A control method of a vehicle audio system and related products

Abstract

The application provides a control method of a vehicle sound system and related products, and the method comprises the following steps: inputting second information into a trained sound effect analysis model to obtain first sound effect parameters corresponding to a first sound source; the second information is determined based on first information; the first information at least comprises audio characteristics, singing characteristics, music style characteristics and arrangement characteristics of the first sound source; determining second sound effect parameters corresponding to the first sound source according to sound source sound field information of the vehicle and sound information of the sound system of the vehicle; determining target sound effect parameters corresponding to the first sound source according to the first sound effect parameters and the second sound effect parameters; and adjusting sound effect parameters of the sound system to the target sound effect parameters in the case of playing the first sound source. The application comprehensively considers the characteristics of the sound source itself, the influence of the sound source sound field information of the vehicle and the sound information of the vehicle sound system on the sound quality, and can improve the sound quality of the vehicle sound system and the auditory experience of the driver and passengers.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, specifically to a control method for a vehicle audio system and related products. Background Technology

[0002] During driving, most users tend to use the vehicle's audio system to play audio sources to enhance their driving experience, and the sound quality of the vehicle's audio system has a significant impact on the user's driving experience.

[0003] However, most current methods improve the sound quality of vehicle audio systems by having users manually adjust the sound effect parameters or select preset sound effect parameters. But most users lack the professional skills required to adjust sound effect parameters, so the current methods cannot effectively improve the sound quality of in-vehicle audio systems.

[0004] Improving the sound quality of vehicle audio systems and the auditory experience of drivers and passengers has become an urgent problem to be solved. Summary of the Invention

[0005] The main objective of this application is to propose a control method and related products for a vehicle audio system, aiming to improve the sound quality of the vehicle audio system and the auditory experience of drivers and passengers.

[0006] This application provides a control method for a vehicle audio system, comprising: inputting second information into a trained sound effect analysis model to obtain first sound effect parameters corresponding to a first sound source; determining the second information based on the first information; the first information including at least the audio characteristics, vocal characteristics, musical style characteristics, and orchestration characteristics of the first sound source; determining second sound effect parameters corresponding to the first sound source based on the sound source sound field information of the vehicle and the sound information of the vehicle's audio system; the sound source sound field information including the sound source sound field height and sound source sound field position; the sound information including the sound type and layout, and the sound power distribution parameters; determining target sound effect parameters corresponding to the first sound source based on the first sound effect parameters and the second sound effect parameters; and adjusting the sound effect parameters of the audio system to the target sound effect parameters when playing the first sound source.

[0007] In one embodiment, before determining the second sound effect parameter corresponding to the first sound source based on the sound source sound field information of the vehicle and the sound information of the vehicle's audio system, the control method further includes: determining the sound source sound field position based on the distribution position of the driver and passengers; determining the sound source sound field height based on the ear height of the driver and passengers; and determining the audio power distribution parameter based on the link relationship between the power amplifier channel of the audio system and each speaker in the audio system, the number of power amplifier channels, the sound source sound field position, and the sound source sound field height.

[0008] In one embodiment, the first sound effect parameter includes at least one type of sound effect parameter and a first value for each type of sound effect parameter; the second sound effect parameter includes positioning accuracy and a second value for the positioning accuracy; the target sound effect parameter includes the at least one type of sound effect parameter and a target value for each type of sound effect parameter; determining the target sound effect parameter corresponding to the first sound source based on the first sound effect parameter and the second sound effect parameter includes: for each type of sound effect parameter in the first sound effect parameter, determining the target value of the sound effect parameter based on the relationship between the sound effect parameter and the positioning accuracy, and the first value of the sound effect parameter and / or the second value of the positioning accuracy.

[0009] In one embodiment, determining the target value of the sound effect parameter based on the relationship between the sound effect parameter and the positioning accuracy, and a first value of the sound effect parameter and / or a second value of the positioning accuracy, includes: when the sound effect parameter is equal to the positioning accuracy, determining the second value of the positioning accuracy as the target value of the sound effect parameter; when the sound effect parameter is related to the positioning accuracy, determining the target value of the sound effect parameter based on the first value of the sound effect parameter and the second value of the positioning accuracy; when the sound effect parameter is unrelated to the positioning accuracy, determining the first value of the sound effect parameter as the target value of the sound effect parameter.

[0010] In one embodiment, before inputting the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source, the control method further includes: acquiring a training dataset, wherein the training dataset includes multiple training samples, each training sample including a third piece of information and playback sound effect parameters corresponding to the second sound source; the third information is determined based on the fourth information; the fourth information includes at least the audio features, singing features, music style features, and orchestration features of the second sound source; for each training sample, the following steps are performed respectively: inputting the training sample into the sound effect analysis model to obtain the predicted sound effect parameters of the vehicle audio system; determining the loss function value of the sound effect analysis model according to the predicted sound effect parameters and the playback sound effect parameters; if the loss function value does not meet the training stopping condition, adjusting the model parameters of the sound effect analysis model to obtain an updated sound effect analysis model, and training the updated sound effect analysis model using the next training sample until the training stopping condition is met to obtain a trained sound effect analysis model.

[0011] In one embodiment, the speaker type and layout include the type, installation location, installation direction, and quantity of each speaker in the speaker system; before inputting the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source, the control method further includes: generating a user preference vector based on user listening preference information when the second information is a vector; and / or generating a speaker parameter vector based on the type of each speaker and the quantity of each speaker when the second information is a vector, and generating a vehicle space vector based on the installation location and installation direction of each speaker; wherein, the second information includes an audio feature vector generated based on the audio features, singing features, music style features, and orchestration features of the first sound source, and also includes the user preference vector, and / or the speaker parameter vector and the vehicle space vector.

