments are obtained. Thus, during the playback of the first or first few audio segments, the subsequent mixing process can be processed simultaneously, thereby shortening the user's waiting time and allowing the user to listen to the target song in a shorter time (generally 3 to 5 seconds), thus optimizing the user experience.

[0133] After the target song is generated on the server side, it can be returned to the user terminal. This target song can be a single song or a batch of songs, i.e., multiple songs. The target song can then be displayed on the user terminal. The user terminal can then display a playback interface for the target song, which may include playback controls. When the user triggers these controls, the target song can be played. Simultaneously, the lyrics of the target song can be dynamically displayed on the playback interface. Furthermore, when dynamically displaying the lyrics, lyric strategies (i.e., lyric keywords) can be displayed differently, such as by enlarging, bolding, underlining, highlighting, or using other colors. These can be set according to actual needs, and this disclosure does not impose any special limitations on them.

[0134] Specifically, when the target song mentioned above is a single song, you can refer to... Figure 16 , Figure 16 A schematic diagram of a playback interface for a target song according to an embodiment of the present disclosure is shown. The playback interface can display the cover of the target song, which includes playback controls. The song title, lyrics, and other information can be displayed below the cover.

[0135] Referring to the explanation of step S1506 above, it can be seen that this disclosure can start playing the target song after the first or first few audio segments of the target song, that is, display the playback interface of the target song. For this situation, please refer to... Figure 16 At this point, a "File generating..." prompt control can be displayed on the playback interface, allowing the user to play the target song but not download it.

[0136] Following the explanation of step S1506 above, after splicing K audio segments to obtain the target song, the aforementioned prompt control can be updated to a "Download Production File" control. This allows the user to trigger the control to download the target song and / or its creation information to a specified storage location. The creation information includes the accompaniment audio and MIDI sheet music file of the target song. After the user clicks the "Download Production File" control, a rights statement prompt box can pop up to explain the copyright and usage information of the target song. (Refer to...) Figure 17 , Figure 17 The diagram illustrates a claim declaration prompt box displayed on the playback interface in an embodiment of this disclosure. This claim declaration prompt box may include a cancel control (i.e., the x in 17) and a "Confirm and Download" control. When the user clicks the "Confirm and Download" control, they are redirected to a secondary confirmation interface. (Reference) Figure 18 , Figure 18A schematic diagram of a secondary confirmation interface in an embodiment of this disclosure is shown. This interface displays the size of the target song and a download control. When the user clicks the download control, they can select a specified storage location to save the target song, and then save it to the specified storage location. (Reference) Figure 19 , Figure 19 This illustration shows a schematic diagram of displaying the target song at a specified storage location in an embodiment of this disclosure. Specifically, it shows an interface schematic diagram of storing the target song in an iCloud cloud drive when the specified storage location is an iCloud cloud drive.

[0137] The aforementioned playback interface may also include a sharing control (i.e., Figure 16 The "Share Song" function allows users to share generated target songs to preset applications (such as WeChat, Moments, Weibo, music apps, etc.) or to preset contacts. For example, see [link to documentation]. Figure 20 , Figure 20 The diagram illustrates the interface after sharing a target song to a file transfer assistant, as shown in this embodiment of the disclosure. The user can also share the target song to a preset contact. The preset contact can then click the relevant sharing link, and after clicking the link, can refer to... Figure 21 , Figure 21 The diagram shows the interface after a preset contact clicks the share link in an embodiment of this disclosure. The interface can display the creator of the target song (i.e., Zhao Liu in the figure), the song cover, lyrics, etc. At the same time, it can also display a "Try it too" control to guide the preset contact to try the relevant song creation process.

[0138] Next, refer to Figure 16 The aforementioned playback interface may also include a song switching control (i.e., Figure 16 The server can regenerate multiple target songs based on the previously selected song to be imitated, target song strategy, target lyrics strategy, and target audio source strategy, and then return them to the user terminal for display.

[0139] Optionally, after the user triggers the "rewrite" control, they can also be directly redirected to another page. Figure 2 The initial interface shown is for starting a new song creation process.

[0140] When the target song includes multiple songs, you can refer to... Figure 22 , Figure 22A schematic diagram of a playback interface for another target song in an embodiment of this disclosure is shown. This playback interface can display the covers of X songs (e.g., 3 songs) out of multiple songs. The cover of the song in the middle position contains playback controls. The song title, lyrics, and other information in the middle position can be displayed below the cover. Furthermore, when the user swipes left or right, they can switch to other X songs, as well as switch to the song in the middle position. When the song in the middle position changes, the song title, lyrics, and other information below the song cover will also change accordingly.

