Vehicle-mounted sound effect automatic adjustment method, device and equipment and readable storage medium

Abstract

The invention discloses a vehicle-mounted sound effect automatic adjustment method, device and equipment and a readable storage medium, and relates to the technical field of sound field adjustment, and the vehicle-mounted sound effect automatic adjustment method comprises the steps: dynamically obtaining a user ear position of a passenger in a vehicle, and determining a target position distance between the user ear position and a vehicle-mounted sound system; inputting the target position distance into a convergent sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; obtaining an initial audio parameter of the current to-be-played audio, and performing compensation adjustment on the initial audio parameter according to the target audio parameter gain value to obtain a target audio parameter; and dynamically controlling the vehicle-mounted sound equipment to play according to the target audio parameters. According to the method and the device, the vehicle-mounted sound system can be automatically and adaptively adjusted, so that passengers can enjoy the adjusted sound field and sound effect in each riding scene.

Description

Technical Field

[0001] The present application relates to the technical field of sound field adjustment, and in particular to a method, device, equipment and readable storage medium for automatic adjustment of vehicle-mounted sound effects. Background Art

[0002] As more and more cars enter ordinary families, the use of cars becomes more and more frequent, and cars are becoming more intelligent and humanized. As an essential entertainment device for cars, the sound effects of car audio directly affect the driving experience. For passengers in different positions, different sound effect modes are often required to achieve the best effect. At present, different sound effect modes have been formed for passengers in different seats through special optimization of sound effects (such as frequency response, phase, delay, etc.), such as driver sound effect mode, front row sound effect mode, rear row sound effect mode or whole car sound effect mode, etc. Each sound effect mode will optimize the sound effect heard by the corresponding passengers, and may reduce the sound effect in other positions.

[0003] However, for traditional car audio systems, users can only manually adjust different sound modes, such as obtaining the desired sound mode through multi-level menu operations. Especially when driving a vehicle, there are certain safety risks if multi-level menus are operated.

[0004] Therefore, how to automatically and adaptively adjust the car audio system so that passengers can enjoy the well-tuned sound field and sound effects every time they ride. Summary of the invention

[0005] The main purpose of this application is to provide a method, device, equipment and readable storage medium for automatic adjustment of vehicle-mounted sound effects, aiming to solve the technical problem of how to automatically and adaptively adjust the vehicle-mounted audio system so that passengers can enjoy the calibrated sound field and sound effects every time they ride.

[0006] To achieve the above objectives, the present application provides a method for automatically adjusting vehicle-mounted sound effects, comprising: Dynamically obtain the position of the user's ear of the vehicle occupant, and determine the target position distance between the user's ear position and the vehicle audio system; Inputting the target position distance into a converged sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; Acquire initial audio parameters of the audio to be played currently, and perform compensation adjustment on the initial audio parameters according to the target audio parameter gain value to obtain target audio parameters; The vehicle audio system is dynamically controlled to play the target audio parameters.

[0007] Optionally, the method further comprises: Acquire optimal audio parameter information pre-calibrated based on optimal sound effects for multiple seating positions in the vehicle, and determine the optimal audio parameter information corresponding to each position distance according to the position distance corresponding to each seating position and the vehicle audio system; Calculate the difference between each of the optimal audio parameter information and the initial audio parameter to obtain the audio parameter gain value corresponding to each of the position distances; Using each of the position distances as a learning sample, and using the audio parameter gain value corresponding to each of the position distances as a sample label associated with the learning sample; According to the learning samples and the sample labels associated with the learning samples, supervised learning is performed on the preset sound effect configuration neural network model to obtain a converged sound effect configuration neural network model.

[0008] Optionally, the step of performing supervised learning on the sound effect configuration neural network model according to the learning samples and the sample labels to obtain a converged sound effect configuration neural network model comprises: Dividing the learning sample into a training sample and a verification sample; Training a preset sound effect configuration neural network model through the training samples and sample labels associated with the training samples; The prediction accuracy of the preset sound effect configuration neural network model is verified through the verification samples and the sample labels associated with the verification samples, and the training is stopped until the prediction accuracy reaches a preset ratio threshold to obtain a converged sound effect configuration neural network model.

[0009] Optionally, the step of compensating and adjusting the initial audio parameter according to the target audio parameter gain value includes: Determining a target phase gain value and a target amplitude gain value according to the target audio parameter gain value; According to the target phase gain value, the audio phase of the initial audio parameter is compensated and adjusted, and according to the target amplitude gain value, the audio amplitude of the initial audio parameter is compensated and adjusted.

[0010] Optionally, the step of dynamically acquiring the ear position of the vehicle occupant includes: Dynamically identify the user's sitting position information in the car through a camera and / or seat sensor; Obtaining physical characteristic information corresponding to the registration input of each seat, wherein the physical characteristic information includes height and body proportion; The ear position of the user of the vehicle occupant is determined according to the body feature information and the seating position information.

