Sound field generation method and device, equipment and medium

Abstract

The invention provides a sound field generation method and device, equipment and a medium, and the method comprises the steps: inputting scene description information into a large-scale language model, and obtaining the sound content information and sound position information of a scene corresponding to the scene description information outputted by the large-scale language model; and generating a scene sound field corresponding to the scene description information based on the sound content information and the sound position information. According to the method, the device, the equipment and the medium provided by the invention, the input scene description information is analyzed through the large language model, the corresponding sound content information and position information are generated, and high matching of the sound and the scene is ensured. Sound field generation is performed by combining the sound content information and the sound position information, and the propagation characteristics of the sound in the space are accurately reproduced. The method can reduce the dependence on complex hardware, and is suitable for various complex application scenes. Meanwhile, scene changes can be responded in real time, and a more vivid and dynamic sound environment is provided.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a sound field generation method, device, equipment and medium. Background Art

[0002] Sound field restoration technology simulates the propagation characteristics of sound in space to achieve the spatial positioning, sense of direction and environmental reflection effect of sound, so that users can feel realistic three-dimensional sound effects. This technology is widely used in virtual reality, augmented reality, immersive audio systems and other fields to provide users with an immersive auditory experience.

[0003] However, existing sound field restoration technologies mainly rely on multi-channel audio systems and physical acoustic models, which usually require a large amount of hardware equipment and complex computing resources. In addition, these technologies are difficult to handle changes in dynamic scenes in practical applications and cannot flexibly respond to diverse sound field requirements, limiting their application in complex environments. Summary of the invention

[0004] The present invention provides a sound field generation method, device, equipment and medium, which are used to solve the defects of high cost and limited application scope of sound field restoration hardware in related technologies.

[0005] The present invention provides a method for generating a sound field, comprising the following steps: Inputting the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; Based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0006] According to the sound field generation method provided by the present invention, the scene description information includes scene environment description information, and the scene environment description information is used to describe the environment where the scene is located.

[0007] According to the sound field generation method provided by the present invention, the scene description information also includes scene reference sound information, and the scene reference sound information is used to describe the content and / or position of the candidate sound in the scene.

[0008] According to the sound field generation method provided by the present invention, generating the scene sound field corresponding to the scene description information based on the sound content information and the sound position information includes: Acquire audio corresponding to the sound content information; Based on the audio and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0009] According to the sound field generation method provided by the present invention, the step of obtaining the audio corresponding to the sound content information includes: In a case where the sound content information includes human voice content, generating audio corresponding to the human voice content based on a speech synthesis model; And, in a case where the sound content information includes non-human voice content, audio corresponding to the non-human voice content is generated based on a sound effect generation model.

[0010] According to the sound field generation method provided by the present invention, generating the scene sound field corresponding to the scene description information based on the audio and the sound position information includes: Based on the sound position information, spatial sound restoration is performed on the audio to obtain a scene sound field corresponding to the scene description information.

[0011] The present invention also provides a sound field generating device, comprising the following modules: A scene parsing unit, used to input the scene description information into a large language model, and obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; A sound field generating unit is used to generate a scene sound field corresponding to the scene description information based on the sound content information and the sound position information.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-mentioned sound field generation methods is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the sound field generation method described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned sound field generation methods.

[0015] The sound field generation method, device, equipment and medium provided by the present invention parse the scene description information input by the user through a large language model, generate the corresponding sound content information and sound position information, and ensure the high matching between the sound and the scene. The sound field is generated by combining the sound content information and the sound position information, and the propagation characteristics of the sound in the space are accurately reproduced. The present invention can reduce the dependence on complex hardware and is applicable to various complex application scenarios. At the same time, the present invention can respond to scene changes in real time and provide a more realistic and dynamic sound environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a schematic flow chart of the sound field generating method provided by the present invention.

[0018] Figure 2 It is a structural schematic diagram of the sound field generating device provided by the present invention.

[0019] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Sound field restoration technology is an important technology used to reproduce the propagation characteristics of sound in a specific space. It provides a highly immersive auditory experience by simulating the spatial positioning, sense of direction, sense of distance, and environmental reflection and absorption effects of sound. This technology is widely used in virtual reality, augmented reality, immersive games, and high-fidelity audio systems. For example, in a virtual reality environment, sound field restoration technology enables users to accurately perceive the direction and distance of the sound source, thereby enhancing the sense of immersion; in a high-fidelity audio system, sound field restoration technology can accurately reproduce the sound effects of a music concert and provide a realistic audio experience.

