Audio playing method, device, apparatus and storage medium

Abstract

The application relates to the technical field of signal processing, and discloses an audio playing method, device and equipment and a storage medium, the method comprising the following steps: in the case of playing an audio signal, determining an auditory sensitive frequency band corresponding to a target user, the target user being a user with an auditory tolerance lower than a preset standard, and the auditory sensitive frequency band being a frequency band causing damage to the auditory of the target user; extracting an audio signal component corresponding to the auditory sensitive frequency band from the audio signal; performing attenuation processing on the audio signal component to obtain a processed audio signal, and playing the processed audio signal. Compared with the existing vehicle-mounted audio control method which cannot perform differential audio control on auditory sensitive users, the application can perform attenuation processing on the audio signal component corresponding to the auditory sensitive frequency band of the user in the currently played audio signal, thereby realizing differential audio control on the auditory sensitive user and avoiding damage to the hearing of the user.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to audio playback methods, apparatus, devices and storage media. Background Technology

[0002] With the increasing popularity of intelligent vehicles and the continuous improvement of cabin intelligence, in-vehicle audio systems have become standard equipment in vehicles, with significantly enhanced playback quality, power output, and sound field control capabilities. At the same time, family car use is becoming more common, and children are increasingly frequently seen as rear-seat passengers. The impact of the in-vehicle audio environment on children's auditory health is receiving growing attention. Because children's (especially those aged 2 to 12) auditory systems are still developing, their cochlear hair cells have a much lower tolerance for high sound pressure levels and high-frequency sound waves than adults. Therefore, prolonged exposure to high-noise environments or repeated exposure to high-frequency, strong sound stimulation can easily cause irreversible damage to children's auditory nerves.

[0003] Currently, existing in-vehicle audio control methods are mainly based on the design of sound effect algorithms and volume mapping rules based on the hearing characteristics of adults, without taking into account the physiological characteristics of children. This means that under the same audio playback parameters, adults may feel that the volume is moderate and the sound quality is comfortable, but at the same time and from the same source, it may cause potential auditory overload stimulation to children in the same car, thus causing irreversible hearing damage to children. Summary of the Invention

[0004] The main objective of this application is to provide an audio playback method, apparatus, device, and storage medium, which aims to solve the technical problem that existing audio control methods cannot provide differentiated audio control for users with hearing sensitivity.

[0005] To achieve the above objectives, this application proposes an audio playback method, the method comprising: When playing an audio signal, determine the auditory sensitive frequency band corresponding to the target user. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user. Extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; The audio signal components are attenuated to obtain a processed audio signal, and the processed audio signal is played.

[0006] In one embodiment, the step of determining the auditory sensitive frequency band corresponding to the target user when playing an audio signal includes: When playing an audio signal, the sensory feature data of all users in the current playback environment is acquired. The sensory feature data includes at least one of the following: bearing status data corresponding to the bearing location of the user, image feature data, and voiceprint feature data. Age attribute recognition is performed on the image feature data to obtain the first physiological characteristic parameters corresponding to the user; The voiceprint feature data is subjected to voiceprint attribute recognition to obtain the second physiological feature parameters corresponding to the user. Based on the bearer status data, the first physiological characteristic parameter and / or the second physiological characteristic parameter, a target user is determined from each of the users, and the auditory sensitive frequency band corresponding to the target user is determined.

[0007] In one embodiment, the step of determining the target user from among the users based on the bearer status data, the first physiological characteristic parameter, and / or the second physiological characteristic parameter includes: The carrying weight value corresponding to the user is determined based on the carrying status data, and a first weight corresponding to the carrying status data is generated based on the carrying weight value. A second weight corresponding to the first physiological feature parameter is generated based on the age attribute information in the first physiological feature parameter, and a third weight corresponding to the second physiological feature parameter is generated based on the voiceprint maturity information in the second physiological feature parameter. A hearing tolerance assessment value for each user is generated based on the first weight, the second weight, the bearing status data, and the first physiological characteristic parameter; or, a hearing tolerance assessment value for each user is generated based on the first weight, the third weight, the bearing status data, and the second physiological characteristic parameter; or, a hearing tolerance assessment value for each user is generated based on the first weight, the second weight, the third weight, the bearing status data, the first physiological characteristic parameter, and the second physiological characteristic parameter. Users whose auditory tolerance assessment value is lower than a preset threshold are identified as target users.

[0008] In one embodiment, before the step of playing the processed audio signal, the method further includes: Obtain the real-time ambient noise sound pressure level of the audio playback area where the target user is located; Based on the real-time ambient noise sound pressure level, the processed audio signal is gain-corrected to obtain the corrected audio signal. The step of playing the processed audio signal includes: Play the corrected audio signal.

[0009] In one embodiment, after the step of playing the corrected audio signal, the method further includes: During the playback of the corrected audio signal, the current playback duration of the corrected audio signal is acquired in real time; When the current playback duration reaches the first duration threshold, the corrected audio signal is attenuated a second time to obtain the target audio signal, and a transition audio signal of a preset duration is played. Once the transition audio signal has finished playing, the target audio signal is played.

[0010] In one embodiment, after the step of acquiring the current playback duration of the corrected audio signal in real time, the method further includes: If the current playback duration reaches the second duration threshold, the playback of the corrected audio signal will be interrupted. If the audio interruption duration reaches the preset silence duration, the corrected audio signal is adjusted based on the preset limited gain, and the adjusted audio signal continues to be played; wherein, the second duration threshold is greater than the first duration threshold.

[0011] In one embodiment, the step of extracting the audio signal component corresponding to the auditory sensitive frequency band from the audio signal includes: Extract the auditory sensitive frequency band from the audio signal, and divide the auditory sensitive frequency band into several auditory sensitive sub-bands; Extract the audio signal sub-components corresponding to each of the aforementioned auditory sensitive sub-frequency bands; The step of attenuating the audio signal components to obtain the processed audio signal includes: Determine the preset attenuation parameters corresponding to each of the aforementioned auditory sensitive sub-bands; The corresponding audio signal sub-components are attenuated based on the preset attenuation parameters to obtain the processed audio signal.

[0012] Furthermore, to achieve the above objectives, this application also proposes an audio playback device, the device comprising: The sensitive frequency band determination module is used to determine the auditory sensitive frequency band corresponding to the target user when playing an audio signal. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user. The signal extraction module is used to extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; An audio playback module is used to attenuate the audio signal components to obtain a processed audio signal, and to play the processed audio signal.

[0013] In addition, to achieve the above objectives, this application also proposes an audio playback device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the audio playback method as described above.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the audio playback method described above.

[0015] This application provides an audio playback method, apparatus, device, and storage medium. The method includes: while playing an audio signal, determining the auditory sensitive frequency band corresponding to a target user, wherein the target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes hearing damage to the target user; extracting the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; performing attenuation processing on the audio signal component to obtain a processed audio signal, and playing the processed audio signal.

[0016] This application can, while playing an audio signal, identify the hearing-sensitive frequency bands that would damage the hearing of a target user whose hearing tolerance is below a preset standard. It then extracts the audio signal components corresponding to these sensitive frequency bands from the audio signal, attenuates these components, and obtains and plays the processed audio signal. Compared to existing in-vehicle audio control methods that cannot provide differentiated audio control for hearing-sensitive users, this application attenuates the audio signal components corresponding to the user's hearing-sensitive frequency bands in the currently played audio signal, thereby achieving differentiated audio control for hearing-sensitive users and avoiding damage to their hearing. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the audio playback device structure in the hardware operating environment involved in the embodiments of this application; Figure 2 This is a flowchart illustrating the first embodiment of the audio playback method of this application; Figure 3 This is a schematic diagram of the audio signal attenuation processing in the audio playback method of this application; Figure 4 This is a flowchart illustrating the second embodiment of the audio playback method of this application; Figure 5 This is a flowchart illustrating the target user identification process in the audio playback method of this application. Figure 6 This is a flowchart illustrating the third embodiment of the audio playback method of this application; Figure 7 This is a structural block diagram of the audio playback device of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] Reference Figure 1 , Figure 1 This is a schematic diagram of the audio playback device structure in the hardware operating environment involved in the embodiments of this application.