[0011] Optionally, the step of determining the in-vehicle occupant information according to the physical feature information and the seating position information includes: Detecting seat adjustment information corresponding to each seat in the vehicle, wherein the seat adjustment information includes a seat back angle and a seat height; The ear position of a user of an occupant in the vehicle is determined according to the seat adjustment information, the body characteristic information and the sitting position information.

[0012] Optionally, after the step of dynamically identifying the user's seating position information in the vehicle, the method further comprises: Determining whether there are multiple passengers in the vehicle based on the seating position information; If there are multiple passengers in the vehicle, the sound effect mode mapped to the seating position information is called from a pre-stored sound effect mode mapping table according to the seating position information; the called sound effect mode is used as a target sound effect mode, and the vehicle audio system is controlled to play in the target sound effect mode, wherein the target sound effect mode is a front row sound effect mode, a rear row sound effect mode or a whole vehicle sound effect mode; If the number of passengers in the vehicle is one, execute: the step of obtaining the physical feature information corresponding to the registered input of each seat.

[0013] In addition, the present application also provides a vehicle-mounted sound effect automatic adjustment device, comprising: An acquisition module, used to dynamically acquire the position of a user's ear of an occupant in the vehicle and determine a target position distance between the user's ear position and the vehicle audio system; A prediction module, used for inputting the target position distance into a converged sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; A compensation module, used for obtaining initial audio parameters of the audio to be played currently, and performing compensation adjustment on the initial audio parameters according to the target audio parameter gain value to obtain target audio parameters; The control module is used to dynamically control the vehicle audio system to play the target audio parameters.

[0014] The present application also provides an automatic vehicle sound effect adjustment device, which is a physical device, and includes: a memory, a processor, and a program of the automatic vehicle sound effect adjustment method stored in the memory and executable on the processor. When the program of the automatic vehicle sound effect adjustment method is executed by the processor, the steps of the automatic vehicle sound effect adjustment method as described above can be implemented.

[0015] The present application also provides a readable storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores a program for implementing a method for automatically adjusting vehicle-mounted sound effects. The program for implementing a method for automatically adjusting vehicle-mounted sound effects is executed by a processor to implement the steps of the method for automatically adjusting vehicle-mounted sound effects as described above.

[0016] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for automatically adjusting vehicle sound effects.

[0017] The technical solution of the present application is to dynamically obtain the user ear position of the occupant in the car, determine the target position distance between the user ear position and the car audio, then input the target position distance into the converged sound effect configuration neural network model, output the target audio parameter gain value corresponding to the target position distance, obtain the initial audio parameters of the current audio to be played, compensate and adjust the initial audio parameters according to the target audio parameter gain value, obtain the target audio parameters, and then dynamically control the car audio to play with the target audio parameters, so as to judge the situation of the passengers through the sensing sensor, control the car audio to switch different audio playback parameters, and thus improve the effect of the car audio playback. That is, in each riding scene, no matter how the user's riding position changes, the car audio can be automatically and adaptively adjusted, so that passengers can enjoy the adjusted sound field and sound effects in each riding scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 This is a flow chart of the first embodiment of the method for automatically adjusting vehicle sound effects of the present application; Figure 2 This is a flow chart of a second embodiment of the method for automatically adjusting vehicle audio effects of the present application; Figure 3 A flowchart of a sound effect adjustment algorithm according to a specific embodiment of the present application; Figure 4 This is a schematic diagram of the module structure of the vehicle-mounted automatic sound effect adjustment device according to an embodiment of the present application; Figure 5Schematic diagram of the device structure of the hardware operating environment involved in the vehicle-mounted sound effect automatic adjustment device in this embodiment.

[0021] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0023] Embodiment 1 For traditional car audio systems, users can only manually adjust different sound modes, such as obtaining the desired sound mode through multi-level menu operations. Especially when driving a vehicle, there are certain safety risks if multi-level menu operations are performed.

[0024] Therefore, how to automatically and adaptively adjust the car audio system so that passengers can enjoy the well-tuned sound field and sound effects every time they ride.

[0025] Based on this, the present application embodiment provides a method for automatically adjusting the vehicle sound effects. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for automatically adjusting the vehicle audio effect of the present application, including: Step S10, dynamically obtaining the position of the user's ear of the vehicle occupant, and determining the target position distance between the user's ear position and the vehicle audio system; The ear position of the vehicle occupant may be identified through images or videos dynamically acquired by the vehicle-mounted camera and / or load-bearing information acquired by the seat sensor.

[0026] Step S20, inputting the target position distance into a converged sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; Step S30, obtaining initial audio parameters of the audio to be played currently, and performing compensation adjustment on the initial audio parameters according to the target audio parameter gain value to obtain target audio parameters; It is known to those skilled in the art that the propagation of sound will cause the attenuation of the sound signal as the distance increases. That is, when other factors are the same (single variable), the longer the sound propagation distance, the greater the sound effect parameter loss value. Therefore, the greater the distance to the target position, the greater the gain value of the target audio parameter.

