Audio playing method, vehicle-mounted terminal and storage medium

By calculating the waveform variations between the main audio and ambient audio, and dynamically adjusting audio playback, the problem that the existing technology cannot provide the best audio experience in different environments is solved, and high-quality audio playback in various environments is achieved.

CN119068902APending Publication Date: 2024-12-03BEIJING BENENDA INTELLIGENT CONTROL TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411226267.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing audio playback methods cannot effectively adapt to different environmental conditions, resulting in a huge discount in noisy or reverberating environments, and the best audio experience in various environments cannot be provided.

Method used

By obtaining the processing waveform diagram of the main audio and ambient audio, calculating the class characteristic parameters of the differential comparison frame and non-differential comparison frame, quantifying the waveform variation difference, obtaining the difference difference and non-differential difference, and then performing audio playback control, dynamic Regulate the amplitude of the main audio to reduce the impact of ambient noise.

Benefits of technology

It effectively improves the quality of audio playback, allowing users to enjoy the best audio effects under various environmental conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068902A_ABST
    Figure CN119068902A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of audio processing, and particularly discloses an audio playing method, a vehicle-mounted terminal and a storage medium, and the method comprises the steps: obtaining all group difference comparison frames and all group non-difference comparison frames based on a processing oscillogram of a main audio and a processing oscillogram of an environment audio, based on all types of feature parameters of all groups of difference comparison frames, all types of feature parameters of all groups of non-difference comparison frames and all types of feature parameters of calculation comparison frames, the difference distinction degree and the non-difference distinction degree of the calculation comparison frames are obtained, and based on the difference distinction degree and the non-difference distinction degree of the calculation comparison frames, the difference distinction degree and the non-difference distinction degree of the calculation comparison frames are obtained. And obtaining a regulation and control judgment result of the calculation comparison frame, and obtaining an audio playing control result at the current moment according to the regulation and control judgment result of the calculation comparison frame. According to the invention, the influence of environmental noise is effectively reduced by dynamically regulating and controlling the amplitude of the main audio, so that a user can enjoy the best audio effect under various environmental conditions.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of audio processing, and in particular to an audio playing method, a vehicle-mounted terminal and a storage medium. Background Art

[0002] At present, there are application demands in complex environments, especially in the fields of multimedia playback, conference systems, smart homes, and in-car entertainment systems. With the increasing popularity and complexity of these application scenarios, audio playback quality has become one of the key factors in user experience. However, in actual applications, audio playback is often interfered by a variety of environmental factors, such as background noise, echo, reverberation, etc. These factors will significantly reduce the clarity and intelligibility of the audio and affect the user's auditory experience. Traditional audio playback systems often cannot effectively adapt to different environmental conditions, such as noisy streets, quiet libraries, or conference rooms with reverberation. These different environments will have different effects on audio signals, resulting in a significant reduction in playback effects. Therefore, how to enable users to enjoy the best audio effects under various environmental conditions has become an urgent issue in the current audio playback field.

[0003] However, the existing audio playback method only calculates the target user's predicted total score for the audio to be played by integrating the first predicted score and the second predicted score, and automatically adjusts the playback order of the audio to be played based on the predicted total score. It does not consider effectively reducing the impact of environmental noise by dynamically adjusting the amplitude of the main audio, and does not enable users to enjoy the best audio effects under various environmental conditions. For example, the patent publication number is "CN116955692A" and the patent name is "An audio playback method, device, vehicle-mounted terminal and storage medium". The method includes the following steps: obtaining user preference information for audio information, and quantifying the preference information using a multi-level division method; constructing a quantization matrix, calculating the user similarity value between the target user and other users, and the audio similarity value between the currently playing audio and each audio to be played; determining multiple similar users of the target user, and determining multiple similar audios of the currently playing audio; calculating a first predicted score value of the target user for the audio to be played based on the user similarity value and the score value of the similar users for the audio to be played, and calculating a second predicted score value of the audio to be played based on the audio similarity value and the evaluation score value of the similar audio; integrating the first predicted score and the second predicted score to calculate the predicted total score of the target user for the audio to be played; and automatically adjusting the playback order of the audio to be played based on the predicted total score. However, this patent only calculates the target user's predicted total score for the audio to be played by integrating the first predicted score and the second predicted score, and automatically adjusts the playback order of the audio to be played based on the predicted total score. It does not consider effectively reducing the impact of environmental noise by dynamically controlling the amplitude of the main audio, and does not enable users to enjoy the best audio effects under various environmental conditions.