[0012] This application also provides a control device for a vehicle audio system, including a first sound effect module, a second sound effect module, a third sound effect module, and a sound effect adjustment module; the first sound effect module is used to input second information into a trained sound effect analysis model to obtain first sound effect parameters corresponding to a first sound source; the second information is determined based on the first information; the first information includes at least the audio characteristics, singing characteristics, musical style characteristics, and orchestration characteristics of the first sound source; the second sound effect module is used to determine the second sound effect parameters corresponding to the first sound source according to the sound source sound field information of the vehicle and the sound information of the vehicle's audio system; the sound source sound field information includes the sound source sound field height and sound source sound field position; the sound information includes the sound type and layout, and the sound power distribution parameters; the third sound effect module is used to determine the target sound effect parameters corresponding to the first sound source according to the first sound effect parameters and the second sound effect parameters; the sound effect adjustment module is used to adjust the sound effect parameters of the audio system to the target sound effect parameters when playing the first sound source.

[0013] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described control method for the vehicle audio system.

[0014] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described control method for a vehicle audio system.

[0015] This application also provides a computer program product, which is stored in a storage medium and, when executed by at least one processor, implements the above-described vehicle audio system control method.

[0016] This application provides a control method and related products for a vehicle audio system. By inputting second information determined based on first information into a trained sound effect analysis model, first sound effect parameters corresponding to a first sound source are obtained. The first information includes at least the audio characteristics, singing characteristics, musical style characteristics, and orchestration characteristics of the first sound source. Based on the sound field information of the vehicle's sound source and the sound information of the vehicle's audio system, second sound effect parameters corresponding to the first sound source are determined. Based on the first and second sound effect parameters, target sound effect parameters corresponding to the first sound source are determined. When playing the first sound source, the sound effect parameters of the audio system are adjusted to the target sound effect parameters. This method comprehensively considers the characteristics of the sound source itself, the sound field information of the vehicle's sound source, and the sound information of the vehicle's audio system on the sound quality, thereby improving the sound quality of the vehicle audio system and the listening experience of the driver and passengers. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the control method for a vehicle audio system provided in an embodiment of this application;

[0018] Figure 2 This is a schematic flowchart illustrating the control method for the vehicle audio system provided in this application embodiment. Figure 1 ;

[0019] Figure 3 This is a schematic flowchart illustrating the control method for the vehicle audio system provided in this application embodiment. Figure 2 ;

[0020] Figure 4 This is a schematic flowchart illustrating the control method for the vehicle audio system provided in this application embodiment. Figure 3 ;

[0021] Figure 5 This is a schematic diagram of the structure of the control device for the vehicle audio system provided in the embodiments of this application;

[0022] Figure 6 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application;

[0023] Figure 7 This is a schematic diagram of another embodiment of the electronic device provided in this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0025] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0026] The vehicle audio system control method provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the vehicle audio system control method, but is not limited to the above forms.

[0027] The control method of the vehicle audio system provided in this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0028] Please see Figure 1 The vehicle audio system control method provided in this application embodiment may include:

[0029] Step S101: Input the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source; the second information is determined based on the first information; the first information includes at least the audio features, singing features, music style features and orchestration features of the first sound source;

[0030] Step S102: Based on the vehicle's sound source sound field information and the vehicle's audio system audio information, determine the second sound effect parameters corresponding to the first sound source; the sound source sound field information includes the sound source sound field height and sound source sound field position; the audio information includes the audio type and layout, as well as the audio power distribution parameters.

[0031] Step S103: Determine the target sound effect parameters corresponding to the first sound source based on the first sound effect parameters and the second sound effect parameters;

[0032] Step S104: While playing the first audio source, adjust the audio parameters of the audio system to the target audio parameters.

[0033] This application provides a control method for a vehicle audio system. By inputting second information determined based on first information into a trained sound effect analysis model, first sound effect parameters corresponding to a first sound source are obtained. The first information includes at least the audio characteristics, singing characteristics, musical style characteristics, and orchestration characteristics of the first sound source. Based on the sound field information of the vehicle's sound source and the sound information of the vehicle's audio system, second sound effect parameters corresponding to the first sound source are determined. Based on the first and second sound effect parameters, target sound effect parameters corresponding to the first sound source are determined. When playing the first sound source, the sound effect parameters of the audio system are adjusted to the target sound effect parameters. This method comprehensively considers the characteristics of the sound source itself, the sound field information of the vehicle's sound source, and the sound information of the vehicle's audio system on the sound quality, thereby improving the sound quality of the vehicle audio system and the listening experience of the driver and passengers.

[0034] Optionally, the audio features of the first audio source include file features, statistical features, frequency domain features, and time domain features. File features may include file formats such as MP3, WAV, and Dolby; statistical features may include file precision, sampling rate, and bit depth information; frequency domain features refer to the frequency characteristics obtained by calculating Fourier transforms, and may include frequency components and frequency structure; and time domain features may include duration.

[0035] Optionally, the performance characteristics of the first audio source include the singing language, the gender of the singer, the number of singers, and the performance space. The performance space can indicate whether the first audio source is a live performance version or an original version. The musical style characteristics of the first audio source can characterize its musical style, such as classical music, jazz, pop, rock, etc. The instrumentation characteristics of the first audio source can characterize the instruments used in its arrangement, such as distinctive ethnic instruments, guitar, piano, etc.