[0027] It is easy to understand that since the position of the car audio is fixed, different user ear positions often result in different relative spatial distances between the user and the car audio, as well as different sound pickup angles between the user's ear and the car audio. Therefore, different user ear positions often require corresponding different target audio parameter gain values.

[0028] Because in different riding scenarios, the distance and orientation of the fixed-position car audio relative to the ear positions of different users are different. That is, the same sound source (i.e., the audio played by the same car audio) has different position distances relative to the ear positions of different users. For example, the farther the user's ear position is from the sound source, the more incomplete the information of the target audio picked up by the ear, and the worse the sound effect heard by the user. Therefore, this embodiment dynamically obtains the user's ear position of the occupant in the car, and determines the target position distance between the user's ear position and the car audio, inputs the target position distance into the converged sound effect configuration neural network model, outputs the target audio parameter gain value corresponding to the target position distance, and then obtains the initial audio parameters of the current audio to be played, and compensates and adjusts the initial audio parameters according to the target audio parameter gain value to obtain the target audio parameters, thereby restoring the target audio as much as possible, and avoiding the attenuation of the audio signal of the target audio to the greatest extent to affect the user's sound effect experience of the target audio.

[0029] The target audio parameter gain value includes a target audio phase gain value and a target audio amplitude gain value.

[0030] Exemplarily, the step of compensating and adjusting the initial audio parameter according to the target audio parameter gain value includes: Step A10, determining a target phase gain value and a target amplitude gain value according to the target audio parameter gain value; Step A20: compensating and adjusting the audio phase of the initial audio parameter according to the target phase gain value, and compensating and adjusting the audio amplitude of the initial audio parameter according to the target amplitude gain value.

[0031] It is known that when the audio parameters of the car audio remain unchanged, if the user's ear position is different, the sound effect heard by the user is also different. In this embodiment, when the user's ear position changes, since the position of the car audio is fixed, that is, the position of the car audio is known in advance (for example, stored in the vehicle system), the target position distance between the user's ear position and the car audio can be calculated according to the position of the user's ear and the position of the car audio, and then the target position distance is input into the converged sound effect configuration neural network model, and the target audio parameter gain value corresponding to the target position distance is output, and the initial audio parameters of the current audio to be played are obtained, and the initial audio parameters are compensated and adjusted according to the target audio parameter gain value to obtain the target audio parameters. Among them, the compensation adjustment degree of the audio parameter can be based on the current sound effect of the current audio received by the current user's ear position reaching the same best sound effect. Specifically, when a user of standard height is located in a fixed position with a standard sitting posture, the user's ear can receive the preset sound effect of the current audio, wherein the preset sound effect can be a sound effect that is pre-adjusted to achieve the best auditory enjoyment. It can also be understood that when the distance and angle between the user's ear and the car audio are the preset distance and preset angle, the current sound effect of the current audio played from the car audio with the preset audio parameters received by the human ear is the preset sound effect. In this embodiment, when the position of the user's ear of the occupant in the car changes, the distance and angle between the human ear and the car audio change. At this time, the target position distance between the user's ear position and the car audio can be calculated, and then the calibrated position distance is input into the converged sound effect configuration neural network model, and the target audio parameter gain value corresponding to the target position distance is output. By calibrating the target audio parameter gain values ​​required when multiple different user ear positions reach the preset sound effect, it is convenient for the user's ear position to dynamically change, and the current sound effect of the current audio played from the car audio can be received as the preset sound effect, so that the user can continue to enjoy the adjusted sound field and sound effect no matter how the user's ear position moves.

[0032] After step S30, step S40 is executed to dynamically control the vehicle audio system to play the target audio parameters.

[0033] The technical solution of the embodiment of the present application is to dynamically obtain the user ear position of the occupant in the car, determine the target position distance between the user ear position and the car audio, then input the target position distance into the converged sound effect configuration neural network model, output the target audio parameter gain value corresponding to the target position distance, obtain the initial audio parameters of the current audio to be played, compensate and adjust the initial audio parameters according to the target audio parameter gain value, obtain the target audio parameters, and then dynamically control the car audio to play with the target audio parameters, so as to judge the situation of the passengers through the sensing sensor, control the car audio to switch different audio playback parameters, and thus improve the effect of the car audio playback. That is, in each riding scene, no matter how the user's riding position changes, the car audio can be automatically and adaptively adjusted, so that passengers can enjoy the adjusted sound field and sound effects in each riding scene.

[0034] It is worth mentioning that the key protection points of the embodiment of the present application also include debugging the best sound effect at a preset ear position in the car only once, which can be combined with the pre-converged sound effect configuration neural network model to obtain the audio parameters of the best sound effect at the ear positions of all users in the car, avoiding the need to debug the sound effect at each different user ear position in the car, saving time and effort. However, if the method of debugging once at each position is adopted, the number of parameter groups is related to the number of debugging positions, so that the user can only experience the optimal sound effect at the debugging position (that is, the user's ear is at the preset ear position during the above debugging). The technical solution of the embodiment of the present application calculates the target position distance between the user's ear position and the car audio, and then inputs the target position distance into the converged sound effect configuration neural network model, and outputs the target audio parameter gain value corresponding to the target position distance, so as to calibrate the target audio parameter gain values ​​required for achieving the preset sound effect at multiple different user ear positions, and obtain the initial audio parameters of the audio to be played, and compensate and adjust the initial audio parameters according to the target audio parameter gain value to obtain the target audio parameters, and then control the car audio to play with the target audio parameters, so that the user can predict the optimal sound effect parameters in real time through the neural network at any sitting position, bringing the best audio experience to the user.