[0023] like Figure 1 As shown, the audio playback device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may be connected to a display screen. Optionally, the user interface 1003 may include a standard wired interface or a wireless interface; in this application, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0024] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the audio playback device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0025] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an audio playback program.

[0026] exist Figure 1 In the audio playback device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user device; the audio playback device calls the audio playback program stored in the memory 1005 through the processor 1001 and executes the steps of the audio playback method provided in the embodiments of this application.

[0027] It should be noted that with the popularization of intelligent vehicles and the continuous improvement of cockpit intelligence, in-vehicle audio systems have become standard equipment in vehicles, with significantly enhanced playback quality, power output, and sound field control capabilities. At the same time, family car use is increasing, and children are frequently seen as rear-seat passengers, leading to growing concern about the impact of the in-vehicle audio environment on children's auditory health. Because children's (especially those aged 2 to 12) auditory systems are still developing, their cochlear hair cells have a much lower tolerance for high sound pressure levels and high-frequency sound waves than adults. Therefore, prolonged exposure to high-noise environments or repeated high-frequency, strong sound stimulation can easily cause irreversible damage to children's auditory nerves.

[0028] Currently, existing in-vehicle audio control methods are mainly based on the design of sound effect algorithms and volume mapping rules based on the hearing characteristics of adults, without taking into account the physiological characteristics of children. This means that under the same audio playback parameters, adults may feel that the volume is moderate and the sound quality is comfortable, but at the same time and from the same source, it may cause potential auditory overload stimulation to children in the same car, thus causing irreversible hearing damage to children.

[0029] Therefore, in order to overcome the above-mentioned defects, this application provides an audio playback method, apparatus, device, and storage medium. The method includes: when playing an audio signal, determining the auditory sensitive frequency band corresponding to a target user, wherein the target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user; extracting the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; performing attenuation processing on the audio signal component to obtain a processed audio signal, and playing the processed audio signal.

[0030] This application can, while playing an audio signal, identify the hearing-sensitive frequency bands that would damage the hearing of a target user whose hearing tolerance is below a preset standard. It then extracts the audio signal components corresponding to these sensitive frequency bands from the audio signal, attenuates these components, and obtains and plays the processed audio signal. Compared to existing in-vehicle audio control methods that cannot provide differentiated audio control for hearing-sensitive users, this application attenuates the audio signal components corresponding to the user's hearing-sensitive frequency bands in the currently played audio signal, thereby achieving differentiated audio control for hearing-sensitive users and avoiding damage to their hearing.

[0031] For ease of understanding, the following is combined with Figures 2 to 6 The audio playback method provided in the embodiments of this application will be described in detail.

[0032] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the audio playback method of this application. The first embodiment of the audio playback method of this application is presented as follows: Figure 2 As shown, in this embodiment, the specific method includes: Step S10: When playing an audio signal, determine the auditory sensitive frequency band corresponding to the target user. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user.

[0033] It is understood that the method of this embodiment can be applied to an audio playback device, which can be any device with functions such as program execution, audio signal processing, and playback, such as a vehicle's central control unit or in-vehicle infotainment system, etc. This embodiment does not limit this. The execution subject of this method embodiment can be the aforementioned audio playback device (hereinafter referred to as the device) to describe this embodiment and the following embodiments.

[0034] It is also understood that the audio playback device in this embodiment may include components such as an audio signal source input interface (e.g., a Bluetooth receiver module, a USB interface, a vehicle-mounted internal storage module, a wireless communication module, etc.), a digital signal processor (DSP), a digital-to-analog converter, a power amplifier, and a speaker. In an in-vehicle scenario, the audio playback device can interact with other electronic control units in the vehicle via an in-vehicle bus (such as a CAN bus, Ethernet, etc.) and supports multiple audio source inputs such as Bluetooth, USB, and in-vehicle streaming media.

[0035] Understandably, the audio signal can be an electrical signal or digital data stream provided by an audio source to drive the speaker to produce sound. It can originate from various audio sources, such as audio streams from mobile devices transmitted via Bluetooth, externally stored audio files read via a USB interface, local audio files stored in the vehicle's internal storage, or system prompts generated by the vehicle's operating system. In this embodiment, the frequency range of the audio signal played by the device can cover the audible frequency band (e.g., 20Hz to 20kHz), and the audio signal contains multiple frequency components, each with its own amplitude and phase.

[0036] It should be understood that the target user can be a user located in the environment where the audio playback device is located (e.g., a vehicle cabin) and whose auditory tolerance is lower than a preset standard. For example, children aged 2 to 12 years old, because the auditory system (including the outer ear, middle ear, inner ear, and auditory nerve) of children in this age group is still in the developmental stage, and the cochlear hair cells are less resistant to high sound pressure levels and specific frequency ranges of sound wave stimulation than adults. In addition, the target user can also be other users with special sensitivities in their auditory system, and this embodiment does not limit this. In this embodiment, the audio playback device can identify the physiological characteristics of users in the environment where the audio playback device is located by collecting data from sensors (e.g., seat pressure sensors, in-vehicle cameras, zone microphones, etc.), thereby determining the target user from multiple users.

[0037] It should also be understood that the auditory sensitive frequency band can be the frequency band in a target user's auditory system where they are more vulnerable to sound signals within a specific frequency range and are more easily damaged by sound stimulation. For users with auditory tolerance below a preset standard (e.g., children), their corresponding auditory sensitive frequency band is typically located in the high-frequency region, such as the 2kHz to 16kHz range. In this embodiment, the specific frequency range of the auditory sensitive frequency band can be adaptively adjusted according to the target user's age, auditory development status, or individual differences.

[0038] Understandably, auditory tolerance refers to a user's ability to withstand sustained exposure to specific sound pressure levels (expressed in decibels, dB) and frequencies without experiencing temporary threshold shifts or permanent hearing loss. In practice, a user's auditory tolerance is typically related to factors such as age, the degree of development of the auditory system, and the health of the cochlear hair cells. For example, children generally have lower auditory tolerance than adults, meaning that children are at higher risk of auditory system damage under the same sound pressure levels and frequencies than adults.

[0039] It is also understandable that the preset standard can be a pre-set reference threshold used to distinguish between users with normal hearing tolerance and users with low hearing tolerance, which can be set based on physiological or medical guidelines for safe hearing exposure (such as the World Health Organization's recommendations on safe hearing exposure levels for children).

[0040] In its implementation, during audio signal playback, the device can acquire characteristic data of each user in the environment where the audio playback device is located through the in-vehicle sensor system. This includes at least one of the following: user's carrying status data, image feature data, and voiceprint feature data. Based on this characteristic data, the device identifies target users whose auditory tolerance is lower than a preset standard. Then, the device can determine the corresponding auditory sensitive frequency band based on the target user's physiological characteristics (e.g., age, voiceprint maturity). Specifically, the device's storage module can have a pre-set mapping table that records the correspondence between different age ranges and corresponding auditory sensitive frequency band ranges. After determining the target user and their age, the device can obtain the corresponding auditory sensitive frequency band by querying this mapping table.

[0041] Step S20: Extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal.

[0042] It should be noted that an audio signal component can be a local signal component of an audio signal corresponding to the auditory sensitive frequency band. In this embodiment, the audio signal may contain multiple frequency components in the frequency domain, wherein the signal component whose frequency falls within the auditory sensitive frequency band (e.g., 2kHz to 16kHz) is the audio signal component. In practical applications, the device can separate the audio signal component from the complete audio signal using frequency domain filtering techniques (e.g., bandpass filtering).