[0036] In one embodiment, before inputting the second information into the trained sound effect analysis model in step S101 to obtain the first sound effect parameters corresponding to the first sound source, the control method provided in this application embodiment further includes: acquiring the first sound source; extracting features from the first sound source to determine the feature information of the first sound source.

[0037] Optionally, the first audio source is a digital audio source, which can be an audio signal provided by a car music app, a car CD, a USB device, a mobile phone connected to the vehicle via Bluetooth, or other devices.

[0038] In one embodiment, a preset feature extraction rule can be used to extract features from the first sound source to obtain the feature information of the first sound source. Alternatively, the first sound source can be input into a trained first feature processing model, and the first feature processing model can be used to extract features from the first sound source to obtain the feature information of the first sound source.

[0039] In one embodiment, before performing feature extraction on the first sound source and determining the feature information of the first sound source as described above, the control method provided in this application embodiment further includes: preprocessing the first sound source.

[0040] Optionally, the above preprocessing includes at least one of removing DC components, correcting sampling errors, and filtering.

[0041] This application embodiment obtains a first sound source and preprocesses it to ensure the purity of the first sound source. Furthermore, by extracting features from the preprocessed first sound source to determine its feature information, the accuracy of determining the feature information of the first sound source can be improved. This allows the vehicle audio system to maximize the reproduction of the sound source's own features based on the target sound effect parameters determined according to the feature information of the first sound source, thereby improving the sound quality of the vehicle audio system and the user's listening experience.

[0042] Optionally, the first information may also include user listening preferences and / or the type and layout of the vehicle audio system, wherein the type and layout of the audio system includes the type, installation location, installation direction, and number of each type of audio system.

[0043] Among these, user listening preference information can characterize a user's listening habits and can be extracted from user operation information during the listening process. This operation information can include sound effect parameter selection information. In actual implementation, user listening preference information can be extracted based on user operation information related to sound effect parameter selection. This operation information can also include music selection information. For example, if the number of times a user switches from rock songs to other songs is higher than a preset number, it indicates that the user does not like rock music. Similarly, if the playback time of songs by artist A accounts for a higher percentage than a preset percentage in the user's playback history, it indicates that the user likes songs by artist A.

[0044] The vehicle audio system can include at least one of the following speaker types: high-frequency speaker, mid-frequency speaker, and low-frequency speaker. The installation direction of each speaker in the vehicle audio system characterizes its directivity, and the installation position of each speaker characterizes its compactness and symmetry. The equalizer settings of the vehicle audio system can be adjusted based on the installation direction and position of each speaker to improve the sound quality.

[0045] In one embodiment, before inputting the second information into the trained sound effect analysis model in step S101 above to obtain the first sound effect parameters corresponding to the first sound source, the control method provided in this application embodiment further includes:

[0046] The first piece of information is identified as the second piece of information;

[0047] The second information includes at least the characteristic information of the first sound source, and may also include user listening preference information, and / or the sound type and layout of the vehicle audio system.

[0048] In another embodiment, before inputting the second information into the trained sound effect analysis model in step S101 above to obtain the first sound effect parameters corresponding to the first sound source, the control method provided in this application embodiment further includes any one of the following:

[0049] Based on preset feature fusion and transformation rules, the first information is fused and transformed to obtain the second information;

[0050] The first information is input into the trained second feature processing model, and the second feature processing model performs feature fusion and transformation on the first information to obtain the second information.

[0051] The first feature processing model and the second feature processing model mentioned above can be the same feature processing model or different feature processing models. Optionally, the first feature processing model and the second feature processing model mentioned above are the same feature processing model built based on the TensorFlow open-source machine learning framework. This model can include at least one neural network among Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Deep Neural Networks (DNN). In actual implementation, the dynamic characteristics of RNN networks can be used to record and process the time-series features of the first sound source, realizing the capture of cyclic features of the first sound source and the generation of prediction parameters. Furthermore, the convolutional operations of CNN networks can be used to extract local features from the first sound source and extract effective information to support further feature analysis and model training. DNN networks can also be used to learn the deep structure of the first sound source to identify and understand more complex and abstract features in the first sound source. Furthermore, the feature processing model can continuously optimize its own model parameters by learning the inherent laws of features, thereby improving the accuracy of feature extraction, feature fusion, and transformation.

[0052] Optionally, when the second information is a vector, the second information includes at least an audio feature vector generated based on the audio features, singing features, music style features and orchestration features of the first sound source, and may also include a user preference vector generated based on the user's listening preference information, a sound parameter vector generated based on the type of each sound source and the number of each type of sound source, and a vehicle space vector generated based on the installation location and installation direction of each sound source.

[0053] In one embodiment, before inputting the second information into the trained sound effect analysis model in step S101 above to obtain the first sound effect parameters corresponding to the first sound source, the control method provided in this application embodiment further includes:

[0054] If the second information is a vector, a user preference vector is generated based on the user's music listening preference information; and / or

[0055] When the second information is a vector, an audio parameter vector is generated based on the type of each audio device and the quantity of each type of audio device, and a vehicle space vector is generated based on the installation location and installation direction of each audio device.

[0056] The second information includes an audio feature vector generated based on the audio features, singing features, music style features, and orchestration features of the first sound source, as well as a user preference vector, and / or, a sound parameter vector and a vehicle space vector.