[0004] Therefore, the present invention proposes an audio playback method, a vehicle-mounted terminal and a storage medium. Summary of the invention

[0005] The present invention provides an audio playback method, a vehicle-mounted terminal and a storage medium, which are used to obtain all groups of difference comparison frames and all groups of non-difference comparison frames according to the processing waveform diagram of the main audio and the processing waveform diagram of the ambient audio, and obtain all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames according to each group of difference comparison frames and each group of non-difference comparison frames, so as to facilitate the subsequent calculation of difference distinction and non-difference distinction, and then obtain the difference distinction of the calculated comparison frame according to all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculated comparison frame, and compare the waveform changes of the main audio and the ambient audio in the calculated comparison frame and the waveform changes in the difference comparison frame. The degree of difference in the change situation is quantified, and the non-difference distinction of the calculated comparison frame is obtained according to all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculated comparison frames. The degree of difference between the waveform change of the main audio and the ambient audio in the calculated comparison frame and the waveform change in the non-difference comparison frame is quantified. According to the difference distinction and non-difference distinction of the calculated comparison frame, the regulation and judgment result of the calculated comparison frame is accurately obtained. According to the regulation and judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained, which effectively improves the audio playback quality and enables users to enjoy the best audio effect under various environmental conditions.

[0006] The present invention provides an audio playing method, comprising:

[0007] S1: obtaining a main audio acquisition waveform and an ambient audio acquisition waveform, and performing waveform correction on the main audio acquisition waveform and the ambient audio acquisition waveform to obtain a main audio processing waveform and an ambient audio processing waveform;

[0008] S2: based on the processing waveform of the main audio and the processing waveform of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained, and based on each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained;

[0009] S3: based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the non-difference discrimination of the calculation comparison frames, and based on the difference discrimination and non-difference discrimination of the calculation comparison frames, obtaining the control judgment result of the calculation comparison frames;

[0010] S4: Based on the control judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained.

[0011] Preferably, S1: obtaining a collection waveform of the main audio and a collection waveform of the ambient audio, and performing waveform correction on the collection waveform of the main audio and the collection waveform of the ambient audio to obtain a processing waveform of the main audio and a processing waveform of the ambient audio, including:

[0012] Obtain the amplitude of the main audio at each moment in a preset time period before the current moment, and use all moments of the main audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the main audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the acquisition points of the main audio, and connect all the acquisition points of the main audio in order from small to large according to the horizontal coordinate value to obtain the acquisition waveform of the main audio;

[0013] Obtain the amplitude of the ambient audio at each moment in a preset time period before the current moment, and use all moments of the ambient audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the ambient audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the collection points of the ambient audio, and connect all the collection points of the ambient audio in order from small to large according to the horizontal coordinate value to obtain the collection waveform of the ambient audio;

[0014] Waveform correction is performed on the collected waveform graph of the main audio and the collected waveform graph of the ambient audio to obtain the processed waveform graph of the main audio and the processed waveform graph of the ambient audio.

[0015] Preferably, waveform correction is performed on the collected waveform graph of the main audio and the collected waveform graph of the ambient audio to obtain the processed waveform graph of the main audio and the processed waveform graph of the ambient audio, including:

[0016] Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the main audio and all adjacent acquisition points is greater than a preset first threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the main audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the main audio;

[0017] The ordinate of each abnormal acquisition point of the acquisition waveform of the main audio is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point, to obtain a new main audio acquisition waveform, and the new main audio acquisition waveform is used as the processing waveform of the main audio;

[0018] Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the ambient audio and all adjacent acquisition points is greater than a preset second threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the ambient audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the ambient audio;

[0019] The ordinate of each abnormal acquisition point of the ambient audio acquisition waveform is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point to obtain a new ambient audio acquisition waveform, and the new ambient audio acquisition waveform is used as the ambient audio processing waveform.

[0020] Preferably, based on the processing waveform of the main audio and the processing waveform of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained, including:

[0021] Segmenting the processing waveform graph of the main audio and the processing waveform graph of the ambient audio according to a preset time width to obtain all segmented frames of the processing waveform graph of the main audio and all segmented frames of the processing waveform graph of the ambient audio;

[0022] Defining ordinal numbers of all the segmented frames of the processing waveform graph of the main audio and all the segmented frames of the processing waveform graph of the ambient audio in sequence according to the time sequence of the segmented frames, and treating the segmented frames of the processing waveform graph of the main audio and the segmented frames of the processing waveform graph of the ambient audio with the same ordinal definition as a group of comparison frames to obtain all groups of comparison frames;

[0023] Uniformly sampling the time period of each group of comparison frames based on a preset number of samples to obtain all sampling moments of each group of comparison frames, and based on all sampling moments of each group of comparison frames, the segmented frames of the processing waveform graph of the main audio, and the segmented frames of the processing waveform graph of the ambient audio, all sampling points of the segmented frames of the processing waveform graph of the main audio and all sampling points of the segmented frames of the processing waveform graph of the ambient audio of each group of comparison frames are obtained;

[0024] The difference between the ordinates of the sampling points of the segmented frames of the processing waveform graph of the main audio and the sampling points of the segmented frames of the processing waveform graph of the ambient audio, which have the same sampling time of each group of comparison frames, is taken as the comparison difference of the sampling time, the comparison difference with the largest value among the comparison differences of all sampling times of each group of comparison frames is taken as the first comparison difference of each group of comparison frames, and the comparison difference with the smallest value among the comparison differences of all sampling times of each group of comparison frames is taken as the second comparison difference of each group of comparison frames;

[0025] Determine whether the absolute value of the difference between the first comparison difference and the second comparison difference of each group of comparison frames is greater than a preset difference threshold. If so, the corresponding group of comparison frames is regarded as a group of difference comparison frames. Otherwise, the corresponding group of comparison frames is regarded as a group of non-difference comparison frames.

