Sound adjusting method and device of self-adaptive vehicle-mounted audio equipment, vehicle and medium

Abstract

The invention relates to the technical field of vehicle audio systems, in particular to a sound adjusting method and device of self-adaptive vehicle-mounted audio equipment, a vehicle and a medium. The method comprises the following steps: acquiring a face image of a current user; analyzing the face image by using a preset face gender-age recognition model, and determining the gender and age of the current user; and based on the gender and the age of the current user, determining a current audio parameter by using a preset gender-age-hearing frequency matching model, and controlling the vehicle-mounted loudspeaker system to produce sound based on the current audio parameter. Thus, the audio parameters are automatically adjusted according to the gender and age of the person in the vehicle, the problems that in the prior art, manual adjustment of audio setting is not convenient enough, and self-adaptive adjustment cannot be conducted according to the gender, age and auditory characteristics of the person in the vehicle are solved, and individuation and intelligence of audio experience in the vehicle are improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle audio systems, and in particular to a sound adjustment method, device, vehicle and medium for adaptive vehicle audio equipment. Background Art

[0002] With the continuous development of automobile technology, people's demand for in-car audio experience is also increasing. In order to meet this demand, various in-car audio devices have appeared on the market, including audio systems, in-car players, etc.

[0003] In the related art, in-vehicle audio equipment usually requires users to manually adjust audio settings to meet personal preferences.

[0004] However, this manual adjustment is not convenient enough and cannot be adaptively adjusted according to the gender, age and auditory characteristics of the people in the car, and urgently needs to be improved. Summary of the invention

[0005] The present application provides a sound adjustment method, device, vehicle and medium for adaptively adjusting the sound of an in-vehicle audio device to solve the problems in the prior art that manual adjustment of audio settings is not convenient enough and cannot be adaptively adjusted according to the gender, age and auditory characteristics of the occupants of the vehicle, so as to enhance the personalization and intelligence of the in-vehicle audio experience.

[0006] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a sound adjustment method for an adaptive vehicle audio device, comprising the following steps:

[0007] Get the current user's facial image;

[0008] Analyze the facial image using a preset face gender-age recognition model to determine the gender and age of the current user;

[0009] Based on the gender and age of the current user, a preset gender-age-hearing frequency matching model is used to determine the current audio parameters, and the vehicle speaker system is controlled to produce sound based on the current audio parameters.

[0010] According to an embodiment of the present application, controlling the vehicle speaker system to emit sound based on the current audio parameter includes:

[0011] generating a corresponding audio signal based on the current audio parameters;

[0012] The audio signal is sent to a power amplifier to obtain an enhanced audio signal, and the enhanced audio signal is transmitted to the vehicle speaker system to drive the vehicle speaker system to produce sound.

[0013] According to one embodiment of the present application, before analyzing the facial image using the preset face gender-age recognition model to determine the gender and age of the current user, the method further includes:

[0014] Get a dataset of facial images with gender and age annotated.

[0015] Preprocessing the face image dataset to obtain a preprocessed face image dataset;

[0016] Using a feature extractor to perform feature extraction on the preprocessed face image data set to obtain a face feature set, and dividing the face feature set into a first training set and a first validation set;

[0017] The first preset neural network is trained using the first training set to obtain a first initial neural network model, and the first verification set is used to verify the first initial neural network model until the first initial neural network model meets a first preset condition, and the iterative training of the first preset neural network is terminated to obtain the preset face gender-age recognition model, otherwise the iterative training is continued after adjusting the hyperparameters.

[0018] According to an embodiment of the present application, before determining the current audio parameter based on the gender and age of the current user using the preset gender-age-hearing frequency matching model, the method further includes:

[0019] Acquire standard hearing test data of different genders and age groups, wherein the standard hearing test data is a correspondence between the different genders and age groups and audio parameters;

[0020] Preprocessing the standard hearing test data, and dividing the preprocessed standard hearing test data into a second training set and a second validation set;

[0021] Based on the gender-age-hearing frequency sensitivity theory, the second preset neural network is trained using the second training set to obtain a second initial neural network model, and the second verification set is used to verify the second initial neural network model until the second initial neural network model meets the second preset condition, and the iterative training of the second preset neural network is terminated to obtain the preset gender-age-hearing frequency matching model, otherwise the iterative training continues after adjusting the hyperparameters.

[0022] According to an embodiment of the present application, the audio parameters include frequency, pitch and loudness.