[0141] It should be noted that when the user scrolls to the last target song, refer to Figure 23 , Figure 23 The diagram illustrates a playback interface for another target song in an embodiment of this disclosure. The playback interface can display a prompt message "Swipe left to imitate 5 more songs" (the number of imitated songs can be set according to actual circumstances, and this disclosure does not impose any special limitations on this). Furthermore, after detecting a user's left swipe operation, another transition interface can be displayed. This transition interface is used for... Figure 23 Based on this, the creation progress of the above 5 songs is displayed for reference. Figure 24 , Figure 24 A schematic diagram of another transition interface in an embodiment of this disclosure is shown. Figure 24 The phrase "in imitation...56%" indicates the progress of the creation of the aforementioned five songs.

[0142] Similarly, after the above five songs have been imitated, users can listen to each target song by swiping left and right. Then, they can download the selected target song to a specified storage location using the "Download Created File" control on the playback interface, or share the selected target song to a preset application or preset contact using the "Share Song" control on the playback interface.

[0143] The interactive song creation process disclosed herein helps creators quickly and conveniently complete song creation, reducing the requirements on users' own creative abilities. Whether a novice or an experienced creator, they can easily and quickly obtain target songs through simple interactive operations and further create based on these target songs. This avoids the problem of being unable to generate songs due to insufficient user creative ability, increasing the creative enthusiasm of novice creators and expanding the applicability of related music apps. The process from imitation to creation provided in this disclosure allows novice creators to start by imitating songs, learning the song creation process, providing creative inspiration, and thus stimulating their creative potential.

[0144] EXEMPLARY DEVICE

[0145] After introducing the song creation method according to exemplary embodiments of this disclosure, the following will refer to... Figure 25 and Figure 26 The song creation apparatus according to an exemplary embodiment of the present disclosure will be described.

[0146] Figure 25 A schematic diagram of a song creation apparatus 2500 according to an embodiment of the present disclosure is shown, including:

[0147] The song recommendation module 2510 is used to display a song recommendation interface in response to the trigger operation of the song creation control; the song recommendation interface includes M songs to be imitated; M is an integer greater than 1;

[0148] The song strategy display module 2520 is used to display a song strategy interface in response to selecting a song to be imitated from the song recommendation interface; the song strategy interface includes a variety of song strategies.

[0149] The lyrics strategy display module 2530 is used to display the lyrics strategy interface in response to selecting a target song strategy from the song strategy interface; the lyrics strategy interface is used to select or input lyrics strategy.

[0150] The sound source display module 2540 is used to display the sound source strategy interface in response to determining the target lyrics strategy from the lyrics strategy interface; the sound source strategy interface includes a variety of sound source strategies containing different timbres.

[0151] The song display module 2550 is used to display a target song in response to determining a target sound source strategy from the sound source strategy interface. The target song is generated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target sound source strategy.

[0152] In one optional implementation, the M songs to be imitated are determined based on the user's historical listening data; the user's historical listening data includes multiple historically played songs and playback parameters corresponding to each historically played song; the playback parameters include the number of times played and / or the playback duration.

[0153] In one alternative implementation, the song recommendation module 2510 is configured as follows:

[0154] The song recommendation interface displays multiple singer names and N songs to be imitated for each singer name; the multiple singer names are obtained by statistical analysis based on the singer information corresponding to the M songs to be imitated; where N is an integer greater than or equal to 1 and N is less than M.

[0155] In one alternative implementation, the song recommendation module 2510 is configured as follows:

[0156] Based on a first display order, the names of the multiple singers are displayed; the first display order is determined based on the similarity between the singers corresponding to the multiple singer names and the singers preferred by the user, and the singers preferred by the user are determined based on the user's profile characteristics and historical listening data; based on a second display order, the N songs to be imitated are displayed; the second display order is determined based on the similarity between the N songs to be imitated and the songs created by the user, and the songs created by the user are determined based on the user's profile characteristics and historical creation characteristics.