[0043] In practical implementation, after determining the target user's auditory sensitive frequency band, the device can use a bandpass filter to separate the signal components belonging to the auditory sensitive frequency band from the audio signal. The passband range of this bandpass filter is set to match the auditory sensitive frequency band (e.g., 2kHz to 16kHz), and the stopband range is set to the frequency range outside the auditory sensitive frequency band. This ensures that after the audio signal passes through the bandpass filter, it outputs the audio signal component corresponding to the auditory sensitive frequency band. Simultaneously, the signal components of other frequency bands in the audio signal can be retained and used for subsequent synthesis with the attenuated audio signal components to generate a complete audio signal. Furthermore, the device can also use a Fast Fourier Transform (FFT) to transform the audio signal from the time domain to the frequency domain, and extract the set of frequency points corresponding to the auditory sensitive frequency band in the frequency domain to obtain the audio signal components.

[0044] Step S30: Attenuate the audio signal components to obtain the processed audio signal, and play the processed audio signal.

[0045] Understandably, the processed audio signal can be a complete audio signal obtained by attenuating the audio signal component corresponding to the hearing-sensitive frequency band and recombining it with signal components from other frequency bands outside the hearing-sensitive frequency band. In the processed audio signal, the amplitude of the audio signal component corresponding to the hearing-sensitive frequency band is lower than the amplitude of that frequency band in the original audio signal, while the signal components of other frequency bands maintain their original amplitude or remain essentially unchanged.

[0046] In its implementation, after extracting the audio signal component corresponding to the hearing-sensitive frequency band, the device can obtain an attenuation parameter (e.g., a preset gain coefficient) corresponding to the hearing-sensitive frequency band, and multiply the amplitude of the audio signal component by this gain coefficient to obtain the attenuated audio signal component. Then, the device can synthesize the attenuated audio signal component with the signal components of the remaining frequency bands in the audio signal that were not extracted, obtaining a processed audio signal, and output the processed audio signal to a speaker for playback. In this embodiment, because the amplitude of the audio signal component corresponding to the hearing-sensitive frequency band in the currently played processed audio signal is lower than the amplitude of that frequency band in the original audio signal, it can avoid damage to the target user's hearing caused by the sound signal in that frequency band, thereby achieving hearing protection for the target user.

[0047] Further, the step of extracting the audio signal component corresponding to the auditory sensitive frequency band from the audio signal includes: extracting the auditory sensitive frequency band from the audio signal, and dividing the auditory sensitive frequency band into frequency bands to obtain several auditory sensitive sub-frequency bands; and extracting the audio signal sub-component corresponding to each auditory sensitive sub-frequency band. It should be noted that the hearing-sensitive sub-band can be several frequency sub-intervals obtained by further dividing the hearing-sensitive band according to a preset division rule. In this embodiment, each hearing-sensitive sub-band can cover a part of the frequency range of the hearing-sensitive band, and the hearing-sensitive sub-bands do not overlap with each other.

[0048] It should also be noted that the number of auditory sensitive sub-bands and the frequency range of each auditory sensitive sub-band can be adaptively adjusted according to the physiological characteristics of the target user, the distribution of auditory sensitivity, or the needs of the actual application scenario. This embodiment does not impose specific limitations on this.

[0049] Understandably, an audio signal sub-component can be a signal component in the audio signal belonging to each auditory sensitive sub-band, with a one-to-one correspondence between them; that is, each auditory sensitive sub-band corresponds to a unique audio signal sub-component. In this embodiment, after dividing the auditory sensitive frequency band into several auditory sensitive sub-bands, for each auditory sensitive sub-band, the local signal component in the audio signal falling within the frequency range of that auditory sensitive sub-band is the audio signal sub-component corresponding to that auditory sensitive sub-band.

[0050] In its implementation, after determining the auditory sensitive frequency band (e.g., 2kHz to 16kHz), the device can read the corresponding frequency band division parameters from its internal storage module. These parameters include the number of sub-bands and the start and cutoff frequencies of each sub-band. Then, the device can divide the auditory sensitive frequency band into several consecutive frequency sub-intervals in the frequency domain based on these parameters. Each frequency sub-interval is a single auditory sensitive sub-band. Subsequently, the device can use multiple bandpass filters to filter the audio signal. The passband range of each bandpass filter is set to match the corresponding auditory sensitive sub-band, ensuring that after passing through multiple bandpass filters, the audio signal outputs the audio signal sub-component corresponding to the auditory sensitive sub-band of that bandpass filter.

[0051] Accordingly, the step of attenuating the audio signal components to obtain the processed audio signal includes: determining a preset attenuation parameter corresponding to each of the hearing-sensitive sub-bands; and attenuating the corresponding audio signal sub-components based on the preset attenuation parameters to obtain the processed audio signal.

[0052] It should be noted that the preset attenuation parameter can be a pre-set parameter value used to reduce the amplitude of audio signal sub-components, and it can correspond one-to-one with the hearing-sensitive sub-frequency bands. In this embodiment, the preset attenuation parameter can be expressed in the form of a gain coefficient, such as a positive value less than 1, or in the form of an attenuation decibel value, such as -6dB, -9dB, or -12dB.

[0053] It should also be noted that, considering the physiological characteristic that target users are more sensitive to higher frequency sound signals, the preset attenuation parameters corresponding to each auditory sensitive sub-band in this embodiment can increase with the frequency, thereby effectively protecting the target user's hearing while preserving the audibility and sound quality of the audio signal as much as possible. For example, when the auditory sensitive frequency band is divided into three auditory sensitive sub-bands: 2kHz to 4kHz, 4kHz to 8kHz, and 8kHz to 16kHz, the preset attenuation parameter corresponding to the 2kHz to 4kHz auditory sensitive sub-band can be set to -6dB (i.e., a gain coefficient of 0.5), the preset attenuation parameter corresponding to the 4kHz to 8kHz auditory sensitive sub-band can be set to -9dB (i.e., a gain coefficient of 0.355), and the preset attenuation parameter corresponding to the 8kHz to 16kHz auditory sensitive sub-band can be set to -12dB (i.e., a gain coefficient of 0.25).

[0054] In practical applications, if the preset attenuation parameter is expressed in the form of a gain coefficient, the device can multiply the amplitude of the audio signal sub-component by the gain coefficient to obtain the attenuated amplitude, thereby achieving attenuation processing of the audio signal sub-component. Alternatively, if the preset attenuation parameter is expressed in the form of an attenuation decibel value, the device can reduce the amplitude of the audio signal sub-component according to that attenuation decibel value, thereby achieving attenuation processing of the audio signal sub-component.

[0055] In the specific implementation, refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the audio signal attenuation processing in the audio playback method of this application. Figure 3As shown, the device can divide the auditory sensitive frequency band from 2kHz to 16kHz into three auditory sensitive sub-bands based on frequency band division parameters: a first auditory sensitive sub-band, a second auditory sensitive sub-band, and a third auditory sensitive sub-band. The first auditory sensitive sub-band is from 2kHz to 4kHz, the second is from 4kHz to 8kHz, and the third is from 8kHz to 16kHz. Subsequently, the device can retrieve preset attenuation parameters corresponding to each auditory sensitive sub-band from a pre-stored mapping table in its internal storage. If the preset attenuation parameters are expressed as gain coefficients, the device can multiply the amplitude of each audio signal sub-component by its corresponding preset attenuation parameter to obtain the attenuated audio signal sub-component for each auditory sensitive sub-band. Furthermore, if the preset attenuation parameters are expressed in decibels (dB), for example, a 6dB reduction in sound intensity for the 2kHz to 4kHz frequency band, a 9dB reduction for the 4kHz to 8kHz frequency band, and a 12dB reduction for the 8kHz to 16kHz frequency band, the device can reduce the amplitude of each audio signal sub-component according to its corresponding preset attenuation parameter, obtaining attenuated audio signal sub-components for each auditory sensitive sub-frequency band. Finally, the device can synthesize each attenuated audio signal sub-component with the unattenuated signal components of the remaining frequency bands in the audio signal to obtain the processed audio signal.