[0022] Traditional sound field restoration methods usually rely on multi-channel audio systems and physical acoustic models. These systems require multiple speakers to be installed in the space and use complex algorithms to simulate the sound propagation path and environmental effects. Such methods not only have high requirements for hardware equipment and complex deployment, but also have great demand for computing resources, making them difficult to implement in real-time applications. In addition, these technologies are insufficient in dealing with dynamically changing scenes and cannot flexibly adapt to the user's changing perspective and position in the virtual space, thus limiting the application scenarios of sound field restoration.

[0023] In view of the above problems, an embodiment of the present invention provides a sound field generating method. Figure 1is a flow chart of the sound field generation method provided by the present invention, such as Figure 1 As shown, the method includes: Step 110: input the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model.

[0024] Specifically, scene description information refers to a specific scene described in natural language, including the environmental background of the scene, possible sound elements, and the dynamic characteristics of these sound elements, etc. The specific scene here refers to the scene where the sound field to be generated is located. In an embodiment of the present invention, in order to generate a sound field corresponding to the scene description information, the sound content information and sound position information of the scene corresponding to the scene description information can be first generated based on a large language model. That is, the scene description information can help the large model understand the overall atmosphere and sound layout of the scene, thereby generating more accurate sound information.

[0025] Here, Large Language Model (LLM) is referred to as large model, which refers to a natural language processing (NLP) model with a large parameter scale. The number of model parameters and / or the complexity of the model structure exceeds the preset threshold. The model processes a large amount of text data during training and has the ability to understand and generate natural language. For example, large language models can include Spark large models, etc.

[0026] Furthermore, the large language model here can be a large language model in a general field, or a large language model in the code field obtained by fine-tuning the sound field generation field data. For example, the large language model can be obtained by fine-tuning the pre-trained large language model by applying various sample scene description information and the sound content information and sound position information of the scene corresponding to the sample scene description information. The embodiment of the present invention does not make specific limitations on this.

[0027] The scene description information is input into the large language model, which can use its powerful natural language understanding and generation capabilities to parse the input scene description information. Through a deep understanding of the scene described by the scene description information, the large language model can predict the key sound elements that may be contained in the scene and generate the corresponding sound content information and sound location information.

[0028] Among them, the sound content information may include the types of sounds in the scene, such as wind, rain, human voices, footsteps, etc., which can be specifically reflected in sound elements, such as the type of bird sounds, the nature of human voices (such as whispering or shouting), the intensity and duration of wind sounds, etc. The sound location information describes the specific location of these sounds in space. The location here can be a static location or a dynamic movement path, such as the direction from which the sound comes, whether it is fixed or moving in the scene. For example, the input scene description may be "a quiet park, with birds singing in the distance, people talking in whispers nearby, and occasionally the rustling of leaves in the breeze." In this example, the model uses its language understanding function to identify sound elements such as "birds singing", "talking", and "wind", and outputs the sound content information and location information corresponding to these elements through the generation function, such as birds singing in the distance, whispering nearby, and wind sounds around, accurately distributing these sounds in the corresponding spatial positions.

[0029] Step 120: Generate a scene sound field corresponding to the scene description information based on the sound content information and the sound position information.

[0030] Specifically, the sound content information obtained based on step 110 includes the specific characteristics of each sound element in the scene, such as the type, frequency, pitch, loudness, etc. of the sound. These characteristics describe the physical properties of the sound and are the basic materials for generating the sound. The sound position information provides the distribution and dynamic changes of these sounds in space, such as the source direction of the sound, the distance from the audience, and the movement path of the sound in the scene. Combining these two types of information, a specific and perceptible three-dimensional sound field can be generated, that is, a scene sound field corresponding to the scene description can be generated.

[0031] The core of generating a sound field is to convert the sound elements contained in the sound content information into audio, and perform spatial processing on the audio of each sound element based on its sound position information. Through spatial processing, the propagation characteristics of the audio of the sound element in three-dimensional space can be accurately expressed, creating a realistic audio environment. In this process, spatial processing can ensure the accurate sense of direction and positioning of the sound, so that the audience can perceive the direction of the sound source. At the same time, spatial processing will also simulate the sense of distance of the sound, and by adjusting the loudness and frequency characteristics of the sound, the sound at a distance will sound more blurred and the sound at a close distance will be clearer. In addition, spatial processing will also simulate environmental reflections and reverberation effects. For example, in an empty space, the echo and delay of the sound will be accurately simulated to enhance the authenticity of the sound. In particular, spatial processing also involves the simulation of dynamic changes and movement of sound sources. When the sound source moves in the scene, the system will adjust the positioning, direction and intensity of the sound in real time to accurately express the dynamic changes of the sound. For example, a car drives from far to near and then drives away. Spatial processing allows the audience to feel the change of the sound of the car from far to near and then from near to far.

