An interactive, compiler-based music generation method and apparatus

Abstract

The application discloses an interactive compilation-based music generation method and device, wherein the method comprises the following steps: obtaining a music description language text and a music style description text; performing music configuration classification processing on the music style description text by using a pre-trained configuration classification model to obtain a configuration text; performing adaptation processing on the music description language text according to the configuration text to obtain a to-be-compiled text; and performing music compilation generation processing on the to-be-compiled text to obtain a compilable music file. The embodiment of the application can create music without learning music theory knowledge and can be widely applied to the field of artificial intelligence technology.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to an interactive, compilation-based music generation method and apparatus. Background Technology

[0002] Currently, most music creation applications are based on simulating real-world instruments, such as piano simulators and guitar simulators. These applications often require users to have both music theory knowledge and some instrument playing experience, primarily serving musicians with already good instrument playing skills. For ordinary music enthusiasts lacking music theory knowledge and instrument playing experience, these simulation-based music creation applications often cannot help them create satisfactory works. The music generation methods in related technologies are mainly done manually by people; for example, hip-hop music can be composed by professional hip-hop artists. However, people without musical backgrounds simply do not possess the ability to create music. In summary, the technical problems existing in these technologies urgently need to be solved. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide an interactive, compilation-based music generation method and apparatus, enabling music creation without the need for knowledge of music theory.

[0004] On one hand, the present invention provides an interactive, compilation-based music generation method, comprising:

[0005] Retrieve music description language text and music style description text;

[0006] The music style description text is classified into music configurations using a pre-trained configuration classification model to obtain the configuration text.

[0007] The music description language text is adapted based on the configuration text to obtain the text to be compiled.

[0008] The text to be compiled is processed to generate music, resulting in a compilable music file.

[0009] Optionally, the step of performing music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text includes:

[0010] The configuration classification model includes a text encoder, a music generator, and an audio discriminator;

[0011] The text encoder is used to preprocess the music style description text to obtain the text latent vector;

[0012] The text latent vector is processed by the music generator to generate music fragments.

[0013] The music segment is processed by the audio discriminator to obtain the configuration text.

[0014] Optionally, before performing music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text, the configuration classification model is trained, including:

[0015] Obtain the training text;

[0016] The training text is input into the initialized configuration classification model to obtain the classification result;

[0017] The weights of the music generator in the configuration classification model are frozen, and the text encoder in the configuration classification model is optimized based on the classification results to obtain the trained configuration classification model.

[0018] Optionally, the step of adapting the music description language text according to the configuration text to obtain the text to be compiled includes:

[0019] The configuration text is analyzed to obtain the text configuration items;

[0020] The music description language text is updated according to the text configuration items to obtain the text to be compiled.

[0021] Optionally, the step of performing music compilation and generation processing on the text to be compiled to obtain a compilable music file includes:

[0022] Lexical analysis is performed on the text to be compiled to obtain a set of symbol sequences;

[0023] The set of symbol sequences is subjected to syntactic analysis, and semantic actions corresponding to the syntactic descriptions obtained from the analysis are executed to obtain compilable music text.

[0024] Optionally, the lexical analysis of the text to be compiled to obtain a set of symbol sequences includes:

[0025] Lexical analysis is performed on the text to be compiled. The lexical analyzer identifies the symbols in the text to be compiled, and a set of symbol sequences is obtained. The set of symbol sequences includes at least punctuation marks, reserved words, phonetic names, integers, and identifiers.

[0026] Optionally, the step of performing syntactic analysis on the set of symbol sequences and executing semantic actions corresponding to the analyzed syntactic description to obtain compilable music text includes:

[0027] The global configuration items are obtained by parsing the header of the symbol sequence set using a parser.

[0028] Initialize the music digital interface track according to the global configuration item;

[0029] The remaining part of the symbol sequence set is reduced by the parser to obtain musical measures.

[0030] The musical measure is processed by note event timing calculation to obtain the music digital interface event;

[0031] Add the music digital interface event to the music digital interface track to obtain compilable music text.