[0023] According to one embodiment of the present application, after controlling the vehicle-mounted speaker system to emit sound based on the current audio parameter, the method further includes:

[0024] The current audio parameter is displayed on a vehicle display screen so that the current user can view the specific value corresponding to the current audio parameter.

[0025] According to the sound adjustment method of the adaptive in-vehicle audio device proposed in the embodiment of the present application, by acquiring the facial image of the current user, the facial image can be analyzed using the preset face gender-age recognition model to determine the gender and age of the current user; based on the gender and age of the current user, the current audio parameters are determined using the preset gender-age-hearing frequency matching model, and the in-vehicle speaker system is controlled to emit sound based on the current audio parameters. Thus, by automatically adjusting the audio parameters according to the gender and age of the occupants of the vehicle, the problem that the existing technology is not convenient enough to manually adjust the audio settings, and cannot perform adaptive adjustments according to the gender, age and hearing characteristics of the occupants of the vehicle is solved, so as to enhance the personalization and intelligence of the in-vehicle audio experience.

[0026] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a sound adjustment device for an adaptive vehicle audio device, comprising:

[0027] An acquisition module is used to acquire the facial image of the current user;

[0028] A first determination module is used to analyze the facial image using a preset face gender-age recognition model to determine the gender and age of the current user;

[0029] The second determination module is used to determine the current audio parameters based on the gender and age of the current user and using a preset gender-age-hearing frequency matching model, and control the vehicle speaker system to produce sound based on the current audio parameters.

[0030] According to an embodiment of the present application, the second determining module is specifically configured to:

[0031] generating a corresponding audio signal based on the current audio parameters;

[0032] The audio signal is sent to a power amplifier to obtain an enhanced audio signal, and the enhanced audio signal is transmitted to the vehicle speaker system to drive the vehicle speaker system to produce sound.

[0033] According to one embodiment of the present application, before analyzing the facial image using the preset face gender-age recognition model to determine the gender and age of the current user, the first determination module is further used to:

[0034] Get a dataset of facial images with gender and age annotated.

[0035] Preprocessing the face image dataset to obtain a preprocessed face image dataset;

[0036] Using a feature extractor to perform feature extraction on the preprocessed face image data set to obtain a face feature set, and dividing the face feature set into a first training set and a first validation set;

[0037] The first preset neural network is trained using the first training set to obtain a first initial neural network model, and the first verification set is used to verify the first initial neural network model until the first initial neural network model meets a first preset condition, and the iterative training of the first preset neural network is terminated to obtain the preset face gender-age recognition model, otherwise the iterative training is continued after adjusting the hyperparameters.

[0038] According to one embodiment of the present application, before determining the current audio parameter based on the gender and age of the current user using the preset gender-age-hearing frequency matching model, the second determination module is further used to:

[0039] Acquire standard hearing test data of different genders and age groups, wherein the standard hearing test data is a correspondence between the different genders and age groups and audio parameters;

[0040] Preprocessing the standard hearing test data, and dividing the preprocessed standard hearing test data into a second training set and a second validation set;

[0041] Based on the gender-age-hearing frequency sensitivity theory, the second preset neural network is trained using the second training set to obtain a second initial neural network model, and the second verification set is used to verify the second initial neural network model until the second initial neural network model meets the second preset condition, and the iterative training of the second preset neural network is terminated to obtain the preset gender-age-hearing frequency matching model, otherwise the iterative training continues after adjusting the hyperparameters.

[0042] According to an embodiment of the present application, the audio parameters include frequency, pitch and loudness.

[0043] According to an embodiment of the present application, after controlling the vehicle-mounted speaker system to emit sound based on the current audio parameter, the second determining module is further configured to:

[0044] The current audio parameter is displayed on a vehicle display screen so that the current user can view the specific value corresponding to the current audio parameter.

[0045] According to the sound adjustment device of the adaptive in-vehicle audio device proposed in the embodiment of the present application, by acquiring the facial image of the current user, the facial image can be analyzed using the preset face gender-age recognition model to determine the gender and age of the current user; based on the gender and age of the current user, the current audio parameters are determined using the preset gender-age-hearing frequency matching model, and the sound of the in-vehicle speaker system is controlled based on the current audio parameters. Thus, by automatically adjusting the audio parameters according to the gender and age of the occupants of the vehicle, the problem that the existing technology is not convenient enough to manually adjust the audio settings, and cannot perform adaptive adjustments according to the gender, age and hearing characteristics of the occupants of the vehicle is solved, so as to enhance the personalization and intelligence of the in-vehicle audio experience.