[0056] This embodiment can identify the hearing-sensitive frequency bands that would damage the hearing of target users with hearing tolerance below a preset standard when playing audio signals. It then extracts the audio signal components corresponding to these sensitive frequency bands from the audio signal, attenuates these components, and obtains and plays the processed audio signal. Compared to existing in-vehicle audio control methods that cannot provide differentiated audio control for hearing-sensitive users, this embodiment attenuates the audio signal components corresponding to the user's hearing-sensitive frequency bands in the currently playing audio signal, thereby achieving differentiated audio control for hearing-sensitive users and avoiding damage to their hearing.

[0057] Reference Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the audio playback method of this application. Based on the first embodiment described above, a second embodiment of the audio playback method of this application is proposed.

[0058] In this embodiment, the step of determining the auditory sensitive frequency band corresponding to the target user when playing an audio signal includes: Step S11: When playing an audio signal, obtain the perceptual feature data of all users in the current playback environment. The perceptual feature data includes at least one of the following: bearing status data corresponding to the bearing location of the user, image feature data, and voiceprint feature data.

[0059] Understandably, the current playback environment can be the physical space area where the audio playback device is deployed, that is, the spatial range covered by the sound waves that act on the user's auditory system when the audio playback device outputs audio signals, such as the interior space of a vehicle cabin, which may include the front driving area and the rear passenger area.

[0060] It is also understood that the perceptual feature data can be information used to characterize the physiological characteristics or states of each user in the current playback environment. In this embodiment, the perceptual feature data may include at least one of the following: bearer status data of the corresponding user's bearer location, image feature data, and voiceprint feature data.

[0061] It should be understood that the carrying position can be the physical location of each user in the current playback environment, which typically corresponds to a carrying device. For example, in a vehicle cabin environment, the carrying position can include the driver's seat position, the front passenger seat position, the rear left passenger seat position, and the rear right passenger seat position. Correspondingly, the carrying status data can be a set of data characterizing whether the carrying position carries a user and the physical characteristics of the carrying position, which can be obtained by a mechanical sensing unit deployed at the carrying position. In this embodiment, the carrying status data can include information such as the carrying weight value of the carrying device, the seat belt buckle status, and the backrest angle of the carrying device, wherein the carrying weight value can be detected by a weight sensor or pressure sensor installed inside the carrying device.

[0062] It should also be understood that image feature data can be image information used to characterize the facial and / or limb features of each user in the current playback environment, such as face detection boxes, facial key points, head pose angles, etc., which can be acquired through image acquisition devices (such as in-vehicle cameras). Voiceprint feature data can be audio information used to characterize the voice features of each user in the current playback environment, such as each user's voice samples, voice frequency features, voice duration features, and voice intensity features, etc., which can be acquired through sound acquisition devices (such as zone microphones).

[0063] In its implementation, during audio signal playback, the device can activate its connected sensors to collect data. Specifically, the device can collect the load weight value at each user's load position using weight or pressure sensors on the load-bearing device to obtain load status data, and collect user images at each load position using an in-vehicle camera to obtain image feature data. Simultaneously, it can collect user voice at each load position using zoned microphones to obtain voiceprint feature data.

[0064] Step S12: Perform age attribute recognition on the image feature data to obtain the first physiological characteristic parameters corresponding to the user.

[0065] It should be noted that age attribute recognition can be a process of processing and analyzing image feature data to extract physiological feature information related to the user's age. In this embodiment, age attribute recognition is achieved through an image recognition algorithm, which can predict the user's age or age range based on information such as the geometric features, skin texture features, and facial proportion features of the user's facial image.

[0066] It should also be noted that the first physiological characteristic parameter can be a quantitative value of physiological characteristics used to characterize the user's age or age range. In this embodiment, the first physiological characteristic parameter can be a specific age value (e.g., 5 years old, 8 years old, or 32 years old), or it can be an age range (e.g., 2 to 6 years old, 7 to 12 years old, 13 to 17 years old, or 18 years and older). Furthermore, the first physiological characteristic parameter can also be an age-level code; for example, level 1 represents 0 to 6 years old, level 2 represents 7 to 12 years old, level 3 represents 13 to 17 years old, and level 4 represents 18 years and older.

[0067] In its implementation, after acquiring image feature data, the device can call a pre-built age recognition model in its internal storage module to perform age attribute recognition processing on the image feature data. This age recognition model can be an artificial intelligence model trained on a deep convolutional neural network. Specifically, the device can input the image feature data into the age recognition model. After receiving the image feature data, the age recognition model can extract features from the facial regions in the image feature data and predict the corresponding age value or age range for each user based on the extracted facial features (such as wrinkles around the eyes, skin elasticity features, facial contour proportions, etc.), ultimately outputting the age attribute recognition result.

[0068] Step S13: Perform voiceprint attribute recognition on the voiceprint feature data to obtain the second physiological feature parameters corresponding to the user.

[0069] It should be noted that voiceprint attribute recognition can be the process of extracting physiological feature information related to the maturity of a user's voiceprint from voiceprint feature data. This can be achieved through a voiceprint recognition algorithm, which can infer the maturity of a user's voiceprint based on information such as the fundamental frequency features, formant features, and speech duration features of the user's speech.

[0070] It should also be noted that the second physiological characteristic parameter can be a quantitative value of physiological characteristics used to characterize the maturity of the user's voice development. It can be a specific voiceprint maturity value or a voiceprint maturity level (for example, level 1 represents immature, level 2 represents semi-mature, and level 3 represents mature).

[0071] In its implementation, after obtaining voiceprint feature data, the device can call a pre-built voiceprint recognition model in its internal storage module to perform voiceprint attribute recognition processing on the voiceprint feature data. This voiceprint recognition model can be an artificial intelligence model trained on a deep neural network. Specifically, the device can input the voiceprint feature data into the voiceprint recognition model. After receiving the voiceprint feature data, the voiceprint recognition model can extract features from the voiceprint feature data (such as fundamental frequency, formant frequency, speech duration, and speech intensity envelope), and predict the voiceprint maturity value or voiceprint maturity level for each user based on the extracted voiceprint features, ultimately outputting the voiceprint attribute recognition result.

[0072] Step S14: Based on the bearer status data, the first physiological characteristic parameter and / or the second physiological characteristic parameter, determine the target user from each of the users, and determine the auditory sensitive frequency band corresponding to the target user.

[0073] In practical applications, after obtaining the load-bearing status data, first physiological characteristic parameters, and / or second physiological characteristic parameters of each user, the device can compare these data with preset standards. These preset standards may include at least one of an age threshold, a voiceprint maturity threshold, and a load-bearing weight threshold. Then, based on the comparison results, the device can identify users whose auditory tolerance is lower than the preset standards and designate them as target users. After identifying the target users, the device can query a preset mapping table of user categories and auditory sensitive frequency bands in its internal storage module to find auditory sensitive frequency bands that match the target user's physiological characteristics, based on the target user's corresponding first and / or second physiological characteristic parameters. For example, if the target user is a child aged 2 to 12 years, their corresponding auditory sensitive frequency band could be a range of 2kHz to 16kHz.

[0074] In this embodiment, the device acquires the bearer status data, image feature data, and voiceprint feature data of each user in the current playback environment. It then performs age attribute recognition on the image feature data to obtain a first physiological feature parameter, and / or performs voiceprint attribute recognition on the voiceprint feature data to obtain a second physiological feature parameter. Based on the bearer status data, the first physiological feature parameter, and / or the second physiological feature parameter, the device comprehensively determines the target user and identifies the corresponding auditory sensitive frequency band. This allows for accurate identification of target users with hearing tolerance below a preset standard in complex acoustic environments, and the determination of the corresponding auditory sensitive frequency band based on the physiological characteristics of the target user. This avoids misjudgment or omission that may occur based on a single identification method, thereby improving the targeting and reliability of hearing protection control.