[0032] On the other hand, embodiments of the present invention also provide an interactive, compilation-based music generation device, comprising:

[0033] The first module is used to obtain music description language text and music style description text;

[0034] The second module is used to perform music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text;

[0035] The third module is used to adapt the music description language text according to the configuration text to obtain the text to be compiled;

[0036] The fourth module is used to perform music compilation and generation processing on the text to be compiled, so as to obtain a compilable music file.

[0037] On the other hand, embodiments of the present invention also disclose an electronic device, including a processor and a memory;

[0038] The memory is used to store programs;

[0039] The processor executes the program to implement the method described above.

[0040] On the other hand, embodiments of the present invention also disclose a computer-readable storage medium storing a program that is executed by a processor to implement the methods described above.

[0041] On the other hand, embodiments of the present invention also disclose a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0042] Compared with existing technologies, the present invention, employing the above technical solution, has the following technical effects: The embodiments of the present invention acquire music description language text and music style description text; perform music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text; adapt the music description language text according to the configuration text to obtain text to be compiled; and perform music compilation generation processing on the text to be compiled to obtain a compilable music file. The embodiments of the present invention enable users to create music without needing to learn music theory. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of an interactive, compilation-based music generation method provided in an embodiment of this application;

[0045] Figure 2 This is a syntax definition diagram of a music description language provided in an embodiment of this application;

[0046] Figure 3 This is an example diagram of a compilable music description language text provided in an embodiment of this application;

[0047] Figure 4 This is a neural network model framework diagram of a configuration classification model provided in an embodiment of this application. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] First, let's analyze some of the terms used in this application:

[0050] Musical Instrument Digital Interface (MIDI): The most widely used music standard format in the music production industry, often referred to as "computer-understandable sheet music." It uses digital control signals for musical notes to record music. A complete MIDI music file is only a few tens of kilobytes in size but can contain dozens of music tracks. Almost all modern music is produced and synthesized using MIDI and sound libraries.

[0051] Long Short-Term Memory (LSTM) recurrent neural network: This is a special type of recurrent neural network. Unlike general feedforward neural networks, LSTM can analyze inputs using time series data.

[0052] Extended Backus Normal Form (EBNF) is a metasyntax notation that expresses context-free grammars as a regular way of describing computer programming languages ​​and formal languages. It is an extension of the basic Backus Normal Form (BNF) metasyntax notation.

[0053] To provide more convenient tools for music creation and to popularize artistic creation and appreciation in people's daily lives, computer-aided composition technology has begun to develop in recent years. It can effectively help people create various musical works, thereby enriching their cultural lives, and has many creative applications in the entertainment and multimedia fields. However, there is currently a lack of technology that can directly generate music from natural language descriptions. For users lacking music theory knowledge, they hope to use this convenient technology to control the music creation process and generate the music they desire.

[0054] In view of this, refer to Figure 1 This invention provides an interactive, compilation-based music generation method, comprising:

[0055] S101. Obtain the music description language text and music style description text;

[0056] S102. The music style description text is classified using a pre-trained configuration classification model to obtain the configuration text.

[0057] S103. Adapt the music description language text according to the configuration text to obtain the text to be compiled;

[0058] S104. Perform music compilation and generation processing on the text to be compiled to obtain a compilable music file.

[0059] In this embodiment of the invention, for users lacking music theory and programming knowledge, an existing music description language text is selected, and then a music style description text in natural language representing the expected music style is provided. A configuration classification model is used to analyze and determine the corresponding configuration audio and a set of configuration values. Finally, the configuration portion of the selected music description language text is rewritten to obtain a new compilable music text. (Refer to...) Figure 2 , Figure 2A diagram showing the EBNF syntax definition of the music description language that the compiler provided in this embodiment of the invention can compile. (Refer to...) Figure 3 , Figure 3 Given a music representation language text conforming to the above syntax, the compiler can compile and generate a playable MIDI file from such text. It is conceivable that, in this embodiment of the invention, the user can also write their own music description language text according to the syntax, and then perform music compilation processing on the music description language text to obtain a compilable music file.