[0046] To achieve the above objectives, the third aspect of the present application proposes a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the sound adjustment method of the adaptive vehicle audio device as described in the above embodiment.

[0047] To achieve the above objectives, the fourth aspect of the present application proposes a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement the sound adjustment method of the adaptive vehicle audio device as described in the above embodiment.

[0048] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0050] Figure 1 A flowchart of a sound adjustment method for an adaptive vehicle audio device provided according to an embodiment of the present application;

[0051] Figure 2 This is a schematic diagram of research results on gender, age and hearing according to an embodiment of the present application;

[0052] Figure 3 A schematic diagram of an implementation path of a method for adjusting sound of an adaptive in-vehicle audio device according to an embodiment of the present application;

[0053] Figure 4 A block diagram of a sound adjustment device for an adaptive vehicle audio device provided according to an embodiment of the present application;

[0054] Figure 5 It is a schematic diagram of the structure of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0056] The following describes a sound adjustment method, device, vehicle, and medium for an adaptive in-vehicle audio device according to an embodiment of the present application with reference to the accompanying drawings.

[0057] Figure 1 It is a flow chart of a method for adjusting sound of an adaptive in-vehicle audio device according to an embodiment of the present application.

[0058] like Figure 1 As shown, the sound adjustment method of the adaptive vehicle audio device includes the following steps:

[0059] In step S101, a facial image of the current user is obtained.

[0060] Specifically, in an embodiment of the present application, a facial image of the current user may be collected by an image sensor to capture detailed features of the user's face.

[0061] In step S102, the facial image is analyzed using a preset face gender-age recognition model to determine the gender and age of the current user.

[0062] Specifically, by applying a preset face gender-age recognition model and adopting a face gender-age matching algorithm, an in-depth analysis is performed on the facial image provided by the current user, thereby accurately determining the gender and age information of the current user.

[0063] The following describes in detail how to obtain the preset face gender-age recognition model.

[0064] As a possible implementation method, in some embodiments, before using a preset face gender-age recognition model to analyze facial images and determine the gender and age of the current user, it also includes: obtaining a face image dataset containing labeled gender and age; preprocessing the face image dataset to obtain a preprocessed face image dataset; using a feature extractor to extract features from the preprocessed face image dataset to obtain a face feature set, and dividing the face feature set into a first training set and a first verification set; using the first training set to train a first preset neural network to obtain a first initial neural network model, and using the first verification set to verify the first initial neural network model until the first initial neural network model meets a first preset condition, and then terminating the iterative training of the first preset neural network to obtain the preset face gender-age recognition model, otherwise adjusting the hyperparameters and continuing the iterative training.

[0065] Specifically, first, it is necessary to collect a dataset of face images with gender and age information annotated, which is the basis for gender and age recognition tasks. Next, a series of preprocessing steps can be performed on these face images to ensure the quality and consistency of the data. Preprocessing may include operations such as adjusting the image size, normalizing pixel values, and enhancing contrast, in order to obtain a more standardized preprocessed face image dataset. Then, an efficient feature extractor can be used to extract features from the preprocessed face image dataset to extract key information that helps gender and age recognition from the image, forming a face feature set containing rich information, which serves as the basis for subsequent model training and verification. After obtaining the face feature set, it can be divided into two parts: the first training set and the first verification set. The first training set will be used to train the first preset neural network. Through the adjustment and optimization of weights, the neural network can learn how to accurately predict gender and age based on facial features. During the training process, the first verification set can be used to verify the performance of the model to ensure that the model can maintain good recognition effects on unseen data. Once the first initial neural network model meets the preset conditions (such as reaching a certain accuracy rate or the performance on the validation set is no longer significantly improved), the iterative training of the first preset neural network can be ended. At this point, the preset face gender-age recognition model can be obtained. If the first initial neural network model fails to meet the preset conditions, the hyperparameters (such as learning rate, batch size, network structure, etc.) can be adjusted, and then iterative training can be continued until the model achieves the expected effect.

[0066] In step S103, based on the gender and age of the current user, the current audio parameters are determined using a preset gender-age-hearing frequency matching model, and the vehicle speaker system is controlled to emit sound based on the current audio parameters.