[0032] The sound field generation method provided by the embodiment of the present invention parses the scene description information input by the user through a large language model, generates the corresponding sound content information and sound position information, and ensures a high degree of matching between the sound and the scene. The sound field is generated by combining the sound content information and the sound position information to accurately reproduce the propagation characteristics of the sound in space. The present invention can reduce the dependence on complex hardware and is applicable to various complex application scenarios. At the same time, the present invention can respond to scene changes in real time and provide a more realistic and dynamic sound environment.

[0033] Based on the above embodiment, in step 110, the scene description information includes scene environment description information, and the scene environment description information is used to describe the environment in which the scene is located.

[0034] Specifically, the scene environment description information is used to describe in detail the environment in which the scene is located. It is a key component of the scene description information and provides a basis for generating a sound environment that matches it.

[0035] The scene environment description information covers all aspects of the scene, including the scene's geographical location, environment type, weather conditions, and time. For example, the scene environment description information can describe whether the scene is in a city street, a park, an indoor room, or a rural field. These details of the geographical location and environment type will directly affect the characteristics of the sound, such as the sound's reverberation, attenuation, and propagation effects in different materials and spaces.

[0036] In addition, weather conditions are also an important part of the scene environment description information, such as sunny days, rainy days, windy days, or snowstorms. These conditions affect the background sounds in the environment as well as the texture and intensity of the sounds. For example, on a rainy day, there may be continuous raindrop sounds in the environment, while the sound of wind will be more prominent in an open environment.

[0037] Time is also an important element in describing the scene environment, such as day, night, or dusk. Different times of day will affect the sound characteristics and atmosphere of the environment. For example, a night scene may have a quieter background sound, occasionally accompanied by a distant dog barking or wind, while a daytime city scene may be full of traffic noise and the hustle and bustle of people.

[0038] Through detailed scene environment description information, we can better understand and simulate the natural characteristics of sound in the scene, make the generated sound environment highly consistent with the actual situation of the scene, and enhance the user's immersion and sense of reality in applications such as virtual reality and augmented reality.

[0039] Based on the above embodiment, in step 110, the scene description information further includes scene reference sound information, and the scene reference sound information is used to describe the content and / or position of the candidate sound in the scene.

[0040] Specifically, scene-referenced sound information refers to specific information in the scene description information used to further refine the scene sound features, which is used to describe the content and / or location of candidate sounds in the scene. By providing scene-referenced sound information, large language models can more accurately understand which sound elements should appear in the scene and the specific locations or dynamics of these sounds in the scene.

[0041] Specifically, scene-referenced sound information may include descriptions of specific sounds, such as "there should be distant birds singing in the scene" or "there should be the sound of flowing water nearby." These descriptions clarify the content of the candidate sounds, allowing the system to generate sound materials that meet user expectations based on these prompts. In addition, scene-referenced sound information can also contain spatial positioning information of these sounds, such as "the birdsong comes from the tree in the left front" or "the sound of water flows from the right." These details help to accurately locate the source direction and distance of the sound when generating the sound field.

[0042] By combining scene reference sound information, the sound field generation process can more accurately reflect the user's intentions, not only meeting scene requirements in terms of sound content, but also achieving realistic positioning effects in terms of spatial layout. This refined information input improves the accuracy of the generated sound environment, making the final generated sound field more in line with the actual scene.

[0043] Based on the above embodiment, in step 120, generating the scene sound field corresponding to the scene description information based on the sound content information and the sound position information includes: Acquire audio corresponding to the sound content information; Based on the audio and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0044] Specifically, there are multiple methods for obtaining audio corresponding to the sound content information, depending on the requirements of the scene description information and the available resources.

[0045] For example, a pre-trained audio generation model can be used to generate audio, where the audio generation model can be a literary sound model, such as a speech synthesis model, or a sound effect synthesis model, which is not specifically limited in the embodiments of the present invention. The audio generation model can automatically generate audio corresponding to each sound content matching the scene based on the sound content information as input, and the audio generated can meet the needs of high customization and accurately reflect specific sound elements in the scene, such as ambient sound, human voice or natural sound.