[0060] As a further preferred embodiment, the step of performing music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text includes:

[0061] The configuration classification model includes a text encoder, a music generator, and an audio discriminator;

[0062] The text encoder is used to preprocess the music style description text to obtain the text latent vector;

[0063] The text latent vector is processed by the music generator to generate music fragments.

[0064] The music segment is processed by the audio discriminator to obtain the configuration text.

[0065] In this embodiment of the invention, the configuration classification model includes a text encoder, a music generator, and an audio discriminator. The text encoder can be trained using a bidirectional LSTM model. This text encoder is used to preprocess the music style description text to generate latent text vectors. These latent text vectors are then input into a pre-trained linear Transformer-based music generation model to obtain music segments. The audio discriminator then parses the music segments and retrieves the configuration corresponding to the audio classification result from a predefined configuration table to obtain the configuration text. Figure 4 As shown, Figure 4 This is a neural network model framework diagram of a configuration classification model provided in an embodiment of this application.

[0066] Further, as a preferred embodiment, before performing music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain the configuration text, the configuration classification model is trained, including:

[0067] Obtain the training text;

[0068] The training text is input into the initialized configuration classification model to obtain the classification result;

[0069] The weights of the music generator in the configuration classification model are frozen, and the text encoder in the configuration classification model is optimized based on the classification results to obtain the trained configuration classification model.

[0070] In this embodiment of the invention, music style description text for training is obtained, and the training text is input into a configuration classification model that initializes network parameters to obtain configuration classification results. Then, the weights of the pre-trained linear Transformer-based music generator in the configuration classification model are frozen, and only the bidirectional LSTM-based text encoder is fine-tuned. The text encoder is optimized using the Adam optimizer so that the model output reaches a state that best matches the preset configuration. The learning rate of the Adam optimizer is set to 0.0002; the number of training iterations is 10000, and the model training process is completed on 8 Tesla V100 GPUs.

[0071] As a further preferred embodiment, the step of adapting the music description language text according to the configuration text to obtain the text to be compiled includes:

[0072] The configuration text is analyzed to obtain the text configuration items;

[0073] The music description language text is updated according to the text configuration items to obtain the text to be compiled.

[0074] In this embodiment of the invention, the configuration text is analyzed to obtain text configuration items such as the beat per minute (BPM), instruments, volume, current scale, playing intensity, and rhythm of the music. The corresponding configuration of the music description language text is modified according to the text configuration items to obtain the text to be compiled.

[0075] As a further preferred embodiment, the step of performing music compilation and generation processing on the text to be compiled to obtain a compilable music file includes:

[0076] Lexical analysis is performed on the text to be compiled to obtain a set of symbol sequences;

[0077] The set of symbol sequences is subjected to syntactic analysis, and semantic actions corresponding to the syntactic descriptions obtained from the analysis are executed to obtain compilable music text.

[0078] In this embodiment of the invention, a lexical analyzer performs lexical analysis on the text to be compiled, completing bottom-up syntax analysis of the text to obtain a set of symbol sequences. The lexical analyzer in this embodiment of the invention is an LALR parser implemented based on JavaCUP. This embodiment of the invention provides a parser that progressively reduces the obtained symbol sequences from terminal symbols to start symbols according to the syntax, and executes semantic actions corresponding to the syntax description during the analysis process, finally generating a MIDI file when the start symbols are reduced.

[0079] As a further preferred embodiment, the lexical analysis of the text to be compiled to obtain a set of symbol sequences includes:

[0080] Lexical analysis is performed on the text to be compiled. The lexical analyzer identifies the symbols in the text to be compiled, and a set of symbol sequences is obtained. The set of symbol sequences includes at least punctuation marks, reserved words, phonetic names, integers, and identifiers.