[0075] Further, the step of determining the target user from each of the users based on the bearer status data, the first physiological characteristic parameter, and / or the second physiological characteristic parameter includes: Step S141: Determine the load weight value corresponding to the user based on the load status data, and generate the first weight corresponding to the load status data based on the load weight value.

[0076] Understandably, the load-bearing weight value can be the weight of the user borne at the load-bearing location, which can be detected by a weight sensor or pressure sensor installed inside or below the load-bearing location. In a vehicle cabin environment, one or more weight sensors can be installed under each seat, which can detect the weight of the object borne on the seat to obtain the load-bearing weight value.

[0077] It is also understood that the first weight can be a coefficient value used to characterize the influence of the load status data in the subsequent hearing tolerance assessment. It can be determined based on the comparison between the load weight value and a preset weight range, where the preset weight range can be used to distinguish users of different age groups.

[0078] In its implementation, after obtaining the load weight value corresponding to each load position, the device can compare each load weight value with a preset weight threshold to determine the first weight corresponding to the load status data. Specifically, when the load weight value falls within a preset child weight range (e.g., 10kg to 65kg), the device can set the first weight corresponding to the load status data to a higher value; when the load weight value falls within a preset adult weight range (e.g., greater than 65kg), the device can set the first weight corresponding to the load status data to a lower value.

[0079] Step S142: Generate a second weight corresponding to the first physiological feature parameter based on the age attribute information in the first physiological feature parameter, and generate a third weight corresponding to the second physiological feature parameter based on the voiceprint maturity information in the second physiological feature parameter.

[0080] It should be understood that the age attribute information can be the information used to characterize the user's age or age range in the first physiological characteristic parameter. It can be a specific age value, age range, or age classification code. This embodiment does not limit this.

[0081] It should also be understood that the second weight can be a coefficient value used to characterize the degree of influence of the first physiological characteristic parameter in the subsequent auditory tolerance assessment, which can be determined based on the comparison between the user's age represented by the age attribute information and a preset age range.

[0082] In its implementation, after obtaining the first physiological characteristic parameters corresponding to each user, the device can extract the user's age attribute information from the first physiological characteristic parameters, compare the age attribute information with a preset age range, and then generate a corresponding second weight for each user based on the comparison result. Specifically, when the age represented by the age attribute information falls within a preset child age range (e.g., 2 to 12 years old), the device can set the second weight corresponding to the first physiological characteristic parameter to a higher value; when the age represented by the age attribute information falls within a preset adult age range (e.g., greater than 18 years old), the device can set the second weight corresponding to the first physiological characteristic parameter to a lower value.

[0083] Understandably, voiceprint maturity information can be information used in the second physiological characteristic parameter to characterize the developmental maturity of a user's voiceprint. It can be a specific voiceprint maturity value or a voiceprint maturity level, and this embodiment does not limit this. In practical applications, because children's vocal cord structure and vocal system are not yet fully developed, their voiceprint characteristics (e.g., higher fundamental frequency and more dispersed formant distribution) are significantly different from those of adults. Therefore, this embodiment can use voiceprint maturity information to assess the user's age and auditory development status.

[0084] It is also understood that the third weight can be a coefficient value used to characterize the degree of influence of the second physiological characteristic parameter in the subsequent auditory tolerance assessment, which can be determined based on the comparison between the voiceprint maturity level characterized by voiceprint maturity information and the preset maturity threshold.

[0085] In its implementation, after obtaining the second physiological characteristic parameters corresponding to each user, the device can extract the user's voiceprint maturity information from the second physiological characteristic parameters, compare the voiceprint maturity information with a preset maturity threshold, and then generate a corresponding third weight based on the comparison result. Specifically, when the maturity level represented by the voiceprint maturity information is lower than the preset maturity threshold (e.g., level lower than 2), the device can set the third weight corresponding to the second physiological characteristic parameter to a higher value; when the maturity level represented by the voiceprint maturity information is higher than or equal to the preset maturity threshold, the device can set the third weight corresponding to the second physiological characteristic parameter to a lower value.

[0086] Step S143: Generate an auditory tolerance assessment value for each user based on the first weight, the second weight, the load-bearing status data, and the first physiological characteristic parameter; or, generate an auditory tolerance assessment value for each user based on the first weight, the third weight, the load-bearing status data, and the second physiological characteristic parameter; or, generate an auditory tolerance assessment value for each user based on the first weight, the second weight, the third weight, the load-bearing status data, the first physiological characteristic parameter, and the second physiological characteristic parameter.

[0087] It should be noted that the auditory tolerance assessment value can be a numerical value used to quantify the degree of tolerance of a user's auditory system to sound stimuli. It can reflect the level of a user's auditory tolerance. The lower the auditory tolerance assessment value, the worse the user's auditory tolerance, and the higher the probability that the user is the target user. In this embodiment, the auditory tolerance assessment value can be generated by comprehensively calculating based on the first weight, the second weight, the third weight, the bearing state data, the first physiological characteristic parameter, and the second physiological characteristic parameter.

[0088] It should also be noted that in real-world applications, the device may not be able to simultaneously acquire all data related to the hearing status, the first physiological characteristic parameter, and the second physiological characteristic parameter. For example, in some scenarios, the device may be unable to acquire clear image feature data due to insufficient lighting at night, resulting in the loss of the first physiological characteristic parameter; or, the device may be unable to acquire voiceprint feature data because the user is not speaking, resulting in the loss of the second physiological characteristic parameter. To address these data gaps, the device can employ various evaluation methods to generate an auditory tolerance assessment value.

[0089] For example, when the device acquires load-bearing status data and a first physiological characteristic parameter, it can generate an auditory tolerance assessment value for each user based on a first weight, a second weight, the load-bearing status data, and the first physiological characteristic parameter. Specifically, the device first normalizes the load weight value in the load-bearing status data and the age attribute information in the first physiological characteristic parameter to obtain normalized characteristic values ​​of the load-bearing status data and the first physiological characteristic parameter. It then multiplies the normalized characteristic value of the load-bearing status data by the first weight to obtain a first weighted characteristic value, and simultaneously multiplies the normalized characteristic value of the first physiological characteristic parameter by the second weight to obtain a second weighted characteristic value. Finally, it sums the first weighted characteristic value and the second weighted characteristic value to obtain the auditory tolerance assessment value for each user. The corresponding calculation formula can be expressed as:

[0090] in, This indicates the auditory tolerance assessment value. Indicates the first weight. This represents the normalized eigenvalues ​​of the carrying state data. Indicates the second weight. This represents the normalized eigenvalue of the first physiological characteristic parameter.

[0091] Furthermore, when the device acquires the load-bearing status data and the second physiological characteristic parameter, it can generate an auditory tolerance assessment value for each user based on the first weight, the third weight, the load-bearing status data, and the second physiological characteristic parameter. Specifically, the device first normalizes the load weight value in the load-bearing status data and the voiceprint maturity information in the second physiological characteristic parameter to obtain the normalized characteristic value of the load-bearing status data and the normalized characteristic value of the second physiological characteristic parameter. The normalized characteristic value of the load-bearing status data is then multiplied by the first weight to obtain the first weighted characteristic value. Simultaneously, the normalized characteristic value of the second physiological characteristic parameter is multiplied by the third weight to obtain the third weighted characteristic value. Finally, the first weighted characteristic value and the third weighted characteristic value are summed to obtain the auditory tolerance assessment value for each user. The corresponding calculation formula can be expressed as follows:

[0092] in, This indicates the auditory tolerance assessment value. Indicates the first weight. This represents the normalized eigenvalues ​​of the carrying state data. Indicates the third weight. This represents the normalized eigenvalue of the second physiological characteristic parameter.