[0057] Based on the characteristic information of the sound source, this application embodiment can further combine user preference information, as well as the sound type and layout of the vehicle audio system, to determine the target sound effect parameters. This not only enables the vehicle audio system to maximize the reproduction of the sound source's characteristics based on the target sound effect parameters, but also meets the user's personalized needs for sound effects. Furthermore, the vehicle audio system can enhance the detail, dynamic range, and spatial awareness of the sound source based on the target sound effect parameters, thereby improving the clarity and fullness of the sound quality and providing a more immersive and realistic listening experience for drivers and passengers.

[0058] like Figure 2As shown, in one application scenario, a first audio source can be input into a trained feature processing model. First, the feature processing model extracts features from the first audio source, determining its audio features, vocal features, musical style features, and orchestration features. Then, the feature processing model fuses and transforms these features to obtain the audio feature vector of the first audio source. Furthermore, user listening preference information can be input into the trained feature processing model to obtain a user preference vector. The type and quantity of each type of speaker can also be input to obtain a speaker parameter vector. The installation location and orientation of each speaker can also be input to obtain a vehicle space vector. Further, the audio feature vector, user preference vector, speaker parameter vector, and vehicle space vector can be input into a trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first audio source.

[0059] Optionally, the aforementioned sound effect analysis model includes a hidden layer, an output layer, and an optimizer. After inputting the audio feature vector, user preference vector, audio parameter vector, and vehicle space vector into the trained sound effect analysis model, the model can add non-linearity (e.g., ReLU) to the input vectors through the hidden layer using an activation function. Then, the output layer can classify the task using an activation function (e.g., softmax) on the output of the hidden layer. Finally, the optimizer can perform gradient optimization (e.g., Adam) on the output of the output layer, ultimately outputting the first sound effect parameter corresponding to the first sound source. Before inputting the audio feature vector, user preference vector, audio parameter vector, and vehicle space vector into the trained sound effect analysis model, classification and gradient algorithms can be used to iteratively train the model to obtain a trained sound effect analysis model.

[0060] It is worth mentioning that the vector is only one format example of the second information to facilitate the recognition of the sound effect analysis model, and this application does not restrict the format of the second information.

[0061] This application embodiment uses a trained feature processing model to extract, fuse, and transform features from a first sound source, obtaining an audio feature vector of the first sound source. This improves the efficiency and accuracy of feature extraction, fusion, and transformation, and also enhances the efficiency and accuracy of the sound effect analysis model based on the second information. Furthermore, by using the trained feature processing model to generate a user preference vector based on user listening preference information, and / or by using the feature processing model to generate a speaker parameter vector based on the type and quantity of each speaker, and by generating a vehicle space vector based on the installation location and direction of each speaker, the efficiency and accuracy of the sound effect analysis model based on the second information can be further improved.

[0062] In one embodiment, before inputting the second information into the trained sound effect analysis model in step S101 above to obtain the first sound effect parameters corresponding to the first sound source, the control method provided in this application embodiment further includes:

[0063] Obtain a training dataset, which includes multiple training samples. Each training sample includes a third piece of information and playback sound effect parameters corresponding to the second sound source. The third information is determined based on the fourth information. The fourth information includes at least the audio features, singing features, music style features, and orchestration features of the second sound source.

[0064] For each training sample, perform the following steps:

[0065] The training samples are input into the sound effect analysis model to obtain the predicted sound effect parameters of the car audio system;

[0066] Based on the predicted sound effect parameters and the played sound effect parameters, determine the loss function value of the sound effect analysis model;

[0067] If the loss function value does not meet the training stopping condition, adjust the model parameters of the sound effect analysis model to obtain an updated sound effect analysis model. Then, use the next training sample to train the updated sound effect analysis model until the training stopping condition is met, and obtain the trained sound effect analysis model.

[0068] The playback sound effect parameters corresponding to the second sound source are the optimal sound effect parameters for playing the second sound source. These parameters are at least related to the feature information of the second sound source, and may also be related to user preference information and / or the sound type and layout of the vehicle's audio system. These sound effect parameters can be obtained experimentally. Specifically, the playback sound effect parameters can be selected based on the correlation between the predicted sound effect parameters and the aforementioned information. For example, if the training samples are determined based on the feature information of the second sound source and user preference information, and the predicted sound effect parameters are correlated with both the feature information of the second sound source and user preference information, then the playback sound effect parameters can be selected based on these factors. The second sound source and the aforementioned first sound source can be the same sound source or different sound sources.

[0069] This application embodiment determines the loss function value of the sound effect analysis model by using the predicted sound effect parameters and the playback sound effect parameters obtained from the training samples. This ensures the training effect of the sound effect analysis model, and enables the trained sound effect analysis model to improve the efficiency and accuracy of determining the first sound effect parameters corresponding to the first sound source based on the second information. As a result, the vehicle audio system can maximize the reproduction of the characteristics of the sound source itself based on the first sound effect parameters or the target sound effect parameters determined based on the first sound effect parameters, and improve the sound quality of the vehicle audio system and the user's listening experience.

[0070] In one embodiment, before determining the second sound effect parameter corresponding to the first sound source based on the sound field information of the vehicle's sound source and the sound information of the vehicle's audio system in step S102 above, the control method provided in this application embodiment further includes:

[0071] Determine the location of the sound source and sound field based on the distribution of the drivers and passengers;

[0072] Determine the sound source sound field height based on the ear height of the driver and passengers;

[0073] The speaker power distribution parameters are determined based on the link relationship between the amplifier channels and the speakers in the audio system, the number of amplifier channels, the sound source sound field position, and the sound source sound field height.