[0081] In this embodiment of the invention, a lexical analyzer performs lexical analysis on the text to be compiled, identifying symbols in the text and obtaining a set of symbol sequences. Specifically, the lexical analyzer identifies whitespace characters and end-of-line comments in the text to be compiled, but does not return symbols to the syntax analyzer; the lexical analyzer identifies punctuation marks, reserved words, and phonetic names, returning the corresponding symbols to the syntax analyzer; the lexical analyzer identifies integers, and if the identified integer has more than 12 digits, an error is reported and the program terminates; otherwise, the corresponding symbol is returned to the syntax analyzer; the lexical analyzer identifies identifiers, and if the identified identifier is longer than 24 characters, an error is reported and the program terminates; otherwise, the corresponding symbol is returned to the syntax analyzer.

[0082] As a further preferred embodiment, the step of performing syntactic analysis on the symbol sequence set and executing semantic actions corresponding to the analyzed syntactic description to obtain compilable music text includes:

[0083] The global configuration items are obtained by parsing the header of the symbol sequence set using a parser.

[0084] Initialize the music digital interface track according to the global configuration item;

[0085] The remaining part of the symbol sequence set is reduced by the parser to obtain musical measures.

[0086] The musical measure is processed by note event timing calculation to obtain the music digital interface event;

[0087] Add the music digital interface event to the music digital interface track to obtain compilable music text.

[0088] In this embodiment of the invention, the parser analyzes the symbol stream output by the lexical analyzer, i.e., the set of symbol sequences, from front to back. It parses out the global configuration items at the beginning of the symbol stream. According to the grammar definition, the global configuration items mainly include the tempo (BPM), instrument (INSTRUMENT), and volume (VELOCITY). After parsing out the global configuration values, the parser initializes a MIDI track (i.e., creates a new empty track without MIDI events, only configuring its overall tempo, instrument timbre, and volume as the parsed result). The parser continues to parse the symbol stream, progressively reducing symbols to note events from the bottom up according to the grammar, and then reducing note events to measures. After reducing the measures, the parser calculates the duration of each note event in the measure, generates a note start event and a note end event, and adds these MI DI events to the MI DI track. After reducing all measures, the parser reduces all measures to start symbols, marking the end of the parsing process. At this point, the semantic implementation program is called to write the MI DI track temporarily stored in the parser into the MI DI file, ending the compilation process.

[0089] On the other hand, embodiments of the present invention also provide an interactive, compilation-based music generation device, comprising:

[0090] The first module is used to obtain music description language text and music style description text;

[0091] The second module is used to perform music configuration classification processing on the music style description text using a pre-trained configuration classification model to obtain configuration text;

[0092] The third module is used to adapt the music description language text according to the configuration text to obtain the text to be compiled;

[0093] The fourth module is used to perform music compilation and generation processing on the text to be compiled, so as to obtain a compilable music file.

[0094] and Figure 1 Corresponding to the method described above, this embodiment of the invention also provides an electronic device, including a processor and a memory; the memory is used to store a program; the processor executes the program to implement the method described above.

[0095] and Figure 1 Corresponding to the method described above, embodiments of the present invention also provide a computer-readable storage medium storing a program that is executed by a processor to implement the method described above.

[0096] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 1 The method shown.

[0097] In summary, this invention provides an interactive, compilation-based music generation method that allows ordinary music enthusiasts to programmatically generate MIDI music after understanding simple syntax. For users with no music theory knowledge who cannot correctly use the syntax, they can directly guide the compiler to generate custom-style music based on existing language text through natural language descriptions. Compared to other music creation applications based on analog instruments, this method does not require users to have instrument experience or even music theory knowledge. This method completely transforms the music creation process into a programming process, describing music in a form combining sheet music and computer programs, possessing a high degree of abstraction and therefore greater potential for development and application.

