Music generation method, music generation device and computer readable storage medium

Abstract

The invention relates to a music generation method, a music generation device and a computer readable medium, and relates to the technical field of computers. The music generation method comprises the following steps: receiving first prompt information input by a user, wherein the first prompt information comprises description information of music; according to the first prompt information, generating a first music work, the first music work including first music; a second music work is generated according to the adjustment operation of the user for the first music work, and the adjustment operation comprises at least one of the adjustment operation for the first prompt information and the adjustment operation for the first music.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a music generating method, a music generating device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Music generation technology is an important application in the field of computer technology. With the rapid development of artificial intelligence technology, natural language processing technology is widely used in music generation, using machine learning models to automatically generate music data based on text data.

[0003] However, due to the limitations of the performance of machine learning models and the accuracy of users' textual descriptions of music, automatically generated music often fails to meet user needs. Summary of the invention

[0004] In view of this, the embodiments of the present disclosure propose a music generation method, a music generation device, a computer-readable storage medium, and a computer program product. After automatically generating music according to a text description, the user can make targeted adjustments to the generated music and regenerate the music based on the user's adjustments, thereby improving the quality of music generation and enhancing the user experience.

[0005] According to a first aspect of some embodiments of the present disclosure, a music generation method is provided, comprising: receiving first prompt information input by a user, the first prompt information comprising description information of the music; generating a first musical work according to the first prompt information, the first musical work comprising first music; generating a second musical work according to an adjustment operation performed by the user on the first musical work, the adjustment operation comprising at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

[0006] According to a second aspect of some embodiments of the present disclosure, a music generating device is provided, comprising: a receiving module, configured to receive first prompt information input by a user, the first prompt information comprising description information of the music; a first generating module, configured to generate a first musical work according to the first prompt information, the first musical work comprising first music; a second generating module, configured to generate a second musical work using the machine learning model according to an adjustment operation of the user on the first musical work, the adjustment operation comprising at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

[0007] According to a third aspect of some embodiments of the present disclosure, there is provided a music generating device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the aforementioned music generating methods based on instructions stored in the memory.

[0008] According to a fourth aspect of some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, any one of the aforementioned music generation methods is implemented.

[0009] According to a fifth aspect of some embodiments of the present disclosure, a computer program product is provided, which, when executed on a computer, enables the computer to implement any one of the aforementioned music generation methods.

[0010] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0011] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The drawings described herein are used to provide a further understanding of the present disclosure. Each of the drawings together with the following detailed description is included in this specification and forms a part of the specification, and is used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation on the present disclosure. In the drawings:

[0013] Figure 1 A flowchart showing a music generation method according to some embodiments of the present disclosure;

[0014] Figure 2A An interactive interface for music generation according to some embodiments of the present disclosure is shown;

[0015] Figure 2B An interactive interface for music generation according to other embodiments of the present disclosure is shown;

[0016] Figure 2C An interactive interface for music generation according to some other embodiments of the present disclosure is shown;

[0017] Figure 2D An interactive interface for music generation according to some further embodiments of the present disclosure is shown;

[0018] Figure 3A An editing interface of a first music work according to some embodiments of the present disclosure is shown;

[0019] Figure 3B An editing interface of a first music work according to some other embodiments of the present disclosure is shown;

[0020] Figure 3C An editing interface of a first music work according to yet other embodiments of the present disclosure is shown;

[0021] Figure 3D An editing interface of a first music work according to some further embodiments of the present disclosure is shown;

[0022] Figure 4 A flowchart showing generation of a first musical composition according to some embodiments of the present disclosure is shown;

[0023] Figure 5A A flowchart showing generation of a second musical composition according to some embodiments of the present disclosure;

[0024] Figure 5B A flowchart showing generation of a second musical work according to other embodiments of the present disclosure;

[0025] Figure 6 An interactive interface for generating a second musical composition according to some embodiments of the present disclosure is shown;

[0026] Figure 7 A flowchart showing a music generation method according to other embodiments of the present disclosure;

[0027] Fig. 8A An interactive interface after generating a second musical work according to some embodiments of the present disclosure is shown;

[0028] Figure 8B An interactive interface after generating a second musical work according to other embodiments of the present disclosure is shown;

[0029] Fig. 9 A block diagram showing a music generating device according to some embodiments of the present disclosure;

[0030] Fig.10 A block diagram showing a music generating device according to some other embodiments of the present disclosure;

[0031] Fig.11 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0032] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure, but it is obvious that the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. The following description of the embodiments is actually only illustrative and is by no means intended to limit the present disclosure and its application or use. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein.

[0034] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be performed in different orders, and / or performed in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown in the execution. The scope of the present disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions and numerical values ​​of the parts and steps set forth in these embodiments should be interpreted as being merely exemplary and do not limit the scope of the present disclosure.

[0035] The term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". In addition, the term "include" and its variations used in the present disclosure mean an open term that includes at least the following elements / features but does not exclude other elements / features, that is, "including but not limited to". Therefore, include is synonymous with include. The term "based on" means "based at least in part on".

[0036] References throughout this specification to "one embodiment," "some embodiments," or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearances of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout this specification do not necessarily all refer to the same embodiment, but may do so.

[0037] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.

[0038] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0039] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0040] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.