[0157] In one alternative implementation, the song recommendation module 2510 is configured as follows:

[0158] Based on a third display order, the names of the multiple singers are displayed; the third display order is determined according to the alphabetical order of the first letters of the names of the multiple singers. Based on a fourth display order, the N songs to be imitated are displayed; the fourth display order is determined according to the ranking of the N songs to be imitated in a preset song list.

[0159] In an alternative implementation, after selecting a song to be imitated from the song recommendation interface and before displaying the song strategy interface, the song recommendation module 2510 is configured to:

[0160] The song recommendation interface displays a preview control for the song to be imitated; in response to receiving a trigger operation on the preview control, the song to be imitated or a specified segment of the song to be imitated is played.

[0161] In one optional implementation, the lyrics strategy interface further includes a lyrics strategy input control; the lyrics strategy display module 2530 is configured as follows:

[0162] When the number of target lyric strategies selected from the lyric strategy interface meets the preset number condition, the lyric strategy input control is set to a disabled state.

[0163] In one optional implementation, the lyrics strategy includes lyrics keywords; the lyrics strategy display module 2530 is configured to:

[0164] Obtain the associated keywords of the lyrics keywords, which are generated based on the semantic analysis results of the lyrics keywords; display the associated keywords in the lyrics strategy interface.

[0165] In one alternative implementation, the song display module 2550 is configured as follows:

[0166] The playback interface of the target song is displayed, and the playback interface includes a playback control; in response to receiving a trigger operation on the playback control, the target song is played, and the lyrics of the target song are dynamically displayed on the playback interface.

[0167] In one alternative implementation, the song display module 2550 is configured as follows:

[0168] The lyrics keywords are displayed in a distinctive manner.

[0169] In one optional implementation, the playback interface further includes a download control, which is used to download the target song and / or the creation information of the target song to a specified storage location; wherein, the creation information includes the accompaniment audio and MIDI sheet music file of the target song.

[0170] In one optional implementation, the playback interface further includes a sharing control for sharing the target song to a preset application or to a preset contact.

[0171] In one optional implementation, the target songs are multiple songs; the song display module 2550 is configured as follows:

[0172] Display the playback interface corresponding to each target song; in response to receiving a switching operation on the playback interface, switch the target song.

[0173] In one optional implementation, the playback interface further includes a song changing control, and the song display module 2550 is configured as follows:

[0174] In response to receiving a trigger operation on the song replacement control, a new target song is displayed; the new target song is a plurality of songs regenerated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy.

[0175] Figure 26 A schematic diagram of another song creation apparatus 2600 according to an embodiment of this disclosure is shown, including:

[0176] The feature extraction module 2610 is used to extract features from the selected song to be imitated, and obtain the song features of the song to be imitated; the song features include spectral features, speech features and rhythm features;

[0177] The composition module 2620 is used to generate composition information based on the song characteristics of the song to be imitated and the selected target song strategy;

[0178] Accompaniment generation module 2630 is used to generate musical accompaniment based on the composition information;

[0179] The lyrics generation module 2640 is used to generate target lyrics based on the selected target lyrics strategy and the lyrics of the song to be imitated;

[0180] The main melody generation module 2650 is used to generate the main melody of music based on the music accompaniment, the target lyrics, and the selected target sound source strategy.

[0181] The mixing module 2660 is used to mix the main melody and the accompaniment of the music to obtain the created target song.

[0182] In one alternative implementation, the mixing processing module 2660 is configured to:

[0183] The main melody of the music is divided into K main melody segments according to a preset time interval; and the accompaniment of the music is divided into K accompaniment segments according to the preset time interval; K is an integer greater than 1; the main melody segments and accompaniment segments in the same duration interval are mixed to obtain K audio segments; the K audio segments are spliced ​​together according to the start time and end time of the K audio segments to obtain the target song.

[0184] Furthermore, other specific details of the embodiments disclosed herein have been described in detail in the inventive embodiments of the methods described above, and will not be repeated here.

[0185] EXEMPLARY STORAGE MEDIUM

[0186] The storage medium of the exemplary embodiments of this disclosure will now be described.

[0187] In this exemplary embodiment, the above method can be implemented by a program product, such as a portable compact disc read-only memory (CD-ROM) containing program code, which can run on a device, such as a personal computer. However, the program product disclosed herein is not limited thereto. In this document, a readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0188] The program product may employ any combination of one or more readable media. A readable media may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0189] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0190] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RE, etc., or any suitable combination thereof.