[0067] That is, according to the gender and age information of the current user, by applying the preset gender-age-hearing frequency matching model, the audio parameter settings suitable for the user can be determined. Subsequently, based on these audio parameters, the vehicle speaker system can be effectively controlled to make the sound it produces clear and comfortable to meet the hearing needs of different user groups.

[0068] As a possible implementation method, in some embodiments, the sound of the vehicle speaker system is controlled based on the current audio parameters, including: generating a corresponding audio signal based on the current audio parameters; sending the audio signal to a power amplifier to obtain an enhanced audio signal, and transmitting the enhanced audio signal to the vehicle speaker system to drive the vehicle speaker system to produce sound.

[0069] Specifically, according to the current audio parameters, a corresponding audio signal can be generated; then, this audio signal will be sent to the power amplifier, and after amplification processing, an enhanced audio signal will be obtained. Then, the enhanced audio signal will be transmitted to the car speaker system, and the car speaker will be driven by this system to produce sound.

[0070] The following describes in detail how to obtain the preset gender-age-hearing frequency matching model.

[0071] Furthermore, in some embodiments, before determining the current audio parameters based on the gender and age of the current user using a preset gender-age-hearing frequency matching model, it also includes: obtaining standard hearing test data for different gender and age groups, wherein the standard hearing test data is the correspondence between different gender and age groups and audio parameters; preprocessing the standard hearing test data, and dividing the preprocessed standard hearing test data into a second training set and a second verification set; based on the gender-age-hearing frequency sensitivity theory, using the second training set to train the second preset neural network to obtain a second initial neural network model, and using the second verification set to verify the second initial neural network model, until the second initial neural network model meets the second preset condition, terminating the iterative training of the second preset neural network to obtain the preset gender-age-hearing frequency matching model, otherwise adjusting the hyperparameters and continuing the iterative training.

[0072] Specifically, first, it is necessary to collect standard hearing test data of different gender and age groups, which reflect the precise correspondence between different gender and age groups and audio parameters, based on the gender-age-hearing frequency sensitivity theory, such as Figure 2 As shown ( Figure 2 (a) is the male hearing characteristic curve, Figure 2(b) is the female hearing characteristic curve), gender and age are divided into different groups, and the parameters related to sound frequency, pitch, and loudness are determined based on the professional knowledge and experience of audio processing. Subsequently, these standard hearing test data will be preprocessed to ensure the quality and availability of the data. After preprocessing, these data are divided into two main parts: the second training set and the second validation set. Based on the gender-age-hearing frequency sensitivity theory, the second training set is used to train the second preset neural network model. During the training process, the structure and parameters of the neural network can be continuously adjusted and optimized in order to achieve the best learning effect. After the training is completed, the second validation set can be used to verify the performance of the second initial neural network model. If the performance of the model meets the second preset condition, the iterative training of the second preset neural network can be terminated. If the performance of the model fails to meet expectations, the hyperparameters (such as learning rate, number of network layers, number of neurons, etc.) can be adjusted, and then the iterative training can be continued until the model meets the preset conditions. Through this series of steps, the preset gender-age-hearing frequency matching model can be finally obtained, which can accurately predict the audio parameters corresponding to different gender and age groups.

[0073] In some embodiments, the audio parameters include frequency, pitch and loudness.

[0074] Furthermore, in some embodiments, after controlling the vehicle speaker system to emit sound based on the current audio parameters, the method further includes: displaying the current audio parameters using a vehicle display screen so that the current user can view specific values ​​corresponding to the current audio parameters.

[0075] That is to say, after controlling the sound of the vehicle speaker system based on the current audio parameters, the vehicle display screen can also be used to display the current audio parameters, so that the current user can view the specific values ​​corresponding to the current audio parameters, and thus better understand information such as the sound quality and volume of the audio being played.

[0076] To facilitate those skilled in the art to further understand the sound adjustment method of the adaptive vehicle audio device proposed in the embodiment of the present application, the following is combined with Figure 3 For further explanation.

[0077] like Figure 3 As shown, first, facial information is collected through an image sensor; secondly, a facial gender and age matching algorithm (i.e., a preset facial gender-age recognition model) and a gender-age-stage frequency matching algorithm (i.e., a preset gender-age-hearing frequency matching model) are developed and implemented; then, the facial gender and age matching algorithm and the gender-age-stage frequency matching algorithm are integrated into the vehicle system, and the audio signal is amplified to a sufficient level through a power amplifier; finally, the amplified audio signal causes the speaker to vibrate and make a sound.