[0041] In related music generation technologies, the automatically generated music often cannot meet the needs of users due to the performance of machine learning models and the accuracy of users' text descriptions of music. In order to improve the quality of music generation and enhance user experience, the disclosed embodiments provide a new music generation method. After music is automatically generated according to text descriptions, users can make targeted adjustments to the generated music, and regenerate music according to the user's adjustments.

[0042] Figure 1 A flowchart of a music generation method according to some embodiments of the present disclosure is shown.

[0043] like Figure 1 As shown, the music generation method includes: step S1, receiving first prompt information input by a user, the first prompt information including description information of the music; step S2, generating a first musical work according to the first prompt information, the first musical work including first music; step S3, generating a second musical work according to the user's adjustment operation on the first musical work, the adjustment operation including at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

[0044] The music generation method of this embodiment can be executed on the client side, or partially on the server side.

[0045] The themes of music include, for example, missing home, missing friends, celebrating success, etc. The images of music include, for example, sunset, waves, reefs, streets, buildings, etc. The emotional types of music include, for example, sadness, joy, helplessness, touching, etc. The styles of music include, for example, rock, jazz, pop, folk, rap, etc.

[0046] The first musical work may be a pure music work without lyrics, and only includes the first music, such as a piano piece, a guitar piece, or other pure music. The first musical work may also be a vocal music work, which includes not only the first music but also the human voice corresponding to the first music. Usually, a vocal music work also includes lyrics, and the human voice sings the content of the lyrics.

[0047] Reference below Figures 2A-2D , further describing the music generation method according to the embodiment of the present disclosure. Figures 2A-2D The interactive interfaces for music generation according to different embodiments of the present disclosure are respectively shown.

[0048] like Figure 2A As shown, in the interactive interface of music generation (also called "music creation"), an input box is provided, for example, the input box displays "Try to describe the mood or picture" to guide the user to enter the description information of the music. Figure 2A The interactive interface shown also shows some music works that have been generated. For these music works, the title and cover of the music can be displayed.

[0049] Figure 2B Another interactive interface for music creation is shown. Figure 2B An input box is also provided, which displays "Describe sound or picture" to guide the user to input descriptive information of the music. In response to the input box being activated, the user can use a keyboard or voice input device, for example, to input the descriptive information of the music in the input box in text or voice as prompt information for generating a musical work. The descriptive information of the music may include at least one of the theme of the music, the picture of the music, the emotional type of the music, and the style type of the music. If you want to generate vocal music using your own voice, you can select Figure 2B The "Use My Voice" feature shown.

[0050] Of course, in order to help users input more accurate prompt information more efficiently, some suggestions can be provided on the interactive interface to facilitate users to make choices.

[0051] In some embodiments, receiving the first prompt information input by the user in step S1 includes: providing at least one candidate prompt template in the interactive interface, each candidate prompt template corresponding to a complete music scene, and the information of each candidate prompt template including at least one of the theme of music, the picture of music, the emotional type of music, and the style type of music; using the prompt information in a candidate prompt template selected by the user as part or all of the first prompt information.

[0052] like Figure 2CAs shown, multiple candidate prompt templates are displayed in the interactive interface, such as candidate prompt templates A, B, C, D, E, etc., for the user to select. For example, the information of a candidate prompt template may include Kyoto on a rainy day, which reflects the picture of music. For another example, the information of another candidate prompt template may include embracing the sky happily like a bird, which reflects both the picture of music and the emotional type of music.

[0053] Since each candidate prompt template corresponds to a complete music scene, the user can only select one candidate prompt template. The prompt information in a candidate prompt template selected by the user can be directly applied to the input box as the first prompt information. Figure 2C As shown, the user selects the candidate prompt template "Embrace the sky as happily as a bird", and the corresponding prompt information is directly applied to the input box.

[0054] Of course, the user can further adjust the prompt information based on the prompt information of the candidate prompt template, for example, using Figure 2C The keyboard or voice input device shown at the bottom modifies the prompt information by deleting, adding, etc. In this case, the prompt information in a candidate prompt template selected by the user is only a part of the first prompt information.

[0055] In other embodiments, receiving first prompt information input by a user includes: providing at least one candidate prompt information on an interactive interface, each candidate prompt information including at least one of the theme of the music, the picture of the music, the emotional type of the music, and the style type of the music; and using one or more candidate prompt information selected by the user as part or all of the first prompt information.

[0056] like Figure 2D As shown, multiple candidate prompt information is displayed on the interactive interface for the user to select. For example, the candidate prompt information may include prompt information reflecting the theme, picture, emotion type, and style type of music, such as missing, rainy day, Kyoto, birds, cheerful, and rock.

[0057] The user can select multiple candidate prompt information and combine them. The candidate prompt information selected by the user can be directly applied to the input box as the first prompt information. Figure 2D As shown in the figure, the user can select multiple candidate prompt information "bird", "happy". Of course, the user can also further adjust the prompt information in the input box, for example, using Figure 2D The keyboard or voice input device shown at the bottom modifies the prompt information "birds, happy" to "birds happily embrace the sky with their wings." For example, in this case, the multiple candidate prompt information selected by the user is only a part of the first prompt information.

[0058] Combined with the above Figures 2A-2DDescribes how to receive the first prompt information input by the user in step S1. Figures 3A-3D Next, it is described how to generate the first music piece according to the first prompt information in step S2.

[0059] In step S2, generating a first musical work according to the first prompt information includes: using a machine learning model to generate the first music according to the first prompt information.