[0191] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (FAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0192] EXEMPLARY ELECTRONIC DEVICE

[0193] refer to Figure 27 An electronic device according to an exemplary embodiment of the present disclosure will be described.

[0194] Figure 27 The electronic device 2700 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0195] like Figure 27 As shown, the electronic device 2700 is presented in the form of a general-purpose computing device. The components of the electronic device 2700 may include, but are not limited to: at least one processing unit 2710, at least one storage unit 2720, a bus 2730 connecting different system components (including storage unit 2720 and processing unit 2710), and a display unit 2740.

[0196] The storage unit stores program code, which can be executed by the processing unit 2710 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 2710 can perform actions such as... Figure 1 The methods and steps shown are as follows.

[0197] Storage unit 2720 may include volatile storage units, such as random access memory (RAM) unit 2721 and / or cache memory unit 2722, and may further include read-only memory unit (ROM) unit 2723.

[0198] Storage unit 2720 may also include a program / utility 2724 having a set (at least one) program module 2725, such program module 2725 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0199] Bus 2730 may include a data bus, an address bus, and a control bus.

[0200] Electronic device 2700 can also communicate with one or more external devices 2800 (e.g., keyboard, pointing device, Bluetooth device, etc.) via input / output (I / O) interface 2750. Electronic device 2700 also includes a display unit 2740 connected to input / output (I / O) interface 2750 for display purposes. Furthermore, electronic device 2700 can communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 2760. As shown, network adapter 2760 communicates with other modules of electronic device 2700 via bus 2730. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 2700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0201] It should be noted that although several modules or sub-modules of the apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0202] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0203] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for song composition, characterized in that, Applied to a user terminal, the method includes: In response to a trigger operation on the song creation control, a song recommendation interface is displayed; the song recommendation interface includes M songs to be imitated; M is an integer greater than 1; the song recommendation interface also includes multiple singer names and N songs to be imitated corresponding to each singer name; the multiple singer names are obtained by statistical analysis based on the singer information corresponding to the M songs to be imitated; where N is an integer greater than or equal to 1, and N is less than M; The multiple singer names are displayed in a first display order; the first display order is determined based on the similarity between the singers corresponding to the multiple singer names and the singers preferred by the user, and the singers preferred by the user are determined based on the user's profile characteristics and historical listening data; The N songs to be imitated are displayed in a second display order; the second display order is determined based on the similarity between the N songs to be imitated and user-preferred songs, which are determined based on the user's profile characteristics and historical creation characteristics. In response to selecting a song to be imitated from the song recommendation interface, a song strategy interface is displayed; the song strategy interface includes a variety of song strategies. In response to selecting a target song strategy from the song strategy interface, a lyrics strategy interface is displayed; the lyrics strategy interface is used to select or input lyrics strategies. In response to determining a target lyrics strategy from the lyrics strategy interface, a sound source strategy interface is displayed; the sound source strategy interface includes a variety of sound source strategies containing different timbres. In response to determining the target audio source strategy from the audio source strategy interface, the target song is displayed, wherein the target song is generated by the server based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy; The server generates the target song based on the following method: Feature extraction is performed on the song to be imitated to obtain the song features; the song features include spectral features, speech features, and rhythm features; Based on the song characteristics of the song to be imitated and the target song strategy, composition information is generated; Based on the composition information, a musical accompaniment is generated; Based on the target lyrics strategy and the lyrics of the song to be imitated, generate target lyrics; Generate the main melody of the music based on the musical accompaniment, the target lyrics, and the target sound source strategy; The main melody and the accompaniment of the music are mixed to obtain the original target song.

2. The method according to claim 1, characterized in that, The M songs to be imitated were determined based on the user's historical listening data; The user's historical music listening data includes multiple historically played songs and the playback parameters corresponding to each historically played song; The playback parameters include the number of playbacks and / or the playback duration.

3. The method according to claim 1, characterized in that, The method further includes: The names of the multiple singers are displayed according to a third display order, which is determined based on the alphabetical order of the first letters of the names of the multiple singers. The N songs to be imitated are displayed according to the fourth display order; the fourth display order is determined based on the ranking of the N songs to be imitated in the preset song list.

4. The method according to claim 1, characterized in that, After selecting a song to be imitated from the song recommendation interface and before displaying the song strategy interface, the method further includes: The song to be imitated is displayed as a preview control on the song recommendation interface; In response to receiving a trigger operation on the listening control, the song to be imitated or a specified segment of the song to be imitated is played.