[0046] In addition, audio materials corresponding to the sound content can also be retrieved from the audio database. The audio database usually contains a large number of high-quality pre-recorded or pre-generated sound samples, such as bird sounds, water sounds, and wind sounds in nature, as well as traffic background sounds and crowd sounds in urban environments. According to the sound content information, selecting the ready-made audio material that best meets the scene requirements can effectively improve the efficiency and quality of sound field generation.

[0047] In addition to the above two methods, you can also use professional recording equipment to directly record audio in the actual scene, or use audio synthesis software to generate sound materials with specific effects. The choice of these methods depends on the specific needs and application scenarios of the audio.

[0048] After obtaining the appropriate audio, the scene sound field corresponding to the scene description information can be generated based on the audio and sound position information. The sound position information here includes details such as the specific position, direction, distance, and dynamic characteristics of each sound in three-dimensional space. By combining this position information, the audio can be spatialized to accurately simulate the propagation characteristics of sound at different locations. For example, the effect of simulating sound coming from a distance or moving in space can enable the audience to feel the direction and distance of the sound.

[0049] Based on the above embodiment, the step of obtaining the audio corresponding to the sound content information includes: In a case where the sound content information includes human voice content, generating audio corresponding to the human voice content based on a speech synthesis model; And, in a case where the sound content information includes non-human voice content, audio corresponding to the non-human voice content is generated based on a sound effect generation model.

[0050] Specifically, the process of obtaining the audio corresponding to the sound content information can be achieved through a Wensheng sound model, and in this process different situations can be divided into different types of Wensheng sound models for processing, and the specific method depends on the sound type contained in the sound content information.

[0051] When the sound types are specifically divided into human voice and non-human voice, the corresponding literary sound models may be a speech synthesis model and a sound effect generation model, respectively.

[0052] When the sound content information contains human voice content, the corresponding human voice audio will be generated based on the speech synthesis model. Here, the speech synthesis model is a technology that can simulate and generate natural human voices, usually trained through deep learning and a large amount of voice data. It can generate human voices with different voice characteristics, such as voices of different genders, ages, emotional states, and languages. In this way, highly realistic human voice audio can be generated based on the human voice content specified in the scene description information, such as the speaker's tone, language, and speaking speed. The speech synthesis model can not only ensure the fluency of the generated human voice, but also be personalized according to the specific scene requirements, so that the human voice part is highly consistent with the overall atmosphere of the scene.

[0053] When the sound content information contains non-human voice content, such as ambient sound, natural sound effects or specific background sounds, the audio corresponding to these non-human voice contents is generated based on the sound effect generation model. The sound effect generation model can generate natural sounds (such as birdsong, wind, rain, etc.) or artificial environmental sound effects (such as traffic noise, mechanical operation sounds, etc.). Based on the sound effect generation model, various realistic sound effects can be generated according to the input sound description information to simulate different sound environments. For example, if the scene description information mentions "birdsong in the forest" or "the sound of flowing water in the distance", the sound effect generation model can generate these specific natural sound effects so that the generated audio matches the actual environmental sound field.

[0054] Based on the above embodiment, generating the scene sound field corresponding to the scene description information based on the audio and the sound position information includes: Based on the sound position information, spatial sound restoration is performed on the audio to obtain a scene sound field corresponding to the scene description information.

[0055] Here, the sound position information provides detailed information such as the specific position, direction, and distance of each audio in three-dimensional space. Sound position information is the basis for spatial sound restoration and determines the position of the sound in space and the propagation path.

[0056] Spatial sound restoration uses sound position information to simulate the propagation characteristics of sound in space, so that the generated sound field can accurately reflect the direction of the sound source, the sense of distance, and the reflection, refraction and attenuation characteristics of the sound in different environments.

[0057] Specific spatial sound restoration methods can be implemented using a variety of technologies. For example, the physical modeling method is a technology based on the principles of physical acoustics. It simulates the propagation path of sound in spaces of various materials and shapes, and calculates the reflection, refraction and absorption effects of sound. It is particularly suitable for high-precision sound field simulation, such as simulating the reverberation effect of sound in a cathedral or concert hall.

[0058] Software algorithms based on acoustic simulation are also a method of spatial sound restoration that can be considered. Acoustic simulation algorithms can use mathematical models and physical laws to simulate the propagation and changes of sound in different environments. For example, Finite Difference Time Domain (FDTD) and Ray Tracing techniques can simulate the propagation path of sound waves, calculate the reflection and attenuation of sound, and reproduce the sound characteristics in complex environments.