[0060] Machine learning models include, for example, large language models (LLM) or other natural language processing (NLP) models. For example, machine learning models such as variational autoencoders (VAE), generative adversarial networks (GAN), and transformers can be used to achieve diversified and high-quality music generation.

[0061] Figure 3A The editing interface of the first music piece according to some embodiments of the present disclosure is shown. After generating the first music piece, directly enter the Figure 3A The interactive interface shown for editing the first music is the editing interface of the first music work.

[0062] like Figure 3A As shown, the editing interface of the first music piece includes a control for generating lyrics. In response to the user triggering the control for generating lyrics, first lyrics corresponding to the first music piece are generated. In some embodiments, the machine learning model is used to generate the first lyrics according to the first prompt information and the first music piece. Figure 3A As shown, the generated lyrics content is displayed in the text box at the bottom of the editing interface.

[0063] Of course, the first lyrics may be generated not according to the first prompt information used to generate the first music, but according to other prompt information different from the first prompt information. In other embodiments, other prompt information input by the user is received, and the first lyrics are generated according to the other prompt information using the machine learning model, and the other prompt information includes description information of the first lyrics. Of course, the lyrics may also be generated by comprehensively considering the first music and the prompt information input by the user for generating lyrics, so that the generated lyrics better match the music. That is, the first lyrics are generated according to the other prompt information and the first music using the machine learning model.

[0064] In response to the user triggering again Figure 3AGenerate lyrics controls in the , enter the lyrics editing interface, such as Figure 3B shown. Figure 3B An editing interface of a first musical work according to some other embodiments of the present disclosure is shown.

[0065] Figure 3B The previously generated lyrics are displayed in . The user can edit the previously generated lyrics through the keyboard or voice input device.

[0066] Of course, if the user wants to use lyrics that are completely different from the previous generated lyrics, they can also directly trigger the clear control and enter Figure 3C The editing interface shown. Figure 3C An editing interface of a first musical composition according to yet other embodiments of the present disclosure is shown.

[0067] exist Figure 3C In the example, the user can re-enter prompt information for generating lyrics through a keyboard or voice input device, such as other prompt information different from the first prompt information described above. In response to the user triggering the control for generating lyrics, a machine learning model is used to generate first lyrics matching the first music according to the other prompt information.

[0068] For vocal music, there also needs to be a corresponding human voice, including the singer’s voice. Figure 3A-3C As shown, the editing interface of the first music also includes a control for adding vocals, such as a control with vocals. In response to the user triggering the control with vocals on the editing interface of the first music, the vocals corresponding to the first music are generated. For example, the voice of the singer is generated based on the first music and the first lyrics. Of course, in the case where the vocal music does not include lyrics, the voice of the singer can also be generated based only on the first music.

[0069] For the singer's voice, the user can use a default human voice whose timbre matches the music and its lyrics. In some embodiments, the singer's voice is generated based on the first music and the first lyrics using a machine learning model. There can be multiple singer's voices generated using a machine learning model. The user can select the singer's voice according to actual needs.

[0070] For the voice of the singer, the user can also use his own voice. In other embodiments, the voice of the singer is generated based on the voice of the user using voice imitation technology. Of course, if the client or server has stored the voice of the user, it can also be directly called based on the authorization of the user.

[0071] Figure 3D FIG. 4 shows an editing interface of a first music work according to some further embodiments of the present disclosure. Figure 3DAs shown, in the editing interface of the first music work, a variety of sounds are displayed for users to choose from. Figure 3D The voice of A shown is, for example, the voice of a poet, the voice of B is, for example, the voice of an actor, the voice of C is, for example, the voice of a character in a movie or TV series, and the default voice is, for example, the voice of a singer.

[0072] The user can use a default voice, which can be set based on the user's past selections. Of course, the user can also select other voices according to actual needs. For example, the user can choose his own voice or the voice of another singer according to his preferences.

[0073] Combine the following Figure 4 The description of how to generate a first musical composition with vocals continues. Figure 4 A flowchart of generating a first musical composition according to some embodiments of the present disclosure is shown.

[0074] The first musical work with vocals includes the first music and the voice of the singer, and may include or exclude the first lyrics. The generation of the vocal music including the first lyrics is described in detail below.

[0075] like Figure 4 As shown, generating the first musical work according to the first prompt information includes: step S21, using the machine learning model to generate the first music according to the first prompt information; step S22, receiving other prompt information input by the user, the other prompt information including description information of the first lyrics; step S23, using the machine learning model to generate the first lyrics according to the other prompt information; step S24, generating the singer's voice according to the first music and the first lyrics; step S25, synthesizing the first musical work according to the first music, the first lyrics, and the singer's voice.

[0076] In step S22, the other prompt information may be the same as the first prompt information, that is, the first music and the first lyrics are generated based on the same prompt information. Of course, the other prompt information may also be different from the first prompt information. The user may delete, add, or modify the first prompt information to obtain other prompt information. The user may also not make adjustments based on the first prompt information, but input other prompt information from the perspective of lyrics alone.

[0077] In step S24, when it is desired to generate the first work with the first lyrics, the matching of the sound with the music and the lyrics is comprehensively considered and the appropriate vocal is selected. Of course, if there is no first lyric, the vocal can also be selected by only considering the matching of the sound with the music.