[0035] In a possible implementation, the method further includes: Step B10, obtaining optimal audio parameter information pre-calibrated based on optimal sound effects for multiple seating positions in the vehicle, and determining the optimal audio parameter information corresponding to each position distance according to the position distance corresponding to each seating position and the vehicle audio system; Step B20, performing difference calculation between each of the optimal audio parameter information and the initial audio parameter to obtain an audio parameter gain value corresponding to each of the position distances; Step B30, taking each of the position distances as a learning sample, and taking the audio parameter gain value corresponding to each of the position distances as a sample label associated with the learning sample; Step B40, performing supervised learning on a preset sound effect configuration neural network model based on the learning samples and the sample labels associated with the learning samples to obtain a converged sound effect configuration neural network model.

[0036] Exemplarily, the step of performing supervised learning on the sound effect configuration neural network model according to the learning sample and the sample label to obtain a converged sound effect configuration neural network model includes: Step C10, dividing the learning sample into a training sample and a verification sample; Step C20, training a preset sound effect configuration neural network model using the training samples and sample labels associated with the training samples; Step C30, verifying the prediction accuracy of the preset sound effect configuration neural network model through the verification sample and the sample label associated with the verification sample, and stopping training until the prediction accuracy reaches a preset ratio threshold to obtain a converged sound effect configuration neural network model.

[0037] This embodiment obtains the best audio parameter information pre-calibrated based on the best sound effect for multiple seating positions in the car, and determines the best audio parameter information corresponding to each position distance according to the position distance corresponding to each seating position and the vehicle audio system, and then calculates the difference between each best audio parameter information and the initial audio parameter to obtain the audio parameter gain value corresponding to each position distance, and uses each position distance as a learning sample, and uses the audio parameter gain value corresponding to each position distance as a sample label associated with the learning sample, and then based on the learning sample and the sample label associated with the learning sample, supervised learning is performed on the preset sound effect configuration neural network model, so as to accurately obtain a converged sound effect configuration neural network model, and then facilitates the subsequent prediction of the target audio parameter gain value corresponding to the target position distance based on the converged sound effect configuration neural network model, so as to achieve accurate calibration of the target audio parameter gain value required for achieving the preset sound effect at multiple different user ear positions.

[0038] Embodiment 2 Based on the first embodiment of the present application, in another embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The step of dynamically obtaining the ear position of the vehicle occupant comprises: Step S11, dynamically identifying the user's sitting position information in the car through a camera and / or a seat sensor; In this embodiment, the sitting position information of the user in the vehicle can be identified through images or videos obtained by the vehicle-mounted camera and / or load-bearing information obtained by the seat sensor.

[0039] In one embodiment, the seat sensor may be a gravity sensor (or a pressure sensor), and the seating position information may be obtained by analyzing the load-bearing information obtained by the seat sensor. For example, if the weight information obtained by the seat sensor on the front passenger seat is 50 kg, it is determined that there is a user on the front passenger seat, and the front passenger seat is used as the user's seating position.

[0040] In another embodiment, the seat sensor may be an infrared sensor, which detects the physical volume of the seat and detects whether there is a human body on the seat based on whether the physical volume of the seat is greater than a preset volume threshold, thereby identifying the user's sitting position information in the car.

[0041] In yet another embodiment, the seat sensor may be an inductive sensor for detecting whether a seat belt is buckled. By detecting whether the seat belt on the seat is fastened, it is determined whether there is a human body on the seat, thereby identifying the user's sitting position information in the car.

[0042] Step S12, obtaining the physical characteristic information corresponding to the registration input of each seat, wherein the physical characteristic information includes height and body proportion; Step S13, determining the ear position of the user of the vehicle occupant according to the body feature information and the seating position information.

[0043] In one example, when the camera and / or seat sensor recognizes that there is a human body in the current seat, a preset guidance interface can be output to guide the user to input body feature information. The user can input his or her own body feature information, such as height and body proportions, based on the preset guidance interface, so as to facilitate the subsequent accurate determination of the user's ear position of the occupant in the car based on the body feature information and the seat position of the user in the car (i.e., the sitting position information).

[0044] In another example, since the driver often sits in the driver's seat, the boss usually sits in the right rear seat, or the wife usually sits in the front passenger seat, that is, a specific seat position is usually occupied by a fixed person. For this riding scenario, the physical feature information of the regular seater can be registered and input for each seat of the vehicle in advance. Each subsequent time the user sits in the specific seat, there is no need to register again. The ear position of the user can be directly identified based on the pre-registered physical feature information and the specific seat position of the user.