[0059] In addition, data-driven machine learning methods are also an effective means of spatial sound restoration. By training deep learning models, the propagation characteristics of sound in different environments can be learned and predicted. This method can handle complex acoustic conditions and diverse scene changes, and simulate the spatial characteristics of sound by generating audio effects that conform to real scenes. This method is particularly suitable for application scenarios that require real-time audio rendering and dynamic sound field generation, and can flexibly cope with complex sound sources and nonlinear acoustic environments.

[0060] Through these spatial sound restoration methods, combined with sound position information and audio generated based on sound content information, a scene sound field that is highly consistent with the scene description information can be generated. The generated sound field can not only accurately reproduce the spatial positioning and propagation characteristics of the sound, but also provide a realistic sense of direction and distance.

[0061] The sound field generating device provided by the present invention is described below. The sound field generating device described below and the sound field generating method described above can be referred to each other. Figure 2 Schematic diagram of the structure of the sound field generating device provided by the present invention. Figure 2 As shown, the device comprises: The scene parsing unit 210 is used to input the scene description information into the large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model.

[0062] The sound field generating unit 220 is configured to generate a scene sound field corresponding to the scene description information based on the sound content information and the sound position information.

[0063] The sound field generation device provided by the embodiment of the present invention parses the scene description information input by the user through a large language model, generates the corresponding sound content information and sound position information, and ensures a high degree of matching between the sound and the scene. The sound field is generated by combining the sound content information and the sound position information to accurately reproduce the propagation characteristics of the sound in space. The present invention can reduce the dependence on complex hardware and is applicable to various complex application scenarios. At the same time, the present invention can respond to scene changes in real time and provide a more realistic and dynamic sound environment.

[0064] Based on any of the above embodiments, in the scene parsing unit: The scene description information includes scene environment description information, and the scene environment description information is used to describe the environment where the scene is located.

[0065] The scene description information also includes scene reference sound information, where the scene reference sound information is used to describe the content and / or position of the candidate sound in the scene.

[0066] Based on any of the above embodiments, the sound field generating unit is specifically used for: Acquire audio corresponding to the sound content information; and generate a scene sound field corresponding to the scene description information based on the audio and the sound position information.

[0067] When the sound content information includes vocal content, audio corresponding to the vocal content is generated based on a speech synthesis model; and when the sound content information includes non-vocal content, audio corresponding to the non-vocal content is generated based on a sound effect generation model.

[0068] Based on the sound position information, spatial sound restoration is performed on the audio to obtain a scene sound field corresponding to the scene description information.

[0069] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the sound field generation method, which includes: Inputting the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; Based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0070] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0071] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the sound field generation method provided by the above methods, the method includes: Inputting the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; Based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0072] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the sound field generation method provided by the above methods is implemented, and the method includes: Inputting the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; Based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information is generated.

[0073] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0074] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a sound field, characterized in that: include: Inputting the scene description information into a large language model to obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; Based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information is generated.

2. The sound field generation method according to claim 1, characterized in that: The scene description information includes scene environment description information, and the scene environment description information is used to describe the environment where the scene is located.

3. The sound field generation method according to claim 2, characterized in that: The scene description information also includes scene reference sound information, where the scene reference sound information is used to describe the content and / or position of the candidate sound in the scene.

4. The sound field generation method according to any one of claims 1 to 3, characterized in that: The generating, based on the sound content information and the sound position information, a scene sound field corresponding to the scene description information comprises: Acquire audio corresponding to the sound content information; Based on the audio and the sound position information, a scene sound field corresponding to the scene description information is generated.

5. The sound field generation method according to claim 4, characterized in that: The obtaining of audio corresponding to the sound content information includes: In a case where the sound content information includes human voice content, generating audio corresponding to the human voice content based on a speech synthesis model; And, in a case where the sound content information includes non-human voice content, audio corresponding to the non-human voice content is generated based on a sound effect generation model.

6. The sound field generation method according to claim 4, characterized in that: The step of generating a scene sound field corresponding to the scene description information based on the audio and the sound position information includes: Based on the sound position information, spatial sound restoration is performed on the audio to obtain a scene sound field corresponding to the scene description information.

7. A sound field generating device, characterized in that: include: A scene parsing unit, used to input the scene description information into a large language model, and obtain the sound content information and sound position information of the scene corresponding to the scene description information output by the large language model; A sound field generating unit is used to generate a scene sound field corresponding to the scene description information based on the sound content information and the sound position information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the sound field generating method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the sound field generating method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the sound field generating method according to any one of claims 1 to 6 is implemented.

Images