[0078] In step S25, the first music, the first lyrics, and the singer's voice are synchronized according to the basic properties of the music to synthesize the first music work. Of course, the title and cover of the first music can be further synthesized with the first music, the first lyrics, and the singer's voice to generate a more complete first music work.

[0079] How to generate the first music in step S21, how to receive the prompt information input by the user in step S22, how to generate the first lyrics in step S23, and how to generate the singer's voice in step S24 have been described before and will not be repeated here.

[0080] Front combination Figure 2A-Figure 3D The method of generating the first music, the first lyrics, and the first vocals to obtain the first music work is described in detail. However, the first music generated once is often difficult to meet the quality requirements of the user for the music work, so the user may need to adjust the generation of the music in a targeted manner. Figure 5A-5B , Figure 6 Next, it is described how to generate the second music piece according to the user's adjustment to the first music piece in step S3.

[0081] Figure 5A A flow chart of generating a second musical work according to some embodiments of the present disclosure is shown. Figure 5A As shown, generating the second music work according to the user's adjustment operation on the first music work includes: step S31, displaying the first prompt information on the interactive interface; step S32, receiving the user's modification operation on the first prompt information; step S33, displaying the second prompt information obtained based on the modification operation; step S34, using the machine learning model to generate the second music work according to the second prompt information.

[0082] In step S31, the prompt information input box can be reactivated to display the previously input prompt information, that is, the first prompt information, in the input box. Figure 3A The pen-shaped edit control shown is triggered, and you can enter something like Figure 2B , 2C The interactive interface shown.

[0083] In addition to displaying the first prompt information previously used to generate the first music, further prompt information can be recommended based on the generated first music, that is, some suggestions are given to help the user adjust the first music work.

[0084] In some embodiments, at least one recommendation prompt information based on the first music work is displayed in the interactive interface, and the recommendation prompt information includes at least one of the theme of the music, the picture of the music, the emotional type of the music, and the style type of the music.

[0085] Figure 3A Some recommended tips are displayed, such as pop, jazz, rap, rock, folk, etc. Figure 3A A style control is also shown. In response to the user triggering the control, more music style types can be provided for the user to choose from. Figure 3A It also displays recommended prompt information related to the emotional type of music, such as sadness, touching, helplessness, joy, etc.

[0086] For example, after the first music has been generated based on the first prompt information such as "birds happily embrace the sky with their wings", if the user needs to modify the prompt information, some prompt information can be recommended based on the picture "birds embrace the sky with their wings" in the first music, the emotional type of the music "joyful", etc., such as prompt information about the theme "celebrate success", "celebrate graduation", prompt information about the style type "popular", "folk", etc. The user can select one or more recommended prompt information, and the one or more recommended prompt information selected by the user can be used as part of the second prompt information.

[0087] In step S32 and step S33, the user can modify the first prompt information to obtain the second prompt information. For example, if the first prompt information includes that the style type of the music is popular, the user can modify it to folk song to obtain the second prompt information. For another example, if the first prompt information includes that the emotional type of the music is sad, the user can modify it to helpless to obtain the second prompt information. Similarly, the user can modify the theme, picture, etc. of the music in the first prompt information to obtain the second prompt information.

[0088] Of course, the user can also delete part of the descriptive information of the music from the first prompt information, or add the descriptive information of the music to the first prompt information to obtain the second prompt information. For example, the first prompt information includes the theme of the music as celebrating success, the picture of the music as architecture, and the emotion of the music as cheerfulness. The user can delete the descriptive information of the picture of the music, and the obtained second prompt information includes less descriptive information of the music, reducing the restrictions on the picture of the generated music. Of course, in this case, the user can also add descriptive information for the style type of the music, for example, if the style type of the music is popular, the obtained second prompt information includes more descriptive information of the music, improving the matching degree between the generated music and the user's needs.

[0089] In step S34, a second music piece that better meets the user's needs is generated by using a machine learning model based on the second prompt information obtained by adjusting the first prompt information. Figure 3A The control for regenerating shown is triggered, and the music piece can be regenerated. Similar to the first music piece, the second music piece also includes the title and cover of the second music.

[0090] It should be understood that the user's adjustment operation on the first music piece may be an adjustment operation on the first prompt information, an adjustment operation on the first music, or both. The adjustment operation on the first music may include adjustment of basic attributes of the music.

[0091] In some embodiments, generating the second musical work according to the user's adjustment operation on the first musical work includes: generating the second musical work according to the user's adjustment operation on basic attributes of the first music, the basic attributes including rhythm, melody, timbre, and harmony of the music.

[0092] If the user is not satisfied with the rhythm of the generated first music, the rhythm of the first music can be adjusted separately. The rhythm of music generally includes the beat, speed, accent and style of the music. The user can adjust at least one of the beat, speed, accent and style of the first music to adjust the rhythm of the first music.

[0093] Figure 3A The editing interface shown shows the speed control. In response to the user triggering the speed control, the Figure 6 The speed editing interface is shown. Figure 6 An interactive interface for generating a second musical work according to some embodiments of the present disclosure is shown. Figure 6 As shown, the user can move the speed adjustment control to adjust the speed of the music.

[0094] Similarly, the user can also adjust the melody, timbre, harmony, etc. of the first music based on his or her understanding and preference of music to obtain a second music work that better meets his or her needs.

[0095] The adjustment operation on the basic attribute of the first music can be performed on the first music as a whole. Since the music can be divided into sections, the first music can also be adjusted in sections.