[0045] Since different people have different heights and body proportions, the ear positions of different people sitting on the same vehicle seat are often different. Therefore, identifying the ear position of a user in the vehicle based solely on the user's sitting position information (i.e., which seat the user is sitting in) is often not accurate enough.

[0046] Based on this, this embodiment uses a camera and / or seat sensor to identify the user's sitting position information in the car, and obtains the physical feature information registered and input corresponding to each seat, where the physical feature information includes height and body proportions. Then, based on the physical feature information and sitting position information, the user's ear position of the occupant in the car is accurately identified, which facilitates the subsequent accurate determination of the target audio parameters of the car audio system based on the identified user's ear position, so that passengers can enjoy the calibrated sound field and sound effects in every riding scenario.

[0047] In a possible implementation manner, the step of determining the in-vehicle occupant information according to the physical feature information and the seating position information includes: Step D10, detecting seat adjustment information corresponding to each seat in the vehicle, wherein the seat adjustment information includes a seat back angle and a seat height; Step D20, determining the ear position of the user of the vehicle occupant based on the seat adjustment information, the body feature information and the sitting position information.

[0048] Even if the same person sits on the same vehicle seat, the ear position will be different due to different sitting postures. Based on this, this embodiment detects the seat adjustment information corresponding to each seat in the vehicle, wherein the seat adjustment information includes the seat back angle and the seat height, and determines the sitting posture of the user on the current seat according to the seat adjustment information, such as whether the user is sitting upright, lying flat or sitting diagonally (when the sitting posture is diagonally sitting, the angle information of the diagonal sitting is also determined by the seat adjustment information), etc., so as to facilitate the identification of the ear position of the user in the vehicle based on the user's sitting position information and body feature information, and in combination with the detection of the user's sitting posture, and further improve the accuracy of identifying the user's ear position.

[0049] Since the above embodiments are all aimed at improving the audio experience of a single target user in the car cabin, that is, since the above embodiments are only applicable to the single-person sound effect mode, when faced with the scenario where the audio experience of multiple target users in the car cabin needs to be satisfied at the same time, the above embodiments are no longer well applicable to the multi-person sound effect mode.

[0050] Based on this, the present application also provides a possible implementation manner, after the step of dynamically identifying the user's sitting position information in the vehicle, the method further includes: Step E10, determining whether there are multiple passengers in the vehicle according to the seating position information; Step E20, if there are multiple passengers in the vehicle, then according to the seating position information, call the sound effect mode mapped to the seating position information from a pre-stored sound effect mode mapping table; use the called sound effect mode as the target sound effect mode, and control the vehicle audio system to play in the target sound effect mode, wherein the target sound effect mode is the front row sound effect mode, the rear row sound effect mode, or the whole vehicle sound effect mode; Step E30, if the number of passengers in the vehicle is one, execute: the step of obtaining the physical feature information corresponding to the registered input of each seat.

[0051] In this embodiment, when it is detected that there is only one passenger in the vehicle, the single-person sound effect mode is turned on and the step of obtaining the physical characteristic information registered and inputted corresponding to each seat is executed. When it is detected that there are multiple passengers in the vehicle, for example, when there are passengers in both the front-pilot seat and the main driver's seat, the sound effect mode mapped by the seating position information is called the front-row sound effect mode. At this time, the calibrated best sound effect position for the human ear corresponding to the front-row sound effect mode can be the middle position of the front row, so that the front-row passengers can enjoy the best adjusted sound field and sound effects as much as possible. When it is detected that there are passengers in the back-row seats, the calibrated best sound effect position for the human ear corresponding to the back-row sound effect mode can be the middle position of the back row, so that the back-row passengers can enjoy the best adjusted sound field and sound effects as much as possible. Alternatively, when it is detected that there are passengers in all the seats of the vehicle, the calibrated best sound effect position for the human ear corresponding to the full-vehicle sound effect mode can be the center of the cabin, so that all the passengers in the vehicle can enjoy the best adjusted sound field and sound effects as much as possible. In this embodiment, when it is determined that there are multiple passengers in the vehicle, based on the seating position information, the sound effect mode mapped to the seating position information is called from a pre-stored sound effect mode mapping table, the called sound effect mode is used as the target sound effect mode, and the vehicle audio is controlled to play with the target sound effect mode, wherein the target sound effect mode is the front row sound effect mode, the rear row sound effect mode or the whole vehicle sound effect mode, thereby satisfying the audio experience of multiple target users in the vehicle cabin at the same time. In each riding scenario, no matter how the seating positions of multiple users in the vehicle change, the vehicle audio can be automatically and adaptively adjusted, and the playback device can be controlled to switch to different sound effect modes, so that each passenger can enjoy the well-tuned sound field and sound effects in each riding scenario.

[0052] In order to help understand the technical concept of this application, a specific embodiment is listed, please refer to Figure 3 , Figure 3 : is a flowchart of a sound effect adjustment algorithm of a specific embodiment of the present application. This specific embodiment details the steps of the sound effect adjustment scheme for different spatial positions, wherein: Step 1, obtaining the user's ear position (i.e. the user's ear position); Methods for obtaining ear positions include but are not limited to the following two methods.