[0093] Furthermore, when the device acquires the load-bearing status data, the first physiological characteristic parameter, and the second physiological characteristic parameter, it can generate an auditory tolerance assessment value for each user based on the first weight, second weight, third weight, load-bearing status data, and the first and second physiological characteristic parameters. In specific implementation, after obtaining the first weight, second weight, third weight, load-bearing status data, first physiological characteristic parameter, and second physiological characteristic parameter for each user, the device can normalize the load-bearing status data, first physiological characteristic parameter, and second physiological characteristic parameter respectively to obtain the corresponding normalized feature values. Subsequently, the device can perform a weighted calculation of the first weight, second weight, and third weight for each user with the corresponding normalized feature values ​​to obtain the auditory tolerance assessment value for each user. The corresponding calculation formula can be expressed as:

[0094] in, This indicates the auditory tolerance assessment value. Indicates the first weight. This represents the normalized eigenvalues ​​of the carrying state data. Indicates the second weight. This represents the normalized eigenvalue of the first physiological characteristic parameter. Indicates the third weight. This represents the normalized eigenvalue of the second physiological characteristic parameter.

[0095] Step S144: The users whose auditory tolerance assessment value is lower than a preset threshold are identified as target users.

[0096] In practical applications, after generating auditory tolerance assessment values ​​for each user, the device can compare these values ​​with preset assessment thresholds. These preset thresholds can be pre-defined reference values ​​used to distinguish between users with normal auditory tolerance and those with lower auditory tolerance. When a user's auditory tolerance assessment value is lower than the preset threshold, the user's auditory tolerance is determined to be below the preset standard, and this user can be identified as a target user. Conversely, when a user's auditory tolerance assessment value is higher than or equal to the preset threshold, the user's auditory tolerance is determined to be normal, and this user is not a target user.

[0097] In this embodiment, the device converts the load-bearing status data into a load-bearing weight value and generates a corresponding first weight. It then generates a corresponding second weight from the age attribute information in the first physiological characteristic parameter and a corresponding third weight from the voiceprint maturity information in the second physiological characteristic parameter. Based on the first weight, second weight, third weight, load-bearing status data, first physiological characteristic parameter, and second physiological characteristic parameter, the device generates a hearing tolerance assessment value for each user. Users whose hearing tolerance assessment value is lower than a preset threshold are identified as target users. This improves the determination of target users from binary classification based on a single-dimensional feature to a quantitative assessment based on the comprehensive weight of multi-dimensional features, thereby improving the accuracy and robustness of target user determination and thus enhancing the targeting and precision of subsequent hearing protection.

[0098] In the specific implementation, refer to Figure 5 , Figure 5 This is a flowchart illustrating the target user identification process in the audio playback method of this application. Figure 5 As shown, the device first acquires the perceptual feature data of each user in the current playback environment, including carrying status data, image feature data, and voiceprint feature data. Then, the device calls a pre-set age recognition model to extract and recognize age features from facial images in the image feature data, obtaining the first physiological feature parameters corresponding to each user. It then calls a pre-set voiceprint recognition model to extract and recognize voiceprint features from speech samples in the voiceprint feature data, obtaining the second physiological feature parameters corresponding to each user. Next, the device generates a first weight corresponding to the carrying status data based on the carrying weight value extracted from the carrying status data, generates a second weight corresponding to the first physiological feature parameters based on the age attribute information in the first physiological feature parameters, and generates a third weight corresponding to the second physiological feature parameters based on the voiceprint maturity information in the second physiological feature parameters. Subsequently, the device can perform a weighted fusion evaluation based on the first weight, second weight, third weight, bearer status data, first physiological characteristic parameter, and second physiological characteristic parameter to generate an auditory tolerance assessment value for each user. This assessment value is then compared to a preset threshold. If the auditory tolerance assessment value is lower than the preset threshold, the user's auditory tolerance is determined to be below the preset standard. In this case, the user is identified as a target user and enters hearing protection mode, where the audio signal components are attenuated before playback. Conversely, if the auditory tolerance assessment value is not lower than the preset threshold, the user's auditory tolerance is determined to be normal. In this case, the user is not a target user and can be processed in the normal mode, i.e., the audio signal is not attenuated and is played directly.

[0099] Reference Figure 6 , Figure 6This is a flowchart illustrating the third embodiment of the audio playback method of this application. Based on the above embodiments, the third embodiment of the audio playback method of this application is proposed.

[0100] In this embodiment, before the step of playing the processed audio signal, the method further includes: Step S31: Obtain the real-time ambient noise sound pressure level of the audio playback area where the target user is located.

[0101] It should be understood that the audio playback area can be a sub-region of the space where the target user is located in the current playback environment. In practical applications, the current playback environment (e.g., the interior space of a vehicle cabin) can be divided into multiple audio playback areas according to spatial location, with each audio playback area corresponding to one or more carrying positions. For example, in a vehicle cabin environment, the audio playback area may include the front driver area, the front passenger area, the rear left side area, and the rear right side area. Furthermore, in this embodiment, each audio playback area can be equipped with an independent speaker or speaker group to achieve zoned audio output.

[0102] It should be noted that the real-time ambient noise sound pressure level can be the sound pressure level of other sound signals in the audio playback area besides the audio signal played by the audio playback device. It can be used to characterize the current ambient noise intensity in the audio playback area. For example, in a vehicle cabin environment, the real-time ambient noise sound pressure level can include the superimposed sound pressure level of ambient sounds such as wind noise, tire noise, road noise, engine noise, and other occupant conversations.

[0103] In practical implementation, the device can acquire sound signals within the audio playback area in real time using a sound acquisition device (e.g., a zone microphone) installed near or inside the audio playback area. It then converts the acquired analog sound signals into digital audio signals and calculates the sound pressure level (SPL) of the digital audio signals to obtain the real-time ambient noise SPL value. In practical applications, since the sound signals acquired by the sound acquisition device contain both the audio signal played by the audio playback device through its speakers and ambient noise components, the device needs to filter out the audio signal components played by the audio playback device to obtain the pure ambient noise component. Specifically, the device can use a reference signal of the currently playing audio signal and remove this reference signal from the sound signals acquired by the sound acquisition device using adaptive filtering or echo cancellation algorithms to obtain the ambient noise signal. Subsequently, the device can calculate the SPL of the ambient noise signal (e.g., calculate the A-weighted SPL) to obtain the real-time ambient noise SPL value. In addition, in this embodiment, the device can periodically acquire real-time ambient noise sound pressure values ​​at preset time intervals (e.g., every 100 milliseconds) to achieve real-time tracking of changes in ambient noise, and correct audio signals based on the real-time acquired ambient noise sound pressure values ​​to improve the quality of played audio.

[0104] Step S32: Based on the real-time ambient noise sound pressure level, perform gain correction on the processed audio signal to obtain the corrected audio signal.

[0105] Understandably, gain correction can be an operation that adjusts the amplitude of the processed audio signal; correspondingly, the corrected audio signal can be the audio signal obtained after gain correction of the processed audio signal. In this embodiment, the device can adaptively adjust the amplitude of the processed audio signal according to the real-time ambient noise sound pressure level to obtain the corrected audio signal, which can remain audible in a real-time ambient noise environment while its sound pressure level does not exceed the safe range.

[0106] In this embodiment, by adaptively adjusting the output amplitude of the processed audio signal when the ambient noise in the audio playback area changes, it is possible to avoid the processed audio signal being masked by the ambient noise and thus not being clearly heard by the target user due to excessive ambient noise. At the same time, it is also possible to avoid the processed audio signal output amplitude being too large due to insufficient ambient noise, which could damage the target user's hearing.