[0096] For example, the first music includes multiple paragraphs. Generating the second music work according to the user's adjustment operation on the basic attributes of the first music includes: generating the second music work according to the user's adjustment operation on the basic attributes of at least one paragraph among the multiple paragraphs of the first music.

[0097] Only the basic properties of a part of the first music passages may be adjusted, for example, only the rhythm of the music passage corresponding to the prelude of the first music passage may be adjusted without adjusting other parts of the first music passages.

[0098] The rhythm adjustment of the first music can be further refined. For example, each section of the music has multiple beats, and the user is supported to adjust the rhythm of the first music by beats, which can more efficiently generate music works that match user needs.

[0099] For example, each of multiple paragraphs of a first piece of music includes multiple beats, the rhythm of the first piece of music includes the beats of the music, and generating a second piece of music based on the user's adjustment operation on the basic attributes of the first piece of music includes: displaying the soundtrack of the first piece of music; generating the second piece of music based on the user's adjustment operation on the first piece of music based on the soundtrack, and the adjustment operation on the first piece of music includes adjusting at least one of the duration of the beat and adjusting the combination rule between the beats.

[0100] A track may correspond to a part of music. Each track may correspond to the performance of a musical instrument. The first music may include multiple tracks, and the display of the tracks of the first music may support user adjustments based on the tracks, that is, the second music work may be generated based on the user's adjustment operation on at least one of the multiple tracks of the first music.

[0101] For example, among the multiple tracks of the first music, the first track corresponds to the performance of the drums, so that the whole music has a rhythmic backbone, the second track corresponds to the rhythm of the bass, coordinated with the performance of the drums, the third track corresponds to the performance of the guitar in accordance with the beat, and the fourth track corresponds to the singing of the human voice in accordance with the music. The user can adjust not all tracks, but only some tracks. The user can adjust only the performance of the guitar in the third track. Specifically, the duration of each beat in the third track (i.e., the note time value) can be adjusted, and the combination rule of the strong beat and the weak beat in the third track can also be adjusted. Of course, both can be adjusted.

[0102] Combination of the above Figure 5A and Figure 6 The invention describes how to generate a second musical work according to the user's adjustment to the first musical work. It has been described in detail in combination with different embodiments that the user's adjustment to the first musical work includes both overall adjustment, such as adjustment to the first prompt information used to generate the musical work, and local adjustment, such as adjustment to basic attributes such as the rhythm and melody of the generated music. Figure 5B Other embodiments of generating a second musical composition based on a user's adjustments to a first musical composition are further described.

[0103] Figure 5BA flowchart of generating a second musical work according to some other embodiments of the present disclosure is shown. Figure 5B As shown, generating the second music work according to the user's adjustment operation on the first music work includes: step S31', generating the second music according to the user's adjustment operation on the first music work; step S32', adjusting the first lyrics according to at least one of the melody, rhythm, and style type of the second music to obtain second lyrics; step S33', synthesizing the second music work according to the second music and the second lyrics.

[0104] The first musical work includes first music and first lyrics. Since there is a certain degree of independence between music and lyrics in a musical work, the first music and the first lyrics can be adjusted respectively, so as to efficiently generate a second musical work that better meets the needs of the user.

[0105] First, in step S31', the machine learning model can be used to generate the second music according to the user's adjustment to the first music. As mentioned above, the adjustment to the first music can be an adjustment to the prompt information used to generate the first music, or an adjustment to the basic attributes of the first music.

[0106] Then, in step S32', the first lyrics can be adjusted according to the basic attributes of the second music, such as melody, rhythm, etc., to obtain the second lyrics. For example, the rhythm of the second music is faster than that of the first music, and the first lyrics corresponding to the first music may not be applicable to the second music, so the first lyrics can be adjusted to obtain the second lyrics that match the rhythm of the second music. The first lyrics can also be adjusted according to the style type of the second music to obtain the second lyrics. For example, the style type of the first music is rock and the style type of the second music is pop, and the first lyrics corresponding to the first music are usually not applicable to the second music, so the first lyrics can be adjusted to obtain the second lyrics that match the style type of the second music.

[0107] Of course, in order to adapt to the adjustment of the music and lyrics, the human voice is also adjusted accordingly. That is, the voice of the singer is generated according to the second music and the second lyrics.

[0108] Finally, in step S33', the second music and the second lyrics are synthesized into a second music work. Of course, in the case of vocals, the singer's voice also needs to be synthesized as a part of the second music work. The title and cover of the second music work can also be synthesized together as a part of the second music work.

[0109] Combined with the above Figure 1-Figure 6 A number of embodiments of the music generation method are described in detail. Figure 7 A specific application example of the music generation method is described. Figure 7A flowchart of a music generating method according to some other embodiments of the present disclosure is shown.

[0110] like Figure 7 As shown, the music generation method includes: step S1', receiving first prompt information input by a user; step S2', generating first music according to the first prompt information, and generating first lyrics, a first title, and a first cover corresponding to the first music to synthesize a first musical work; step S3', generating second music according to the user's adjustment to the first music, and generating second lyrics, a second vocal, a second title, and a second cover corresponding to the second music to synthesize a second musical work.

[0111] In step S1' and Figure 1 At least one prompt information suggestion may be provided in the interactive interface for the user to select as part or all of the first prompt information.