[0074] Optionally, the distribution of occupants includes the number of occupants and their individual positions. In practice, in-vehicle images can be captured by cameras, and image recognition technology can be used to determine the occupants' distribution and ear height. Furthermore, by calling a pre-stored formula for calculating the sound source field position, the occupants' distribution can be substituted into the formula to obtain the sound source field position. Similarly, by calling a formula for calculating the sound source field height, the occupants' ear heights can be substituted into the formula to obtain the sound source field height. Additionally, by calling a pre-stored formula for calculating audio power distribution parameters, the link relationships between the audio system's amplifier channels and the speakers in the system, the number of amplifier channels, the sound source field position, and the sound source field height can be substituted into the formula to obtain the audio power distribution parameters. In addition, in actual implementation, the distribution position of the driver and passengers, the ear height of the driver and passengers, the link relationship between the power amplifier channel of the audio system and each speaker in the audio system, the number of power amplifier channels, the sound source sound field position, and the sound source sound field height can be input into the trained first information processing model to obtain the sound source sound field position, sound source sound field height, and speaker power distribution parameters.

[0075] Based on the distribution of the driver and passengers, this application embodiment can accurately determine the sound source sound field position, based on the ear height of the driver and passengers, can accurately determine the sound source sound field height, and based on the link relationship between the power amplifier channels of the audio system and each speaker in the audio system, the number of power amplifier channels, the sound source sound field position, and the sound source sound field height, can accurately determine the audio power distribution parameters. This ensures that when the first sound source is played with the target sound effect parameters determined by fusing the sound source sound field information of the vehicle and the audio information of the vehicle audio system, the sound field of the first sound source can match the position and ear height of the driver and passengers, providing a customized audio experience for each driver and passenger, and improving the sound quality of the in-vehicle audio system and the auditory experience of the driver and passengers.

[0076] The second sound effect parameter in step S102 above can be determined based on the vehicle's sound source sound field information and the vehicle's audio system audio information, combined with preset sound effect determination rules, to determine the second sound effect parameter corresponding to the first sound source. Alternatively, the second sound effect parameter corresponding to the first sound source can be obtained by inputting the vehicle's sound source sound field information and the vehicle's audio system audio information into a trained sound effect determination model.

[0077] This application embodiment integrates the sound field information of the vehicle's audio source and the audio information of the vehicle's audio system. Based on the audio type and layout of the vehicle's audio system, the number of amplifier channels, and the link relationship between the amplifier channels and each audio in the vehicle's audio system, the sound field information of the vehicle's audio source can be optimized to obtain second sound effect parameters. This ensures that when the first audio source is played with the target sound effect parameters determined based on the second sound effect parameters, the sound field of the first audio source can be matched with the position and ear height of the driver and passengers. This provides a customized audio experience for each driver and passenger, and improves the sound quality of the vehicle's audio system and the auditory experience of the driver and passengers.

[0078] In one embodiment, before inputting the vehicle's sound source sound field information and the vehicle's audio system audio information into the trained sound effect determination model, the control method provided in this application embodiment further includes: inputting the sound source sound field position, sound source sound field height, and audio type and layout into the trained second information processing model to obtain the sound source sound field position vector, the sound source sound field height vector, and the audio parameter vector.

[0079] The second sound effect parameter in step S102 above can also be obtained by inputting the sound source sound field position vector, sound source sound field height vector, audio parameter vector, and audio power distribution parameter into the trained sound effect determination model to obtain the second sound effect parameter corresponding to the first sound source. The first information processing model and the second information processing model mentioned above can be the same information processing model or different information processing models.

[0080] like Figure 3As shown, in one application scenario, the distribution location of the driver and passengers, their ear height, the type and layout of the vehicle audio system, the link relationship between the amplifier channels and each speaker in the vehicle audio system, and the number of amplifier channels can be input into a trained information processing model. First, the information processing model can determine the sound source sound field position based on the distribution location of the driver and passengers, and the sound source sound field height based on their ear height. Then, based on the link relationship between the amplifier channels and each speaker in the vehicle audio system, the number of amplifier channels, the sound source sound field position, and the sound source sound field height, the information processing model can determine the speaker power allocation parameters. Next, the information processing model can convert the sound source sound field position, sound source sound field height, and speaker type and layout into vector formats, obtaining the sound source sound field position vector, sound source sound field height vector, and speaker parameter vector. Finally, the sound source sound field position vector, sound source sound field height vector, speaker parameter vector, and speaker power allocation parameters are input into a trained sound effect determination model to obtain the second sound effect parameters corresponding to the first sound source.

[0081] The training process of the above information processing model can refer to the training process of the above feature processing model, and the training process of the above sound effect determination model can refer to the training process of the above sound effect parsing model. It will not be repeated here.

[0082] It is worth mentioning that the vector is only a format example to facilitate the recognition of the sound effect determination model. This application does not impose any restrictions on the format of the sound source sound field position, sound source sound field height, sound type and layout.

[0083] Based on accurately determining the speaker type and layout, speaker power distribution parameters, sound source sound field position, and sound source sound field height, this embodiment of the application obtains the sound source sound field position vector, sound source sound field height vector, and speaker parameter vector by inputting the sound source sound field position, sound source sound field height, speaker type, and layout into a trained second information processing model. This improves the efficiency and accuracy of the sound effect determination model in determining the second sound effect parameters based on the speaker power distribution parameters, speaker type and layout, sound source sound field position, and sound source sound field height.