[0107] In its implementation, after obtaining the real-time ambient noise sound pressure level (MPL), the device determines a target gain value based on this value and performs amplitude adjustment on the processed audio signal according to the target gain value to obtain a corrected audio signal. Specifically, the device can determine the target gain value based on a preset range where the real-time ambient noise MPL falls. For example, when the MPL is in a first preset range, the device can set the target gain value to the gain value corresponding to the first volume range, ensuring that the MPL of the corrected audio signal remains within the first volume range when played in the audio playback area. When the MPL is in a second preset range, the device can adjust the target gain value according to the linear change in the MPL, ensuring that the MPL of the corrected audio signal increases linearly with the increase in the MPL, but does not exceed a preset volume threshold. When the MPL is in a third preset range, the device can set the target gain value to a lock value, locking the MPL of the corrected audio signal at the preset volume threshold when played in the audio playback area. After determining the target gain value, the device can multiply the amplitude of the processed audio signal by the target gain value to obtain the corrected audio signal.

[0108] It should be noted that the first, second, and third preset intervals can be three consecutive and non-overlapping numerical intervals pre-defined to define the range of real-time ambient noise sound pressure levels. The first preset interval can be the interval where the real-time ambient noise sound pressure level is low, for example, an interval where the real-time ambient noise sound pressure level is less than or equal to 70dB. Within the first preset interval, the ambient noise in the audio playback area is usually low, and the processed audio signal does not require significant gain boosting to be clearly audible to the target user. The second preset interval can be the interval where the real-time ambient noise sound pressure level is at a moderate level, for example, an interval where the real-time ambient noise sound pressure level is greater than 70dB and less than or equal to 80dB. Within the second preset interval, the ambient noise in the audio playback area begins to affect the audibility of the processed audio signal, therefore, the gain needs to be increased accordingly as the ambient noise increases. The third preset interval can be the numerical range where the real-time ambient noise sound pressure level is high, such as the range where the real-time ambient noise sound pressure level is greater than 80dB. Within the third preset interval, the ambient noise in the audio playback area is relatively high. If the gain is increased linearly, the sound pressure level of the corrected audio signal may exceed the safe range. Therefore, it is necessary to lock the sound pressure level of the corrected audio signal at the preset volume threshold to avoid damaging the hearing of the target user.

[0109] The step of playing the processed audio signal includes: Step S33: Play the corrected audio signal.

[0110] In this embodiment, the device acquires the real-time ambient noise sound pressure level of the audio playback area where the target user is located, and performs gain correction on the processed audio signal based on the real-time ambient noise sound pressure level to obtain the corrected audio signal. The corrected audio signal is then played, which allows the output amplitude of the processed audio signal to be adaptively adjusted when the ambient noise in the audio playback area where the target user is located changes dynamically. This avoids the processed audio signal being masked by excessive ambient noise and thus not being clearly perceived by the target user, while also avoiding the excessive amplification of the audio signal output amplitude due to insufficient ambient noise, which would place an additional burden on the target user's hearing. In this way, the device can effectively protect the user's hearing while ensuring audio quality.

[0111] Furthermore, after the step of playing the corrected audio signal, the method further includes: Step S41: During the playback of the corrected audio signal, the current playback duration of the corrected audio signal is obtained in real time.

[0112] It should be understood that the current playback duration can be the length of time elapsed from the moment the corrected audio signal began playing to the present moment. In this embodiment, the device can start an internal timer at the same time the corrected audio signal begins playing. This internal timer can continuously accumulate time from the moment the corrected audio signal begins playing at preset time intervals (e.g., every 1 second or every 100 milliseconds), and record the accumulated time value in real time as the current playback duration. During the subsequent playback of the corrected audio signal, the device can continuously read the current playback duration from the internal timer to achieve real-time monitoring of the playback duration.

[0113] Step S42: When the current playback duration reaches the first duration threshold, the corrected audio signal is attenuated a second time to obtain the target audio signal, and a transition audio signal of a preset duration is played.

[0114] It should be noted that the first duration threshold can be a pre-set critical value for the duration of the first level of volume control operation. It can be set according to the auditory physiological characteristics of the target user, the medical recommendations on the duration of auditory safety exposure, and the needs of the actual application scenario. For example, the first duration threshold can be set to 45 minutes.

[0115] It should be noted that secondary attenuation can be an operation that performs amplitude reduction processing on the corrected audio signal again. The amplitude of secondary attenuation can be a preset fixed attenuation amount (e.g., a reduction of 10dB), or it can be an attenuation amount dynamically determined based on the target user's hearing tolerance assessment value. This embodiment does not impose any restrictions on this. Accordingly, the target audio signal can be the audio signal obtained after the corrected audio signal has undergone secondary attenuation processing.

[0116] Understandably, the preset duration can be a pre-defined length of time used to play the transition audio signal. It can be set according to the needs of the actual application scenario; for example, the preset duration could be set to 3 minutes. Correspondingly, the transition audio signal can be an audio signal with a lower amplitude, a smoother envelope, or a more soothing timbre, such as soft music or natural sound effects. This provides the target user with an auditory buffer transition, avoiding auditory discomfort or startle caused by sudden volume changes due to secondary attenuation of the audio signal.

[0117] Step S43: After the transition audio signal has finished playing, play the target audio signal.

[0118] In its implementation, during the playback of the corrected audio signal, the device continuously compares the current playback duration with a first duration threshold. If the current playback duration reaches the first duration threshold, it can be determined that the current playback duration meets the conditions for triggering the first level of volume control. At this point, a secondary attenuation process can be performed on the corrected audio signal. Specifically, the device can obtain a preset secondary attenuation parameter (e.g., a -10dB gain coefficient) and multiply the overall amplitude of the corrected audio signal by this gain coefficient to obtain the audio signal after secondary attenuation, i.e., the target audio signal. Afterward, the device does not immediately play the target audio signal. Instead, it first obtains a transition audio signal of a preset duration stored in its internal storage module and plays this transition audio signal. Finally, after the transition audio signal has finished playing, the device begins playing the target audio signal.

[0119] In this embodiment, after the playback duration of the corrected audio signal reaches a first duration threshold, the device does not immediately reduce the volume abruptly. Instead, it plays a transitional audio signal of a preset duration to provide an auditory buffer for the user, thereby effectively avoiding auditory discomfort or startle caused by sudden volume changes. Simultaneously, this embodiment uses secondary attenuation to reduce the cumulative acoustic stimulation intensity caused by continuous audio signal playback on the target user's auditory system, thus ensuring the target user's auditory comfort while alleviating auditory fatigue.

[0120] Furthermore, after the step of acquiring the current playback duration of the corrected audio signal in real time, the method further includes: interrupting the playback of the corrected audio signal when the current playback duration reaches a second duration threshold; adjusting the corrected audio signal based on a preset limited gain and continuing to play the adjusted audio signal when the audio interruption duration reaches a preset silence duration; wherein the second duration threshold is greater than the first duration threshold.

[0121] It should be noted that the second duration threshold can be a pre-set critical value for the duration of triggering the second-level volume control operation, wherein the second duration threshold is greater than the first duration threshold. In this embodiment, similar to the first duration threshold, the second duration threshold can also be set according to the auditory physiological characteristics of the target user, medical recommendations regarding the duration of auditory safety exposure, and the needs of the actual application scenario. For example, the second duration threshold can be set to 90 minutes.

[0122] Understandably, the audio interruption duration can be the length of silence elapsed from the moment the corrected audio signal was interrupted until the current moment. Correspondingly, the preset silence duration can be a pre-defined minimum duration required for the corrected audio signal to be interrupted, for example, the preset silence duration can be set to 5 minutes.

[0123] In practical applications, when the current playback duration of the corrected audio signal reaches the second duration threshold, the device can interrupt playback. Simultaneously, an interrupt timer is started. This timer continuously increments at preset time intervals (e.g., every 1 second or every 100 milliseconds) from the moment playback is interrupted, recording the accumulated time value as the audio interruption duration in real time. During the interruption of the corrected audio signal's playback, the device can continuously read the audio interruption duration from the interrupt timer to achieve real-time monitoring of the interruption duration.