[0112] The prompt information suggestion can be a candidate prompt template, such as Figure 2B As shown, the user can only choose one. For example, the user can select the candidate prompt template "Kyoto on a rainy day", and the prompt information included in the prompt template can be directly applied to the input box of the prompt information. The user can directly use these prompt information as the first prompt information for generating the first music. Of course, the user can also adjust the prompt information on this basis, such as adding descriptive information about the emotional type of the music "sadness", to obtain the first prompt information with more music description information.

[0113] Hint suggestions can also be candidate hints, such as Figure 2C As shown, the user can select multiple candidate prompt information and combine them. For example, the user can select multiple candidate prompt information "birds" and "cheerful". Similarly, these prompt information can be directly applied to the input box of the prompt information. The user can directly use these prompt information as the first prompt information for generating the first music. Of course, the user can also adjust the prompt information on this basis, such as adding descriptive information about the picture of the music "wings" and "sky" to obtain the first prompt information with more music description information.

[0114] Next, in step S2', the first music is generated according to the first prompt information using the machine learning model. The first lyrics corresponding to the first music can also be generated according to the first prompt information using the machine learning model. Of course, considering the relative independence of music and lyrics, the first lyrics can also be generated according to other prompt information different from the first prompt information. Considering the display requirements of the musical work, the first title and the first cover corresponding to the first music can also be generated. Then, the first music, the first lyrics, the first title, and the first cover are combined into the first musical work.

[0115] Since it is usually difficult for the music generated once to directly match the user's requirements for music, considering the subsequent adjustments, in step S2', only the first music may be generated first without generating the first lyrics, the first title, the first cover, or the corresponding vocals, and the corresponding lyrics, vocals, title, and cover may be generated after the generated music meets the user's requirements.

[0116] Next, in step S3', the second music is generated according to the user's adjustment to the first music using the machine learning model. The adjustment to the first music can be an adjustment to the first prompt information used to generate the first music, or an adjustment to the basic attributes of the first music.

[0117] Regarding the adjustment of the prompt information, the input box of the prompt information can be reactivated, and the previously entered prompt information can be displayed in the input box, so that the user can edit the prompt information on this basis. In addition, at least one recommended prompt information based on the first music can be displayed in the interactive interface to help users adjust the first music more reasonably. For example, the first music is generated based on the first prompt information "The birds happily embrace the sky with their wings." Prompt information such as the emotional type of music "cheerful" and the theme type of music "Celebrating graduation" can be recommended in the interactive interface. In this way, based on the first prompt information and the recommended prompt information, the user can more efficiently input the second prompt information for generating the second music.

[0118] Regarding the adjustment of the basic attributes of the music, the basic attributes of the music can be displayed so that the user can adjust the basic attributes of the first music as a whole. Figure 6 As shown, the user can adjust the speed of the first music by moving the speed adjustment control. Of course, the music can also be divided into multiple sections, supporting the user to adjust the basic attributes of the first music in sections.

[0119] Regarding the adjustment of the basic attributes of the music, the music tracks can also be displayed, so that the user can adjust the basic attributes of the first music track by track. The adjustment of each track can be combined with the beat. For example, the duration of each beat in a certain track can be adjusted, and the combination rule of the strong beat and the weak beat in the track can also be adjusted.

[0120] After generating the second music matching the user's needs, second lyrics corresponding to the second music may be further generated.

[0121] Similar to the generation of the first lyrics, the second lyrics can be generated according to the second prompt information used to generate the second music; the second lyrics can also be generated according to other prompt information different from the second prompt information. Of course, the first lyrics can also be adjusted based on the first lyrics according to at least one of the melody, rhythm, and style type of the second music to obtain the second lyrics. This is particularly applicable when only the basic attributes of the first music are adjusted.

[0122] After the second music and the second lyrics have matched the user's needs, for vocal music, a human voice matching the second music and the second lyrics, that is, the singer's voice, must be generated. Similarly, the user can use his or her own voice as the singer's voice. For example, using voice imitation technology, a second human voice matching the second music and the second lyrics is generated. Of course, a machine learning model can also be used to generate one or more human voices matching the second music and the second lyrics for the user to choose. In order to display the needs, a second title and a second cover corresponding to the second music can also be generated.

[0123] Finally, the second music, the second lyrics, the second vocals, the second title, and the second cover are combined into a second music work, which can be published, shared, and so on as a user's creation. Figure 3A On the interactive interface shown, the save and publish controls are directly triggered. You can also publish, share, and perform other operations on the interactive interface of the returned music work.

[0124] Fig. 8A , 8B The interactive interface after the second music piece is generated according to the embodiment of the present disclosure is shown. Fig. 8A As shown, the generated second music piece is displayed on the interactive interface, including the title and cover of the music. For example, the title of the music is displayed as "Sunset and Waves". The cover of the music can be displayed as a picture of the sunset on the sea. Fig. 8A The input box of the interactive interface also displays the prompt information for generating the second music piece: "In the afterglow of the sunset, the waves beat against the rocks." Users can publish the generated second music piece, for example, to trigger Fig. 8A The publishing control shown. Triggered by different triggering methods Fig. 8A The publishing controls in the can also be used to share, view descriptions, or delete the generated music works, as shown in Figure 8.

[0125] The above is the music generation method provided by the embodiment of the present disclosure. Figure 9-11 A music generating device according to an embodiment of the present disclosure is described, which is used to execute any embodiment of the above-mentioned music generating method.

[0126] Fig. 9A block diagram of a music generating device according to some embodiments of the present disclosure is shown.