5. The method according to claim 1, characterized in that, The lyrics strategy interface also includes a lyrics strategy input control; the method further includes: When the number of target lyric strategies selected from the lyric strategy interface meets the preset number condition, the lyric strategy input control is set to a disabled state.

6. The method according to claim 1, characterized in that, The lyrics strategy includes lyrics keywords; the method further includes: Obtain related keywords of the lyrics keywords, wherein the related keywords are generated based on the semantic analysis results of the lyrics keywords; The associated keywords are displayed in the lyrics strategy interface.

7. The method according to any one of claims 1 to 6, characterized in that, The target songs to be displayed include: Display the playback interface of the target song, which includes playback controls; In response to receiving a trigger operation on the playback control, the target song is played, and the lyrics of the target song are dynamically displayed on the playback interface.

8. The method according to claim 7, characterized in that, The step of dynamically displaying the lyrics of the target song on the playback interface includes: The lyrics keywords are displayed in a distinctive manner.

9. The method according to claim 7, characterized in that, The playback interface also includes a download control, which is used to download the target song and / or the creation information of the target song to a specified storage location; The creation information includes the accompaniment audio and MIDI sheet music file of the target song.

10. The method according to claim 7, characterized in that, The playback interface also includes a sharing control, which is used to share the target song to a preset application or to a preset contact.

11. The method according to claim 7, characterized in that, The target songs are multiple songs; the method further includes: Display the playback interface for each target song; In response to receiving a switching operation on the playback interface, the target song is switched.

12. The method according to claim 7, characterized in that, The playback interface also includes a song changing control, and the method further includes: In response to receiving a trigger operation on the song change control, a new target song is displayed; The new target song is a collection of songs regenerated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy.

13. A method for song composition, characterized in that, include: Feature extraction is performed on the selected song to be imitated to obtain the song features of the song to be imitated; The song features include spectral features, speech features, and rhythmic features; Based on the song characteristics of the song to be imitated and the selected target song strategy, composition information is generated; Based on the composition information, a musical accompaniment is generated; Based on the selected target lyrics strategy and the lyrics of the song to be imitated, target lyrics are generated; Based on the musical accompaniment, the target lyrics, and the selected target sound source strategy, generate the main melody of the music; The main melody and accompaniment of the music are mixed to obtain the original target song.

14. The method according to claim 13, characterized in that, The mixing process of the main melody and the accompaniment to obtain the target song includes: The main melody of the music is divided into K main melody segments according to a preset time interval; and the accompaniment of the music is divided into K accompaniment segments according to the preset time interval; where K is an integer greater than 1. Mix the main melody segment and the accompaniment segment that are in the same duration interval to obtain K audio segments; The K audio segments are spliced ​​together according to their start and end times to obtain the target song.

15. A song creation device, characterized in that, include: The song recommendation module is used to display the song recommendation interface in response to the trigger operation of the song creation control; The song recommendation interface includes M songs to be imitated; M is an integer greater than 1; the song recommendation interface also includes multiple singer names and N songs to be imitated for each singer name; the multiple singer names are obtained by statistical analysis based on the singer information corresponding to the M songs to be imitated; where N is an integer greater than or equal to 1, and N is less than M; The multiple singer names are displayed in a first display order; the first display order is determined based on the similarity between the singers corresponding to the multiple singer names and the singers preferred by the user, and the singers preferred by the user are determined based on the user's profile characteristics and historical listening data; The N songs to be imitated are displayed in a second display order; the second display order is determined based on the similarity between the N songs to be imitated and user-preferred songs, which are determined based on the user's profile characteristics and historical creation characteristics. The song strategy display module is used to display a song strategy interface in response to selecting a song to be imitated from the song recommendation interface; the song strategy interface includes a variety of song strategies. The lyrics strategy display module is used to display the lyrics strategy interface in response to selecting a target song strategy from the song strategy interface; the lyrics strategy interface is used to select or input lyrics strategy. The audio source display module is used to display the audio source strategy interface in response to determining the target lyrics strategy from the lyrics strategy interface; the audio source strategy interface includes a variety of audio source strategies containing different timbres. The song display module is used to display the target song in response to determining the target sound source strategy from the sound source strategy interface. The target song is generated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target sound source strategy. The feature extraction module is used to extract features from the song to be imitated, thereby obtaining the song features of the song to be imitated; the song features include spectral features, speech features, and rhythm features; The composition module is used to generate composition information based on the song characteristics of the song to be imitated and the target song strategy; The accompaniment generation module is used to generate musical accompaniment based on the composition information; The lyrics generation module is used to generate target lyrics based on the target lyrics strategy and the lyrics of the song to be imitated; The main melody generation module is used to generate the main melody of the music based on the musical accompaniment, the target lyrics, and the target sound source strategy. The mixing module is used to mix the main melody and the accompaniment of the music to obtain the created target song.