[0124] It should be noted that the preset limited gain can be a gain coefficient used to adjust the amplitude of the corrected audio signal after the audio interruption duration reaches a preset silence duration. It can be used to ensure that the output sound pressure level of the corrected audio signal after playback resumes does not exceed the target user's hearing safety range. In this embodiment, the preset limited gain can be set to a gain value corresponding to an output sound pressure level less than or equal to 75dB. For example, when the output sound pressure level of the corrected audio signal before playback interruption is 85dB, the preset limited gain can be set to a gain value that ensures the output sound pressure level after playback resumes is no higher than 75dB (i.e., an attenuation of approximately 10dB).

[0125] In its implementation, during the playback of the corrected audio signal, the device continuously compares the current playback duration with a first duration threshold and a second duration threshold. When the current playback duration reaches the first duration threshold, the device performs a first-level volume control operation (i.e., secondary attenuation processing); when the current playback duration further reaches the second duration threshold, the device performs a second-level volume control operation (i.e., interrupting playback of the corrected audio signal). During the interruption of playback of the corrected audio signal, the device continuously compares the audio interruption duration with a preset silence duration. When the audio interruption duration reaches the preset silence duration, it can be determined that the audio interruption duration meets the conditions for resuming playback, and at this time, the playback resumption operation can be performed. Specifically, the device can obtain a preset limited gain and multiply the amplitude of the corrected audio signal by the preset limited gain to obtain an adjusted audio signal. The output sound pressure level of this adjusted audio signal is usually lower than the output sound pressure level of the corrected audio signal before the playback interruption, so that after the target user's auditory system has rested for the preset silence duration, the audio signal can be restarted at a safer volume level.

[0126] In this embodiment, the device can forcibly interrupt audio playback when the duration of continuous audio signal listening by the target user reaches a second duration threshold, allowing the target user's auditory system a period of silent recovery without sound stimulation. This effectively avoids the cumulative damage to the target user's auditory system caused by prolonged continuous sound stimulation. Simultaneously, this embodiment resumes playback with a preset limited gain after the audio interruption duration reaches a preset silence period, ensuring that the output sound pressure level of the resumed audio signal is lower than the output sound pressure level before the interruption. This allows the audio service to continue at a safer volume level while ensuring the target user's auditory system receives sufficient rest, thereby improving the user's auditory experience.

[0127] Furthermore, this application also proposes an audio playback device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the audio playback method described above.

[0128] Furthermore, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the audio playback method described above.

[0129] In addition, refer to Figure 7 , Figure 7 This is a structural block diagram of the audio playback device of this application. Figure 7 As shown in the figure, this application also proposes an audio playback device, which includes: The sensitive frequency band determination module 701 is used to determine the auditory sensitive frequency band corresponding to the target user when playing an audio signal. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user. The signal extraction module 702 is used to extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; The audio playback module 703 is used to attenuate the audio signal components to obtain the processed audio signal, and to play the processed audio signal.

[0130] This embodiment can identify the hearing-sensitive frequency bands that would damage the hearing of target users with hearing tolerance below a preset standard when playing audio signals. It then extracts the audio signal components corresponding to these sensitive frequency bands from the audio signal, attenuates these components, and obtains and plays the processed audio signal. Compared to existing in-vehicle audio control methods that cannot provide differentiated audio control for hearing-sensitive users, this embodiment attenuates the audio signal components corresponding to the user's hearing-sensitive frequency bands in the currently playing audio signal, thereby achieving differentiated audio control for hearing-sensitive users and avoiding damage to their hearing.

[0131] Other embodiments or specific implementations of the audio playback device described in this application can be found in the above-described method embodiments, and will not be repeated here.

[0132] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0133] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0135] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. An audio playback method, characterized in that, The method includes: When playing an audio signal, determine the auditory sensitive frequency band corresponding to the target user. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user. Extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; The audio signal components are attenuated to obtain a processed audio signal, and the processed audio signal is played.

2. The method as described in claim 1, characterized in that, The step of determining the auditory sensitive frequency band corresponding to the target user when playing an audio signal includes: When playing an audio signal, the sensory feature data of all users in the current playback environment is acquired. The sensory feature data includes at least one of the following: bearing status data corresponding to the bearing location of the user, image feature data, and voiceprint feature data. Age attribute recognition is performed on the image feature data to obtain the first physiological characteristic parameters corresponding to the user; The voiceprint feature data is subjected to voiceprint attribute recognition to obtain the second physiological feature parameters corresponding to the user. Based on the bearer status data, the first physiological characteristic parameter and / or the second physiological characteristic parameter, a target user is determined from each of the users, and the auditory sensitive frequency band corresponding to the target user is determined.

3. The method as described in claim 2, characterized in that, The step of determining the target user from each of the users based on the bearer status data, the first physiological characteristic parameter, and / or the second physiological characteristic parameter includes: The carrying weight value corresponding to the user is determined based on the carrying status data, and a first weight corresponding to the carrying status data is generated based on the carrying weight value. A second weight corresponding to the first physiological feature parameter is generated based on the age attribute information in the first physiological feature parameter, and a third weight corresponding to the second physiological feature parameter is generated based on the voiceprint maturity information in the second physiological feature parameter. A hearing tolerance assessment value for each user is generated based on the first weight, the second weight, the bearing status data, and the first physiological characteristic parameter; or, a hearing tolerance assessment value for each user is generated based on the first weight, the third weight, the bearing status data, and the second physiological characteristic parameter; or, a hearing tolerance assessment value for each user is generated based on the first weight, the second weight, the third weight, the bearing status data, the first physiological characteristic parameter, and the second physiological characteristic parameter. Users whose auditory tolerance assessment value is lower than a preset threshold are identified as target users.

4. The method as described in claim 1, characterized in that, Before the step of playing the processed audio signal, the method further includes: Obtain the real-time ambient noise sound pressure level of the audio playback area where the target user is located; Based on the real-time ambient noise sound pressure level, the processed audio signal is gain-corrected to obtain the corrected audio signal. The step of playing the processed audio signal includes: Play the corrected audio signal.

5. The method as described in claim 4, characterized in that, After the step of playing the corrected audio signal, the method further includes: During the playback of the corrected audio signal, the current playback duration of the corrected audio signal is acquired in real time; When the current playback duration reaches the first duration threshold, the corrected audio signal is attenuated a second time to obtain the target audio signal, and a transition audio signal of a preset duration is played. Once the transition audio signal has finished playing, the target audio signal is played.

6. The method as described in claim 5, characterized in that, After the step of acquiring the current playback duration of the corrected audio signal in real time, the method further includes: If the current playback duration reaches the second duration threshold, the playback of the corrected audio signal will be interrupted. If the audio interruption duration reaches the preset silence duration, the corrected audio signal is adjusted based on the preset limited gain, and the adjusted audio signal continues to be played; wherein, the second duration threshold is greater than the first duration threshold.

7. The method as described in claim 1, characterized in that, The step of extracting the audio signal component corresponding to the auditory sensitive frequency band from the audio signal includes: Extract the auditory sensitive frequency band from the audio signal, and divide the auditory sensitive frequency band into several auditory sensitive sub-bands; Extract the audio signal sub-components corresponding to each of the aforementioned auditory sensitive sub-frequency bands; The step of attenuating the audio signal components to obtain the processed audio signal includes: Determine the preset attenuation parameters corresponding to each of the aforementioned auditory sensitive sub-bands; The corresponding audio signal sub-components are attenuated based on the preset attenuation parameters to obtain the processed audio signal.

8. An audio playback device, characterized in that, The device includes: The sensitive frequency band determination module is used to determine the auditory sensitive frequency band corresponding to the target user when playing an audio signal. The target user is a user whose auditory tolerance is lower than a preset standard, and the auditory sensitive frequency band is a frequency band that causes damage to the hearing of the target user. The signal extraction module is used to extract the audio signal component corresponding to the auditory sensitive frequency band from the audio signal; An audio playback module is used to attenuate the audio signal components to obtain a processed audio signal, and to play the processed audio signal.

9. An audio playback device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the audio playback method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the audio playback method as described in any one of claims 1 to 7.

Images