[0127] like Fig. 9 As shown, the music generating device 9 includes: a receiving module 91, configured to receive first prompt information input by a user, wherein the first prompt information includes description information of the music; a first generating module 92, configured to generate a first musical work according to the first prompt information, wherein the first musical work includes first music; a second generating module 93, configured to generate a second musical work according to the user's adjustment operation on the first musical work and using the machine learning model, wherein the adjustment operation includes at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

[0128] The receiving module 91 of the music generating device 9 can be used to execute Figure 1 Step S1 or Figure 7 Step S1'. The first generation module 92 of the music generation device 9 can be used to perform Figure 1 Step S2 or Figure 7 Step S2'. The second generation module 93 of the music generation device 9 can be used to perform Figure 1 Step S3 or Figure 7 Step S3'.

[0129] Fig.10 A block diagram of a music generating device according to some other embodiments of the present disclosure is shown.

[0130] like Fig.10 As shown, the music generating device 10 includes: a memory 101; and a processor 102 coupled to the memory 101, and the processor 102 is configured to execute the music generating method described in any of the aforementioned embodiments based on the instructions stored in the memory 101.

[0131] The memory 101 is used to store one or more computer-readable instructions. The memory 101 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), flash memory. The memory 101 may store, for example, an operating system, an application, a boot loader (BootLoader), a database, and other programs, and may also store various applications and various data.

[0132] The processor 102 is used to run computer-readable instructions to implement the music generation method described in any of the above embodiments. The specific implementation of each step of the music generation method can be found in the above embodiments, and the repeated parts are not repeated here.

[0133] The processor 102 may be configured to execute Figure 1 Step S1-Step S3 or Figure 7 The processor 102 may be embodied as various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc.

[0134] The processor 102 and the memory 101 may communicate with each other directly or indirectly. For example, the processor 102 and the memory 101 may communicate with each other via a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 102 and the memory 101 may also communicate with each other via a system bus, which is not limited in the present disclosure.

[0135] It should be noted that Fig.10 The components of the music generating device 10 shown are only exemplary and non-limiting. The music generating device 10 may also have other components according to actual application requirements. The processor 102 may control other components in the music generating device 10 to perform desired functions.

[0136] The music generating device can be implemented by software, firmware and / or hardware, and can be integrated into an electronic device installed with relevant application programs.

[0137] Fig.11 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0138] Fig.11 The electronic device 11 shown may be a computer system with a dedicated hardware structure, which can execute corresponding functions when a relevant application program is installed.

[0139] Electronic devices include, but are not limited to, mobile terminals such as smart phones, laptops, personal digital assistants (PDA), tablet computers (Tablet Personal Computer, Tablet PC), PMP (portable multimedia player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., as well as fixed terminals such as digital televisions, desktop computers, etc.

[0140] like Fig.11 As shown, a central processing unit (CPU) 111 performs various processes according to a program stored in a read-only memory (ROM) 112 or a program loaded from a storage section 118 to a random access memory (RAM) 113. In RAM 113, data required when CPU 111 performs various processes is stored as needed. The central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above. ROM 112, RAM 113, and storage section 118 may be various forms of computer-readable storage media. It should be noted that although Fig.11 ROM 112, RAM 113 and storage section 118 are shown separately in FIG. 1 , but one or more of them may be combined or located in the same or different memory or storage modules.

[0141] The CPU 111, the ROM 112, and the RAM 113 are connected to each other via a bus 114. To the bus 114, an input / output interface 115 is also connected.

[0142] The following components are connected to the input / output interface 115: an input portion 116, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output portion 117, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage portion 118, including a hard disk, a magnetic tape, etc.; and a communication portion 119, including a network interface card such as a LAN card, a modem, etc. The communication portion 119 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Fig.11 The various devices or modules in the electronic device 11 are shown to communicate via the bus 114, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0143] A drive 1110 is also connected to the input / output interface 115 as needed. A removable medium 1111 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 118 as needed.

[0144] When the series of processing described above is implemented by software, the program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 1111 .

[0145] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which, when running on a computer, enables the computer to implement the music generation method described in any of the aforementioned embodiments. The computer program product includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 119, or installed from the storage part 118, or installed from the ROM 112. When the computer program is executed by the CPU 111, the music generation method of the embodiment of the present disclosure is executed.

[0146] It should be noted that, in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, apparatus, or device or for use in conjunction with an instruction execution system, apparatus, or device.

[0147] The computer readable medium may be a computer readable storage medium, or a computer readable signal medium, or any combination of the two.

[0148] Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. A computer program is stored on a computer-readable storage medium, and when the program is executed by a processor, the method for generating music described in any of the foregoing embodiments is implemented.

[0149] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer readable program codes. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0150] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0151] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute the music generation method of any of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0152] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations involving a remote computer, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0153] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The functions described above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0155] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A music generation method, comprising: Receiving first prompt information input by a user, wherein the first prompt information includes description information of the music; Generate a first musical work according to the first prompt information, wherein the first musical work includes first music; A second musical work is generated according to an adjustment operation performed by the user on the first musical work, wherein the adjustment operation includes at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

2. The music generation method according to claim 1, wherein: Generating a second musical work according to the user's adjustment operation on the first musical work includes: Displaying the first prompt information on the interactive interface; receiving a modification operation of the user on the first prompt information; Displaying second prompt information obtained based on the modification operation; The second musical work is generated according to the second prompt information by using a machine learning model.