[0098] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0099] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0100] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0102] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0103] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0104] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0105] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0106] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. An interactive, compilation-based music generation method, characterized by, The method comprises: obtaining music description language text and music style description text; performing music configuration classification processing on the music style description text by using a pre-trained configuration classification model to obtain configuration text; performing adaptation processing on the music description language text according to the configuration text to obtain to-be-compiled text; performing music compilation generation processing on the to-be-compiled text to obtain a compilable music file; the music configuration classification processing on the music style description text by using the pre-trained configuration classification model to obtain the configuration text comprises: the configuration classification model comprises a text encoder, a music generator, and an audio discriminator; performing preprocessing on the music style description text by using the text encoder to obtain a text hidden vector; performing music generation processing on the text hidden vector by using the music generator to obtain a music segment; performing audio discrimination processing on the music segment by using the audio discriminator to obtain the configuration text; the music compilation generation processing on the to-be-compiled text to obtain the compilable music file comprises: performing lexical analysis processing on the to-be-compiled text to obtain a symbol sequence set; performing syntax analysis processing on the symbol sequence set and executing a semantic action corresponding to an analyzed syntax description to obtain a compilable music text.

2. The method of claim 1, wherein, Before the music configuration classification processing on the music style description text by using the pre-trained configuration classification model to obtain the configuration text, the configuration classification model is trained, comprising: obtaining training text; inputting the training text into an initialized configuration classification model to obtain a classification result; freezing the weight of the music generator in the configuration classification model, and optimizing the text encoder in the configuration classification model according to the classification result to obtain a trained configuration classification model.

3. The method of claim 1, wherein, the adaptation processing on the music description language text according to the configuration text to obtain the to-be-compiled text comprises: performing configuration analysis processing on the configuration text to obtain a text configuration item; performing update processing on the music description language text according to the text configuration item to obtain the to-be-compiled text.

4. The method of claim 1, wherein, the lexical analysis processing on the to-be-compiled text to obtain the symbol sequence set comprises: performing lexical analysis processing on the to-be-compiled text to identify symbols of the to-be-compiled text by using a lexical analyzer to obtain a symbol sequence set, the symbol sequence set at least comprising punctuation marks, reserved words, note names, integers, and identifiers.

5. The method of claim 1, wherein, the syntax analysis processing on the symbol sequence set and the execution of a semantic action corresponding to an analyzed syntax description to obtain the compilable music text comprises: performing configuration parsing processing on a head part of the symbol sequence set by using a syntax analyzer to obtain a global configuration item; initializing a music digital interface audio track according to the global configuration item; performing reduction processing on a remaining part of the symbol sequence set by using the syntax analyzer to obtain a music measure; performing note event time calculation processing on the music measure to obtain a music digital interface event; adding the music digital interface event to the music digital interface audio track to obtain the compilable music text.

6. An interactive, compilation-based music generation apparatus, characterized by comprising: The device comprises: A first module for obtaining music description language text and music style description text; A second module for performing music configuration classification processing on the music style description text through a pre-trained configuration classification model to obtain configuration text; A third module for performing adaptation processing on the music description language text according to the configuration text to obtain to-be-compiled text; A fourth module for performing music compilation generation processing on the to-be-compiled text to obtain a compilable music file; The second module is configured to perform music configuration classification processing on the music style description text through a pre-trained configuration classification model to obtain configuration text, and the configuration classification model comprises a text encoder, a music generator, and an audio discriminator. The text encoder is configured to perform preprocessing on the music style description text to obtain a text hidden vector. The music generator is configured to perform music generation processing on the text hidden vector to obtain a music segment. The audio discriminator is configured to perform audio discrimination processing on the music segment to obtain configuration text. The fourth module is configured to perform music compilation generation processing on the to-be-compiled text to obtain a compilable music file, and the fourth module comprises: A lexical analysis module configured to perform lexical analysis processing on the to-be-compiled text to obtain a symbol sequence set. A syntax analysis module configured to perform syntax analysis processing on the symbol sequence set and execute semantic actions corresponding to the analyzed syntax description to obtain a compilable music text. The electronic device comprises a memory and a processor; 7. An electronic device, comprising: The memory is configured to store a program; The processor is configured to execute the program to implement the method of any one of claims 1 to 5. The computer program, when executed by a processor, implements the method of any one of claims 1 to 5.

8. A computer readable storage medium, the storage medium having stored thereon a computer program, characterized in that, ​

Images