[0053] Method 1: Collect data through the in-car camera, use the outside-in image processing method, and calculate and identify the position of the human ear through the car computer. This method can calculate both the static position data and the dynamic position data of the human ear.

[0054] Method 2: The seat status (including seat height, front and rear position, backrest angle, etc.) can be obtained through the vehicle computer, and combined with the user's physical characteristics (height and body proportions), the static position data of the human ear can be calculated. The head movement data of the user wearing the glasses can be obtained through the IMU of the AR glasses.

[0055] Step 2, optimal sound effect position deviation identification; Optimal sound position: When assembling and adjusting the sound effects, manufacturers will use sensors to obtain sound signals from a certain position in the car, and then analyze and optimize the sound effects of the car audio.

[0056] Based on the movement trajectory of the user's head, mainly the ear position, over time, it is determined whether the user has seriously deviated from the optimal sound effect position. If so, it is considered that the sound effect parameters need to be adjusted according to the user's current position; Step 3: Adjust the sound parameters (i.e. the audio parameters of the car audio).

[0057] Factors that affect sound effects include the cabin structure (doors, ceilings, seats, etc.), materials, and distances from each speaker. Therefore, the acquisition of sound effect parameters needs to be based on acoustic simulation or a large number of tests. Sound effect parameters include loudness and phase, etc.

[0058] Methods for adjusting sound effect parameters include but are not limited to the following two methods.

[0059] Method 1: For the adjustment of multi-position sound effect parameters, a mapping relationship is established between the sound effect parameters and different human ear listening positions (i.e., the user's human ear position), and stored in the storage device of the vehicle computer. Through the detection and judgment in steps 1 and 2, the user's current ear listening position is output, and the stored sound effect parameters are applied.

[0060] Method 2: Establish a neural network of the distance from each speaker and the gain value of each speaker. By detecting the position of the human ear in real time, calculate the distance from the human ear to the speaker based on spatial geometry, and use this as the input of the neural network. The network finally outputs the gain value of each frequency band to achieve dynamic adjustment.

[0061] It should be noted that the many details described in this specific embodiment are only helpful for understanding the technical concept of the present application and do not constitute a limitation of the present application. More simple transformations based on the technical concept of the present application should all be within the scope of protection of the present application.

[0062] In order to further help understand the technical concept of the present application, specific embodiment 2 is listed. This specific embodiment is for adapting the sound effect algorithm for users in different positions. It is different from the operation of specific embodiment 1 in that it is necessary to identify the main listening user. The main listening user means that when there are multiple passengers in the cabin, in order to ensure the best sound effect for the user in a certain position, it is necessary to first confirm their seat position and then select different sound effect parameters.

[0063] Methods for identifying user behavior include but are not limited to the following two: Method 1: Acquisition of seat pressure sensors. The pressure sensor data on different seats can be obtained through the vehicle computer. When the pressure sensor data on the seat reaches the threshold, it is considered that there is a customer at that position.

[0064] Method 2: Seat belt detection and acquisition: The use of seat belts on different seats is obtained through the vehicle computer to determine whether there are passengers.

[0065] Method 3: Obtaining the signal strength in the car machine Bluetooth network. When users in different seats are wearing AR glasses, and each AR device is connected to the car machine's Bluetooth network, the car machine is the master device, and all connected AR devices are slave devices. By detecting the Bluetooth signal strength of the AR device, the user's seat position is determined.

[0066] After the user is identified by the above method, the sound effect is adjusted according to the sound effect adaptation method in the specific embodiment 1.

[0067] Of course, this specific embodiment can also adapt the sound effect algorithm for multiple users. The above two specific embodiments are the best adaptation solutions for a single user. The purpose of this embodiment is to select the best sound effect for multiple users. Since the sound effect adjustment parameters for the front row users may have poor sound effects for the rear edge passengers, in order to balance the listening experience of multiple users, the sound effect parameters of the sound system need to be adjusted.

[0068] It should be noted that the many details described in the second specific embodiment are only helpful for understanding the technical concept of the present application and do not constitute a limitation of the present application. More simple transformations based on the technical concept of the present application should all be within the scope of protection of the present application.

[0069] Embodiment 3 The embodiment of the present invention also provides a vehicle-mounted sound effect automatic adjustment device, please refer to Figure 4 , the vehicle-mounted sound effect automatic adjustment device comprises: The acquisition module 10 is used to dynamically acquire the position of the user's ear of the vehicle occupant and determine the target position distance between the user's ear position and the vehicle audio system; A prediction module 20, configured to input the target position distance into a converged sound effect configuration neural network model, and output a target audio parameter gain value corresponding to the target position distance; The compensation module 30 is used to obtain the initial audio parameters of the audio to be played currently, and to compensate and adjust the initial audio parameters according to the target audio parameter gain value to obtain the target audio parameters; The control module 40 is used to dynamically control the vehicle audio system to play the target audio parameters.