3. The music generation method according to claim 2, wherein: Generating a second musical work according to the user's adjustment operation on the first musical work includes: Displaying, on the interactive interface, at least one piece of recommendation prompt information based on the first music work, the recommendation prompt information including at least one of a theme of the music, a picture of the music, an emotional type of the music, and a style type of the music; The one or more pieces of recommendation prompt information selected by the user are used as part of the second prompt information.

4. The music generation method according to claim 1, wherein: Generating a second musical work according to the user's adjustment operation on the first musical work includes: The second music piece is generated according to the user's adjustment operation on basic attributes of the first music, where the basic attributes include rhythm, melody, timbre, and harmony of the music.

5. The music generation method according to claim 4, wherein: The first music includes a plurality of sections, and generating a second music work according to the user's adjustment operation on the basic attributes of the first music includes: The second music piece is generated according to the user's adjustment operation on the basic attributes of at least one of the multiple sections of the first music piece.

6. The music generating method according to claim 4, wherein: Generating a second music work according to the user's adjustment operation on the basic attribute of the first music work includes: Displaying the audio track of the first music, where the first music includes multiple audio tracks; The second music piece is generated according to the user's adjustment operation on at least one of the multiple tracks of the first music.

7. The music generating method according to claim 5, wherein: Each of the multiple paragraphs includes multiple beats, the rhythm of the first music includes the beat of the music, and generating the second music work according to the user's adjustment operation on the basic attribute of the first music includes: displaying the audio track of the first music; The second music piece is generated according to the user's adjustment operation on the first music based on the audio track, and the adjustment operation on the first music includes at least one of adjusting the duration of the beat and adjusting the combination rule between the beats.

8. The music generating method according to claim 1, wherein: The first musical work also includes first lyrics. Generating the first musical work according to the first prompt information includes: Using a machine learning model, generating the first music according to the first prompt information; The first lyrics are generated according to the first prompt information and the first music by using the machine learning model.

9. The music generating method according to claim 1, wherein: The first musical work is vocal music, including first lyrics and the voice of a singer. Generating the first musical work according to the first prompt information includes: Using the machine learning model, generating the first music according to the first prompt information; receiving third prompt information input by a user, wherein the third prompt information includes description information of the first lyrics; Using the machine learning model, and according to the third prompt information, generating the first lyrics; Generating the singer's voice according to the first music and the first lyrics; The first musical work is synthesized according to the first music, the first lyrics, and the singer's voice.

10. The music generating method according to claim 9, wherein: Using the machine learning model and according to the third prompt information, generating lyrics for the first music includes: The first lyrics are generated according to the third prompt information and the first music by using the machine learning model.

11. The music generating method according to claim 9, wherein: Generating the singer's voice according to the first music and the first lyrics includes: Generate the singer's voice based on the user's voice using voice imitation technology; or The machine learning model is used to generate the singer's voice based on the first music and the first lyrics.

12. The music generating method according to any one of claims 8 to 11, wherein: Generating a second musical work according to the user's adjustment operation on the first musical work includes: generating the second music according to the adjustment operation of the user on the first music piece; According to at least one of the melody, rhythm, and style of the second music, adjusting the first lyrics to obtain second lyrics; The second musical work is synthesized according to the second music and the second lyrics.

13. The music generating method according to any one of claims 12, wherein: The second musical work includes second music and second lyrics, the second music includes multiple paragraphs, each paragraph includes multiple beats, and the first lyrics are adjusted according to at least one of the rhythm and style of the second music to obtain the second lyrics including: The first lyrics are adjusted according to at least one of the time and stress of each paragraph and each beat of the second music to obtain the second lyrics.

14. The music generating method according to claim 1, wherein: The first prompt information received from the user includes: Providing at least one candidate prompt template in the interactive interface, each candidate prompt template corresponds to a complete music scene, and information of each candidate prompt template includes at least one of the theme of music, the picture of music, the emotional type of music, and the style type of music; The prompt information in a candidate prompt template selected by the user is used as part or all of the first prompt information.

15. The music generating method according to claim 1, wherein: The first prompt information received from the user includes: Providing at least one candidate prompt information on the interactive interface, each candidate prompt information including at least one of the theme of the music, the picture of the music, the emotional type of the music, and the style type of the music; The one or more pieces of candidate prompt information selected by the user are used as part or all of the first prompt information.

16. The music generating method according to any one of claims 1 to 11, wherein: The first musical work includes the title and cover of the first music; The second musical work includes the title and cover of the second music; The description information of the music includes at least one of the theme of the music, the picture of the music, the emotional type of the music, and the style type of the music.

17. A music generating device, comprising: A receiving module is configured to receive first prompt information input by a user, wherein the first prompt information includes description information of the music; A first generating module is configured to generate a first music work according to the first prompt information, wherein the first music work includes a first music; The second generation module is configured to generate a second musical work using the machine learning model according to the user's adjustment operation on the first musical work, wherein the adjustment operation includes at least one of an adjustment operation on the first prompt information and an adjustment operation on the first music.

18. A music generating device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the music generating method according to any one of claims 1 to 16 based on instructions stored in the memory.

19. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the music generating method according to any one of claims 1 to 16.

20. A computer program product, when the computer program product is run on a computer, enables the computer to implement the music generation method according to any one of claims 1 to 16.

Images