[0084] Optionally, the first sound effect parameter includes at least one type of sound effect parameter and a first value for each type of sound effect parameter. Optionally, the second sound effect parameter includes at least one type of sound effect parameter and a second value for each type of sound effect parameter. Optionally, the target sound effect parameter includes each type of sound effect parameter in the first sound effect parameter and a target value for each type of sound effect parameter.

[0085] In one embodiment, step S103 above: determining the target sound effect parameters corresponding to the first sound source based on the first sound effect parameters and the second sound effect parameters, includes:

[0086] For each type of sound effect parameter in the first set of first sound effect parameters, the second value of the sound effect parameter is determined as the target value;

[0087] For each type of sound effect parameter in the second set of the first sound effect parameters, the first value of the sound effect parameter is determined as the target value;

[0088] The first set consists of the set of sound effect parameters that are common to both the first and second sound effect parameters; the second set consists of the set of sound effect parameters that are not common to both the first and second sound effect parameters.

[0089] This application embodiment determines the second value of each type of sound effect parameter in the first set of first sound effect parameters as the target value, and determines the first value of each type of sound effect parameter in the second set of first sound effect parameters as the target value. This allows for the correction of sound effect parameters in the first set that are related to the sound source sound field position and / or sound source sound field height, thereby obtaining target sound effect parameters. Based on these target sound effect parameters, the vehicle audio system can not only maximize the reproduction of the characteristics of the sound source itself, but also provide a customized audio experience for each driver and passenger, thereby improving the sound quality of the vehicle audio system and the auditory experience of the driver and passengers.

[0090] Optionally, the first sound effect parameter includes at least one type of sound effect parameter and a first value for each type of sound effect parameter. Optionally, the second sound effect parameter includes positioning accuracy and a second value for positioning accuracy. Optionally, the target sound effect parameter includes each type of sound effect parameter in the first sound effect parameter and a target value for each type of sound effect parameter.

[0091] In another embodiment, step S103 above: determining the target sound effect parameters corresponding to the first sound source based on the first sound effect parameters and the second sound effect parameters, includes:

[0092] For each type of sound effect parameter in the first sound effect parameter, the target value of the sound effect parameter is determined based on the relationship between the sound effect parameter and the positioning accuracy, as well as the first value of the sound effect parameter and / or the second value of the positioning accuracy.

[0093] This application embodiment determines the target value of the sound effect parameter for each type of sound effect parameter in the first sound effect parameter, based on the relationship between the sound effect parameter and the positioning accuracy, as well as the first value of the sound effect parameter and / or the second value of the positioning accuracy. This enables the vehicle audio system to not only maximize the reproduction of the characteristics of the sound source itself based on the target sound effect parameter, but also to provide a customized audio experience for each driver and passenger, thereby improving the sound quality of the vehicle audio system and the auditory experience of the driver and passengers.

[0094] In one embodiment, determining the target value of the sound effect parameter based on the relationship between the sound effect parameter and the positioning accuracy, and a first value of the sound effect parameter and / or a second value of the positioning accuracy, includes:

[0095] When the sound effect parameter is the positioning accuracy, the second value of the positioning accuracy is determined as the target value of the sound effect parameter;

[0096] When the sound effect parameters are related to the positioning accuracy, the target value of the sound effect parameters is determined based on the first value of the sound effect parameters and the second value of the positioning accuracy.

[0097] When the sound effect parameters are independent of the positioning accuracy, the first value of the sound effect parameters is determined as the target value of the sound effect parameters.

[0098] Optionally, the first audio effect parameter includes at least one of the following: frequency band filter, positioning accuracy, frequency response, sensitivity, stereo separation, crossover frequency, equalizer setting, and sound field width. When the audio effect parameter is any one of sound field width, sensitivity, crossover frequency, and frequency response, this audio effect parameter is related to positioning accuracy; when the audio effect parameter is any one of frequency band filter, stereo separation, and equalizer setting, this audio effect parameter is related to positioning accuracy.

[0099] This application embodiment determines the target value of the sound effect parameter by setting the second value of the positioning accuracy when the sound effect parameter is the positioning accuracy; when the sound effect parameter is related to the positioning accuracy, the target value of the sound effect parameter is determined based on the first value of the sound effect parameter and the second value of the positioning accuracy; when the sound effect parameter is independent of the positioning accuracy, the first value of the sound effect parameter is determined as the target value of the sound effect parameter. This allows the vehicle audio system to not only maximize the reproduction of the characteristics of the sound source itself based on the target sound effect parameter, but also provide a customized audio experience for each driver and passenger, thereby improving the sound quality of the vehicle audio system and the auditory experience of the driver and passengers.

[0100] In the case where the sound effect parameters are related to the positioning accuracy, the target value of the sound effect parameters is determined based on the first value of the sound effect parameters and the second value of the positioning accuracy. This can be achieved by substituting the first value of the sound effect parameters and the second value of the positioning accuracy into a preset relational expression, where the preset relational expression can be determined based on the correlation between the sound effect parameters and the positioning accuracy. Alternatively, the target value of the sound effect parameters can be obtained by fusing the first value of the sound effect parameters and the second value of the positioning accuracy using a preset fusion rule.