[0078] According to the sound adjustment method of the adaptive in-vehicle audio device proposed in the embodiment of the present application, by acquiring the facial image of the current user, the facial image can be analyzed using the preset face gender-age recognition model to determine the gender and age of the current user; based on the gender and age of the current user, the current audio parameters are determined using the preset gender-age-hearing frequency matching model, and the in-vehicle speaker system is controlled to emit sound based on the current audio parameters. Thus, by automatically adjusting the audio parameters according to the gender and age of the occupants of the vehicle, the problem that the existing technology is not convenient enough to manually adjust the audio settings, and cannot perform adaptive adjustments according to the gender, age and hearing characteristics of the occupants of the vehicle is solved, so as to enhance the personalization and intelligence of the in-vehicle audio experience.

[0079] Next, the sound adjustment device of the adaptive vehicle audio device proposed in the embodiment of the present application is described with reference to the accompanying drawings.

[0080] Figure 4 It is a block diagram of a sound adjustment device for an adaptive vehicle audio device according to an embodiment of the present application.

[0081] like Figure 4 As shown, the sound adjustment device 10 of the adaptive vehicle audio device includes: an acquisition module 100, a first determination module 200 and a second determination module 300.

[0082] Wherein, the acquisition module 100 is used to acquire the facial image of the current user;

[0083] The first determination module 200 is used to analyze the facial image using a preset face gender-age recognition model to determine the gender and age of the current user;

[0084] The second determination module 300 is used to determine the current audio parameters based on the gender and age of the current user and using a preset gender-age-hearing frequency matching model, and control the vehicle speaker system to produce sound based on the current audio parameters.

[0085] Further, in some embodiments, the second determining module 300 is specifically configured to:

[0086] Generate a corresponding audio signal based on the current audio parameters;

[0087] The audio signal is sent to a power amplifier to obtain an enhanced audio signal, and the enhanced audio signal is transmitted to the vehicle speaker system to drive the vehicle speaker system to produce sound.

[0088] Furthermore, in some embodiments, before analyzing the facial image using a preset face gender-age recognition model to determine the gender and age of the current user, the first determination module 200 is further configured to:

[0089] Get a dataset of facial images with gender and age annotated.

[0090] Preprocessing the face image data set to obtain a preprocessed face image data set;

[0091] Using a feature extractor to extract features from the preprocessed face image data set to obtain a face feature set, and dividing the face feature set into a first training set and a first validation set;

[0092] The first preset neural network is trained using the first training set to obtain a first initial neural network model, and the first initial neural network model is verified using the first verification set until the first initial neural network model meets the first preset condition, and the iterative training of the first preset neural network is terminated to obtain the preset face gender-age recognition model, otherwise the iterative training continues after adjusting the hyperparameters.

[0093] Further, in some embodiments, before determining the current audio parameter based on the gender and age of the current user using a preset gender-age-hearing frequency matching model, the second determination module 300 is further configured to:

[0094] Obtaining standard hearing test data for different genders and age groups, wherein the standard hearing test data is a correspondence between different genders and age groups and audio parameters;

[0095] Preprocessing the standard hearing test data, and dividing the preprocessed standard hearing test data into a second training set and a second validation set;

[0096] Based on the gender-age-hearing frequency sensitivity theory, the second preset neural network is trained with the second training set to obtain a second initial neural network model, and the second initial neural network model is verified with the second verification set until the second initial neural network model meets the second preset condition. The iterative training of the second preset neural network is terminated to obtain the preset gender-age-hearing frequency matching model, otherwise the iterative training continues after adjusting the hyperparameters.

[0097] Further, in some embodiments, the audio parameters include frequency, pitch, and loudness.

[0098] Further, in some embodiments, after controlling the vehicle speaker system to emit sound based on the current audio parameter, the second determination module 300 is further configured to:

[0099] The current audio parameters are displayed on the vehicle display screen so that the current user can refer to the specific values ​​corresponding to the current audio parameters.

[0100] It should be noted that the above explanation of the embodiment of the sound adjustment method of the adaptive vehicle audio device is also applicable to the sound adjustment device of the adaptive vehicle audio device of this embodiment, and will not be repeated here.