[0070] The vehicle-mounted sound effect automatic adjustment device provided in the embodiment of the present invention adopts the vehicle-mounted sound effect automatic adjustment method in the above-mentioned embodiment 1 or embodiment 2, which can solve the technical problem of how to automatically and adaptively adjust the vehicle-mounted audio system, so that passengers can enjoy the adjusted sound field and sound effects every time in the riding scene. Compared with the prior art, the beneficial effects of the vehicle-mounted sound effect automatic adjustment device provided in the embodiment of the present invention are the same as the beneficial effects of the vehicle-mounted sound effect automatic adjustment method provided in the above-mentioned embodiment, and the other technical features of the vehicle-mounted sound effect automatic adjustment device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0071] Embodiment 4 An embodiment of the present invention provides an automatic vehicle sound effect adjustment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the automatic vehicle sound effect adjustment method in the above-mentioned embodiment one.

[0072] Reference below Figure 5 , which shows a schematic diagram of the structure of a vehicle-mounted sound effect automatic adjustment device suitable for implementing the embodiment of the present disclosure. The vehicle-mounted sound effect automatic adjustment device in the embodiment of the present disclosure includes but is not limited to mixed reality (MixedReality) - MR devices (such as MR glasses or MR helmets), augmented reality (AugmentedReality) - AR devices (such as AR glasses or AR helmets), extended reality (ExtendedReality) - XR devices or some combination thereof, etc. near-eye display devices. Figure 5 The vehicle-mounted sound effect automatic adjustment device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0073] like Figure 5As shown, the vehicle-mounted sound effect automatic adjustment device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM1002) or a program loaded from a storage device into a random access memory (RAM1004). Various programs and data required for the operation of the vehicle-mounted sound effect automatic adjustment device are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface is also connected to the bus 1005.

[0074] Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the vehicle-mounted sound effect automatic adjustment device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a vehicle-mounted sound effect automatic adjustment device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0075] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0076] The vehicle-mounted sound effect automatic adjustment device provided by the present invention adopts the vehicle-mounted sound effect automatic adjustment method in the above embodiment, which can solve the technical problem of how to automatically and adaptively adjust the vehicle-mounted audio system, so that passengers can enjoy the adjusted sound field and sound effects every time in the vehicle riding scene. Compared with the prior art, the beneficial effects of the vehicle-mounted sound effect automatic adjustment device provided by the embodiment of the present invention are the same as the beneficial effects of the vehicle-mounted sound effect automatic adjustment method provided by the above embodiment, and the other technical features of the vehicle-mounted sound effect automatic adjustment device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0077] It should be understood that the various parts of the present disclosure can be implemented with hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0078] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0079] Embodiment 5 An embodiment of the present invention provides a computer-readable storage medium having computer-readable program instructions stored thereon, and the computer-readable program instructions are used to execute the method for automatically adjusting the vehicle-mounted sound effects in the above embodiment.

[0080] The computer-readable storage medium provided in the embodiment of the present invention may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0081] The computer-readable storage medium may be included in the vehicle-mounted automatic sound effect adjustment device; or may exist independently without being assembled into the vehicle-mounted automatic sound effect adjustment device.

[0082] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the vehicle-mounted sound effect automatic adjustment device, the vehicle-mounted sound effect automatic adjustment device: dynamically obtains the user ear position of the vehicle occupant, and determines the target position distance between the user ear position and the vehicle-mounted audio system; inputs the target position distance into a converged sound effect configuration neural network model, and outputs a target audio parameter gain value corresponding to the target position distance; obtains the initial audio parameters of the audio to be played, and compensates and adjusts the initial audio parameters according to the target audio parameter gain value to obtain the target audio parameters; and dynamically controls the vehicle-mounted audio system to play with the target audio parameters.

[0083] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0084] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0085] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of the module does not limit the unit itself in some cases.

[0086] The computer-readable storage medium provided by the present invention stores computer-readable program instructions for executing the above-mentioned method for automatically adjusting the vehicle-mounted sound effects, which can solve the technical problem of how to automatically and adaptively adjust the vehicle-mounted audio system, so that passengers can enjoy the adjusted sound field and sound effects every time they are in a vehicle. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the embodiment of the present invention are the same as the beneficial effects of the method for automatically adjusting the vehicle-mounted sound effects provided in the above-mentioned embodiment 1 or embodiment 2, and will not be described in detail here.

[0087] Embodiment 6 An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for automatically adjusting vehicle-mounted sound effects.

[0088] The computer program product provided by the present application can solve the technical problem of how to automatically and adaptively adjust the vehicle audio system, so that passengers can enjoy the adjusted sound field and sound effects every time they are in the vehicle. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the present invention are the same as the beneficial effects of the vehicle audio automatic adjustment method provided by the above-mentioned embodiment 1 or embodiment 2, and will not be described in detail here.