[0101] In this embodiment of the application, when the sound effect parameters are related to the positioning accuracy, the target value of the sound effect parameters is determined by fusing the value of the sound effect parameters in the first sound effect parameters with the positioning accuracy value in the second sound effect parameters. This allows the vehicle audio system to not only maximize the reproduction of the characteristics of the sound source itself based on the target sound effect parameters, but also provide a customized audio experience for each driver and passenger, thereby improving the sound quality of the vehicle audio system and the auditory experience of the driver and passengers.

[0102] Combination Figure 3 and Figure 4 In one application scenario, a first audio source can be input into a trained feature processing model. First, the feature processing model extracts features from the first audio source, determining its audio features, vocal features, musical style features, and orchestration features. Then, the feature processing model fuses and transforms these features to obtain the audio feature vector of the first audio source. Furthermore, user listening preference information can be input into the trained feature processing model to obtain a user preference vector. The type and quantity of each type of speaker can also be input to obtain a speaker parameter vector. The installation location and orientation of each speaker can also be input to obtain a vehicle space vector. Further, the audio feature vector, user preference vector, speaker parameter vector, and vehicle space vector can be input into a trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first audio source.

[0103] In addition, the distribution location of the occupants, their ear height, the type and layout of the vehicle audio system, the link relationship between the amplifier channels and each speaker in the vehicle audio system, and the number of amplifier channels can be input into a trained information processing model. First, the information processing model can determine the sound source sound field position based on the occupants' distribution location, the sound source sound field height based on their ear height, and the speaker power allocation parameters based on the link relationship between the amplifier channels and each speaker in the vehicle audio system, the number of amplifier channels, the sound source sound field position, and the sound source sound field height. Then, the information processing model can convert the sound source sound field position, sound source sound field height, and speaker type and layout into vector formats to obtain the sound source sound field position vector, sound source sound field height vector, and speaker parameter vector. Finally, the sound source sound field position vector, sound source sound field height vector, speaker parameter vector, and speaker power allocation parameters can be input into a trained sound effect determination model to obtain the second sound effect parameters corresponding to the first sound source.

[0104] Furthermore, for each type of sound effect parameter in the first sound effect parameters, a target value for the sound effect parameter can be determined based on the relationship between the sound effect parameter and the positioning accuracy, as well as the first value of the sound effect parameter in the first sound effect parameters and / or the second value of the positioning accuracy in the second sound effect parameters. Finally, when playing the first sound source, the sound effect parameters of the vehicle audio system can be adjusted to the target sound effect parameters so that the vehicle audio system plays the first sound source based on the target sound effect parameters.

[0105] This application embodiment inputs the second information determined based on the feature information of the first sound source into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source. Based on the sound field information of the vehicle's sound source and the sound information of the vehicle's audio system, the second sound effect parameters corresponding to the first sound source are determined. For each type of sound effect parameter in the first sound effect parameters, the target value of the sound effect parameter is determined based on the relationship between the sound effect parameter and the positioning accuracy, and the first value of the sound effect parameter in the first sound effect parameters and / or the second value of the positioning accuracy in the second sound effect parameters. This allows the vehicle audio system to not only maximize the reproduction of the characteristics of the sound source itself when playing the first sound source, but also provide a customized audio experience for each driver and passenger, thereby improving the sound quality of the vehicle audio system and the auditory experience of the driver and passengers.

[0106] Please see Figure 5 This application embodiment also provides a control device 500 for a vehicle audio system, which can realize the above-mentioned control method for the vehicle audio system. The system includes: a first sound effect module 501, a second sound effect module 502, a third sound effect module 503, and a sound effect adjustment module 504.

[0107] The first sound effect module 501 is used to input the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source; the second information is determined based on the first information; the first information includes at least the audio features, singing features, music style features and orchestration features of the first sound source;

[0108] The second sound effect module 502 is used to determine the second sound effect parameters corresponding to the first sound source based on the sound source sound field information of the vehicle and the sound information of the vehicle's audio system; the sound source sound field information includes the sound source sound field height and the sound source sound field position; the audio information includes the audio type and layout, as well as the audio power distribution parameters.

[0109] The third sound effect module 503 is used to determine the target sound effect parameters corresponding to the first sound source based on the first sound effect parameters and the second sound effect parameters;

[0110] The sound effect adjustment module 504 is used to adjust the sound effect parameters of the audio system to the target sound effect parameters when the first sound source is played.

[0111] The vehicle audio system control device provided in this application embodiment can implement all the steps of the above-described vehicle audio system control method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0112] Optionally, such as Figure 6As shown in the illustration, this application also provides an electronic device 600, including a processor 601 and a memory 602. The memory 602 stores a program or instructions that can run on the processor 601. When the program or instructions are executed by the processor 601, they implement the various steps of the control method embodiment of the vehicle audio system described above, and achieve the same technical effect. To avoid repetition, they will not be described again here. It should be noted that the electronic device in this application includes the aforementioned mobile electronic device and non-mobile electronic device.

[0113] Figure 7 To illustrate the hardware structure of the electronic device according to the embodiments of this application, the electronic device includes:

[0114] The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0115] The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called by the processor 701 to execute the control method of the vehicle audio system of the embodiments of this application.