16. The apparatus according to claim 15, characterized in that, The M songs to be imitated were determined based on the user's historical listening data; The user's historical music listening data includes multiple historically played songs and the playback parameters corresponding to each historically played song; The playback parameters include the number of playbacks and / or the playback duration.

17. The apparatus according to claim 15, characterized in that, The song recommendation module is configured as follows: The names of the multiple singers are displayed according to a third display order, which is determined based on the alphabetical order of the first letters of the names of the multiple singers. Based on the fourth display order, the N songs to be imitated are displayed; The fourth display order is determined based on the ranking of the N songs to be imitated in the preset song list.

18. The apparatus according to claim 15, characterized in that, The song recommendation module is configured as follows: The song to be imitated is displayed as a preview control on the song recommendation interface; In response to receiving a trigger operation on the listening control, the song to be imitated or a specified segment of the song to be imitated is played.

19. The apparatus according to claim 15, characterized in that, The lyrics display strategy module is configured as follows: When the number of target lyric strategies selected from the lyric strategy interface meets the preset number condition, the lyric strategy input control is set to a disabled state.

20. The apparatus according to claim 15, characterized in that, The lyrics strategy includes lyrics keywords; the lyrics strategy display module is configured as follows: Obtain related keywords of the lyrics keywords, wherein the related keywords are generated based on the semantic analysis results of the lyrics keywords; The associated keywords are displayed in the lyrics strategy interface.

21. The apparatus according to any one of claims 15 to 20, characterized in that, The song display module is configured as follows: Display the playback interface of the target song, which includes playback controls; In response to receiving a trigger operation on the playback control, the target song is played, and the lyrics of the target song are dynamically displayed on the playback interface.

22. The apparatus according to claim 21, characterized in that, The song display module is configured as follows: The lyrics keywords are displayed in a distinctive manner.

23. The apparatus according to claim 21, characterized in that, The playback interface also includes a download control, which is used to download the target song and / or the creation information of the target song to a specified storage location; The creation information includes the accompaniment audio and MIDI sheet music file of the target song.

24. The apparatus according to claim 21, characterized in that, The playback interface also includes a sharing control, which is used to share the target song to a preset application or to a preset contact.

25. The apparatus according to claim 21, characterized in that, The target songs are multiple songs; the song display module is configured as follows: Display the playback interface for each target song; In response to receiving a switching operation on the playback interface, the target song is switched.

26. The apparatus according to claim 21, characterized in that, The playback interface also includes a song changing control, and the song display module is configured as follows: In response to receiving a trigger operation on the song change control, a new target song is displayed; The new target song is a collection of songs regenerated based on the song to be imitated, the target song strategy, the target lyrics strategy, and the target audio source strategy.

27. A song creation device, characterized in that, include: The feature extraction module is used to extract features from the selected song to be imitated, thereby obtaining the song features of the song to be imitated; the song features include spectral features, speech features, and rhythm features; The composition module is used to generate composition information based on the song characteristics of the song to be imitated and the selected target song strategy; The accompaniment generation module is used to generate musical accompaniment based on the composition information; The lyrics generation module is used to generate target lyrics based on the selected target lyrics strategy and the lyrics of the song to be imitated; The main melody generation module is used to generate the main melody of the music based on the musical accompaniment, the target lyrics, and the selected target sound source strategy. The mixing module is used to mix the main melody and the accompaniment of the music to obtain the created target song.

28. The apparatus according to claim 27, characterized in that, The mixing module is configured as follows: The main melody of the music is divided into K main melody segments according to a preset time interval; and the accompaniment of the music is divided into K accompaniment segments according to the preset time interval; where K is an integer greater than 1. Mix the main melody segment and the accompaniment segment that are in the same duration interval to obtain K audio segments; The K audio segments are spliced ​​together according to their start and end times to obtain the target song.

29. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 14.

30. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 14 by executing the executable instructions.

Images