[0101] According to the sound adjustment device of the adaptive in-vehicle audio device proposed in the embodiment of the present application, by acquiring the facial image of the current user, the facial image can be analyzed using the preset face gender-age recognition model to determine the gender and age of the current user; based on the gender and age of the current user, the current audio parameters are determined using the preset gender-age-hearing frequency matching model, and the sound of the in-vehicle speaker system is controlled based on the current audio parameters. Thus, by automatically adjusting the audio parameters according to the gender and age of the occupants of the vehicle, the problem that the existing technology is not convenient enough to manually adjust the audio settings, and cannot perform adaptive adjustments according to the gender, age and hearing characteristics of the occupants of the vehicle is solved, so as to enhance the personalization and intelligence of the in-vehicle audio experience.

[0102] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0103] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0104] When the processor 502 executes the program, the sound adjustment method of the adaptive vehicle audio device provided in the above embodiment is implemented.

[0105] Furthermore, the vehicle also includes:

[0106] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0107] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0108] The memory 501 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0109] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0110] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0111] The processor 502 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0112] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the sound adjustment method of the adaptive vehicle audio device as described above.

[0113] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0114] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0115] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for adjusting the sound of an adaptive vehicle audio device, characterized in that: The following steps are involved: Get the current user's facial image; Analyze the facial image using a preset face gender-age recognition model to determine the gender and age of the current user; Based on the gender and age of the current user, a preset gender-age-hearing frequency matching model is used to determine the current audio parameters, and the vehicle speaker system is controlled to produce sound based on the current audio parameters.

2. The method according to claim 1, characterized in that The controlling the vehicle speaker system to emit sound based on the current audio parameter comprises: generating a corresponding audio signal based on the current audio parameters; The audio signal is sent to a power amplifier to obtain an enhanced audio signal, and the enhanced audio signal is transmitted to the vehicle speaker system to drive the vehicle speaker system to produce sound.

3. The method according to claim 1, characterized in that Before analyzing the facial image using the preset face gender-age recognition model to determine the gender and age of the current user, the method further includes: Get a dataset of facial images with gender and age annotated. Preprocessing the face image dataset to obtain a preprocessed face image dataset; Using a feature extractor to perform feature extraction on the preprocessed face image data set to obtain a face feature set, and dividing the face feature set into a first training set and a first validation set; The first preset neural network is trained using the first training set to obtain a first initial neural network model, and the first verification set is used to verify the first initial neural network model until the first initial neural network model meets a first preset condition, and the iterative training of the first preset neural network is terminated to obtain the preset face gender-age recognition model, otherwise the iterative training is continued after adjusting the hyperparameters.

4. The method according to claim 1, characterized in that: Before determining the current audio parameter based on the gender and age of the current user by using the preset gender-age-hearing frequency matching model, the method further includes: Acquire standard hearing test data of different genders and age groups, wherein the standard hearing test data is a correspondence between the different genders and age groups and audio parameters; Preprocessing the standard hearing test data, and dividing the preprocessed standard hearing test data into a second training set and a second validation set; Based on the gender-age-hearing frequency sensitivity theory, the second preset neural network is trained using the second training set to obtain a second initial neural network model, and the second verification set is used to verify the second initial neural network model until the second initial neural network model meets the second preset condition, and the iterative training of the second preset neural network is terminated to obtain the preset face gender-age recognition model, otherwise the iterative training continues after adjusting the hyperparameters.

5. The method according to claim 4, characterized in that The audio parameters include frequency, pitch and loudness.

6. The method according to claim 1, characterized in that After controlling the vehicle-mounted speaker system to emit sound based on the current audio parameter, the method further includes: The current audio parameter is displayed on a vehicle display screen so that the current user can view the specific value corresponding to the current audio parameter.

7. A sound adjustment device for an adaptive vehicle audio device, characterized in that: include: An acquisition module is used to acquire the facial image of the current user; A first determination module is used to analyze the facial image using a preset face gender-age recognition model to determine the gender and age of the current user; The second determination module is used to determine the current audio parameters based on the gender and age of the current user and using a preset gender-age-hearing frequency matching model, and control the vehicle speaker system to produce sound based on the current audio parameters.

8. The device according to claim 7, characterized in that The second determining module is specifically used to: generating a corresponding audio signal based on the current audio parameters; The audio signal is sent to a power amplifier to obtain an enhanced audio signal, and the enhanced audio signal is transmitted to the vehicle speaker system to drive the vehicle speaker system to produce sound.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the sound adjustment method for an adaptive in-vehicle audio device as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the sound adjustment method of an adaptive in-vehicle audio device as described in any one of claims 1 to 6.

Images