[0089] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A method for automatically adjusting vehicle sound effects, It is characterized in that include: Dynamically obtain the position of the user's ear of the vehicle occupant, and determine the target position distance between the user's ear position and the vehicle audio system; Inputting the target position distance into a converged sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; Acquire initial audio parameters of the audio to be played currently, and perform compensation adjustment on the initial audio parameters according to the target audio parameter gain value to obtain target audio parameters; The vehicle audio system is dynamically controlled to play the target audio parameters.

2. The method for automatically adjusting vehicle sound effects as claimed in claim 1, It is characterized in that The method further comprises: Acquire optimal audio parameter information pre-calibrated based on optimal sound effects for multiple seating positions in the vehicle, and determine the optimal audio parameter information corresponding to each of the position distances according to the position distances corresponding to each of the seating positions and the vehicle audio system; Calculate the difference between each of the optimal audio parameter information and the initial audio parameter to obtain the audio parameter gain value corresponding to each of the position distances; Using each of the position distances as a learning sample, and using the audio parameter gain value corresponding to each of the position distances as a sample label associated with the learning sample; According to the learning samples and the sample labels associated with the learning samples, supervised learning is performed on the preset sound effect configuration neural network model to obtain a converged sound effect configuration neural network model.

3. The method for automatically adjusting vehicle sound effects as claimed in claim 2, It is characterized in that The step of performing supervised learning on the sound effect configuration neural network model according to the learning samples and the sample labels to obtain a converged sound effect configuration neural network model comprises: Dividing the learning sample into a training sample and a verification sample; Training a preset sound effect configuration neural network model through the training samples and sample labels associated with the training samples; The prediction accuracy of the preset sound effect configuration neural network model is verified through the verification samples and the sample labels associated with the verification samples, and the training is stopped until the prediction accuracy reaches a preset ratio threshold to obtain a converged sound effect configuration neural network model.

4. The method for automatically adjusting vehicle sound effects as claimed in claim 1, It is characterized in that The step of compensating and adjusting the initial audio parameter according to the target audio parameter gain value comprises: Determining a target phase gain value and a target amplitude gain value according to the target audio parameter gain value; According to the target phase gain value, the audio phase of the initial audio parameter is compensated and adjusted, and according to the target amplitude gain value, the audio amplitude of the initial audio parameter is compensated and adjusted.

5. The method for automatically adjusting vehicle sound effects according to any one of claims 1 to 4, It is characterized in that The step of dynamically acquiring the ear position of the vehicle occupant comprises: Dynamically identify the user's sitting position information in the car through a camera and / or seat sensor; Obtaining physical characteristic information corresponding to the registration input of each seat, wherein the physical characteristic information includes height and body proportion; The ear position of the user of the vehicle occupant is determined according to the body feature information and the seating position information.

6. The method for automatically adjusting vehicle sound effects as claimed in claim 5, It is characterized in that The step of determining the occupant information according to the physical feature information and the seating position information comprises: Detecting seat adjustment information corresponding to each seat in the vehicle, wherein the seat adjustment information includes a seat back angle and a seat height; The ear position of a user of an occupant in the vehicle is determined according to the seat adjustment information, the body characteristic information and the sitting position information.

7. The method for automatically adjusting vehicle sound effects as claimed in claim 5, It is characterized in that After the step of dynamically identifying the user's seating position information in the vehicle, the method further includes: Determining whether there are multiple passengers in the vehicle based on the seating position information; If there are multiple passengers in the vehicle, the sound effect mode mapped to the seating position information is called from a pre-stored sound effect mode mapping table according to the seating position information; the called sound effect mode is used as a target sound effect mode, and the vehicle audio system is controlled to play in the target sound effect mode, wherein the target sound effect mode is a front row sound effect mode, a rear row sound effect mode or a whole vehicle sound effect mode; If the number of passengers in the vehicle is one, execute: the step of obtaining the physical feature information corresponding to the registered input of each seat.

8. An automatic vehicle sound adjustment device, It is characterized in that include: An acquisition module, used to dynamically acquire the position of a user's ear of an occupant in the vehicle and determine a target position distance between the user's ear position and the vehicle audio system; A prediction module, used for inputting the target position distance into a converged sound effect configuration neural network model, and outputting a target audio parameter gain value corresponding to the target position distance; A compensation module, used for obtaining initial audio parameters of the audio to be played currently, and performing compensation adjustment on the initial audio parameters according to the target audio parameter gain value to obtain target audio parameters; The control module is used to dynamically control the vehicle audio system to play the target audio parameters.

9. An automatic vehicle sound adjustment device, It is characterized in that The vehicle-mounted sound effect automatic adjustment device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method for automatically adjusting the in-vehicle sound effects as described in any one of claims 1 to 7.

10. A readable storage medium, It is characterized in that The readable storage medium is a computer-readable storage medium, on which is stored a program for implementing a method for automatically adjusting vehicle-mounted sound effects. The program for implementing a method for automatically adjusting vehicle-mounted sound effects is executed by a processor to implement the steps of the method for automatically adjusting vehicle-mounted sound effects as described in any one of claims 1 to 7.

Images