[0116] The input / output interface 703 is used to implement information input and output;

[0117] The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0118] Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704);

[0119] The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0120] The electronic device provided in this application embodiment can implement all the steps of the above-described vehicle audio system control method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0121] This application also provides a computer-readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various steps of the above-described vehicle audio system control method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0122] The processor is the processor in the electronic device described in the above embodiments. The computer-readable storage medium includes computer-readable storage media such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0123] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various steps of the above-described vehicle audio system control method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0124] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0125] This application provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various steps of the control method embodiment of the vehicle audio system described above, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0126] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not delete other identical elements present in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0128] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A control method for a vehicle audio system, characterized in that, include: The second information is input into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source. The second information is determined based on the first information; the first information includes at least the audio characteristics, singing characteristics, musical style characteristics, and orchestration characteristics of the first sound source; The first sound effect parameter includes at least one type of sound effect parameter and a first value for each type of sound effect parameter; Based on the vehicle's sound source sound field information and the vehicle's audio system audio information, the second sound effect parameter corresponding to the first sound source is determined; the sound source sound field information includes the sound source sound field height and sound source sound field position; the audio information includes the audio type and layout, as well as the audio power distribution parameters; the second sound effect parameter includes the positioning accuracy and a second value of the positioning accuracy; For each type of sound effect parameter in the first sound effect parameters, a target value for the sound effect parameter is determined based on the relationship between the sound effect parameter and the positioning accuracy, as well as a first value of the sound effect parameter and / or a second value of the positioning accuracy. When playing the first audio source, the audio effect parameters of the audio system are adjusted to target audio effect parameters; the target audio effect parameters include the at least one type of audio effect parameters and the target values ​​of the various types of audio effect parameters.

2. The control method as described in claim 1, characterized in that, Before determining the second sound effect parameter corresponding to the first sound source based on the vehicle's sound source sound field information and the sound information of the vehicle's audio system, the control method further includes: The location of the sound source sound field is determined based on the distribution of the drivers and passengers; The sound source sound field height is determined based on the ear height of the driver and passengers; The speaker power allocation parameters are determined based on the link relationship between the amplifier channels of the audio system and each speaker in the audio system, the number of amplifier channels, the sound source sound field position, and the sound source sound field height.

3. The control method as described in claim 1, characterized in that, The step of determining the target value of the sound effect parameter based on the relationship between the sound effect parameter and the positioning accuracy, and a first value of the sound effect parameter and / or a second value of the positioning accuracy, includes: When the sound effect parameter is the positioning accuracy, the second value of the positioning accuracy is determined as the target value of the sound effect parameter; When the sound effect parameter is related to the positioning accuracy, the target value of the sound effect parameter is determined based on the first value of the sound effect parameter and the second value of the positioning accuracy. When the sound effect parameter is independent of the positioning accuracy, the first value of the sound effect parameter is determined as the target value of the sound effect parameter.

4. The control method as described in claim 1, characterized in that, Before inputting the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source, the control method further includes: Obtain a training dataset, wherein the training dataset includes multiple training samples, each training sample including a third piece of information and playback sound effect parameters corresponding to the second sound source; the third information is determined based on a fourth piece of information; the fourth information includes at least the audio features, singing features, music style features, and orchestration features of the second sound source; For each training sample, perform the following steps: The training samples are input into the sound effect analysis model to obtain the predicted sound effect parameters of the vehicle audio system; Based on the predicted sound effect parameters and the played sound effect parameters, the loss function value of the sound effect analysis model is determined; If the loss function value does not meet the training stopping condition, the model parameters of the sound effect analysis model are adjusted to obtain an updated sound effect analysis model. The updated sound effect analysis model is then trained using the next training sample until the training stopping condition is met, resulting in a trained sound effect analysis model.

5. The control method as described in claim 1, characterized in that, The speaker type and layout include the type, installation location, installation direction, and quantity of each speaker in the speaker system; Before inputting the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source, the control method further includes: If the second information is a vector, a user preference vector is generated based on the user's music listening preference information; and / or When the second information is a vector, an audio parameter vector is generated based on the type of each audio device and the quantity of each type of audio device, and a vehicle space vector is generated based on the installation position and installation direction of each audio device. The second information includes an audio feature vector generated based on the audio features, singing features, music style features, and orchestration features of the first sound source, as well as the user preference vector, and / or the audio parameter vector and the vehicle space vector.

6. A control device for a vehicle audio system, characterized in that, It includes a first sound effect module, a second sound effect module, a third sound effect module, and a sound effect adjustment module; The first sound effect module is used to input the second information into the trained sound effect analysis model to obtain the first sound effect parameters corresponding to the first sound source; the second information is determined based on the first information; the first information includes at least the audio features, singing features, music style features and orchestration features of the first sound source; The first sound effect parameter includes at least one type of sound effect parameter and a first value for each type of sound effect parameter; The second sound effect module is used to determine the second sound effect parameters corresponding to the first sound source based on the sound source sound field information of the vehicle and the sound information of the vehicle's audio system; the sound source sound field information includes the sound source sound field height and the sound source sound field position; the audio information includes the audio type and layout, as well as the audio power distribution parameters; the second sound effect parameters include the positioning accuracy and a second value of the positioning accuracy; The third sound effect module is used to determine the target value of the sound effect parameter for each type of sound effect parameter in the first sound effect parameter, based on the relationship between the sound effect parameter and the positioning accuracy, and the first value of the sound effect parameter and / or the second value of the positioning accuracy; The sound effect adjustment module is used to adjust the sound effect parameters of the audio system to target sound effect parameters when the first sound source is played; the target sound effect parameters include the at least one type of sound effect parameters and the target values ​​of the various types of sound effect parameters.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the control method as described in any one of claims 1 to 5.

9. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by at least one processor, the computer program product implements the control method as described in any one of claims 1 to 5.

Images