[0026] Preferably, based on each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained, including:

[0027] The square of the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average difference energy of each group of difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average amplitude difference of each group of difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of difference comparison frames;

[0028] The square of the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average difference energy of each group of non-difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average amplitude difference of each group of non-difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of non-difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of non-difference comparison frames;

[0029] The average difference energy, average amplitude difference and zero-crossing difference are regarded as characteristic parameters of all classes.

[0030] Preferably, S3: based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the non-difference discrimination of the calculation comparison frames, and based on the difference discrimination and non-difference discrimination of the calculation comparison frames, obtaining the control judgment result of the calculation comparison frames, including:

[0031] S301: taking the last group of comparison frames as the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, and obtaining the non-difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames;

[0032] S302: Determine whether the difference distinction of the calculated comparison frame is less than the non-difference distinction. If so, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame. Otherwise, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame.

[0033] Preferably, based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, the difference discrimination of the calculation comparison frames is obtained, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, the non-difference discrimination of the calculation comparison frames is obtained, including:

[0034]

[0035]

[0036] Among them, β is the difference discrimination of the calculated comparison frame, δ is the non-difference discrimination of the calculated comparison frame, n is the number of all groups of difference comparison frames, m is the number of all groups of non-difference comparison frames, A is the average difference energy of the calculated comparison frame, B is the average amplitude difference of the calculated comparison frame, C is the zero-crossing difference of the calculated comparison frame, S a is the sum of the average difference energies of all group difference comparison frames, S b is the sum of the average amplitude differences of all group difference comparison frames, S c is the sum of the zero-crossing differences of all group difference comparison frames, G a is the sum of the average difference energies of all groups of non-difference alignment frames, G b is the sum of the average amplitude differences of all groups of non-differential alignment frames, G c is the sum of the zero-crossing differences of all groups of non-difference comparison frames, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0037] Preferably, S4: obtaining the audio playback control result at the current moment based on the control judgment result of the calculated comparison frame, including:

[0038] When the result of the control judgment of the calculated comparison frame is that control is required, the maximum value of the amplitude of the main audio at all times within a preset time period before the current time is used as the control amplitude, and the amplitude of the main audio at the current time is adjusted to be the same as the control amplitude;

[0039] When the control judgment result of the calculated comparison frame is that no control is required, no processing is performed.

[0040] The present invention provides a vehicle-mounted terminal, which includes: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the vehicle-mounted terminal device executes the audio playback method as described in any one of Examples 1-8.

[0041] The present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the audio playback method described in any one of Examples 1-8 is implemented.

[0042] The beneficial effects of the present invention compared with the prior art are as follows: according to the processing waveform diagram of the main audio and the processing waveform diagram of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained; according to each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained, which is convenient for the subsequent calculation of difference distinction and non-difference distinction; further, according to all class feature parameters of all groups of difference comparison frames and all class feature parameters of calculation comparison frames, the difference distinction of calculation comparison frames is obtained, and the waveform changes of the main audio and the ambient audio in the calculation comparison frames and the waveform changes in the difference comparison frames are compared. The difference degree between the conditions is quantified, and the non-difference distinction of the calculated comparison frames is obtained according to all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculated comparison frames. The difference degree between the waveform changes of the main audio and the ambient audio in the calculated comparison frames and those in the non-difference comparison frames is quantified. According to the difference distinction and non-difference distinction of the calculated comparison frames, the regulation and judgment results of the calculated comparison frames are accurately obtained. According to the regulation and judgment results of the calculated comparison frames, the audio playback control result at the current moment is obtained, which effectively improves the audio playback quality and enables users to enjoy the best audio effects under various environmental conditions.

[0043] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structure specifically pointed out in the written application document.

[0044] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0046] Figure 1 This is a flow chart of an audio playback method in an embodiment of the present invention;

[0047] Figure 2 This is a specific flow chart of S3 in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0049] Embodiment 1:

[0050] The present invention provides an audio playback method, referring to Figure 1 ,include:

[0051] S1: obtaining a main audio acquisition waveform and an ambient audio acquisition waveform, and performing waveform correction on the main audio acquisition waveform and the ambient audio acquisition waveform to obtain a main audio processing waveform and an ambient audio processing waveform;

[0052] S2: based on the processing waveform of the main audio and the processing waveform of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained, and based on each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained;

[0053] S3: based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the non-difference discrimination of the calculation comparison frames, and based on the difference discrimination and non-difference discrimination of the calculation comparison frames, obtaining the control judgment result of the calculation comparison frames;

[0054] S4: Based on the control judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained.

[0055] In this embodiment, the acquisition waveform of the main audio is a waveform obtained by connecting all acquisition points of the main audio (the playback audio to which the audio playback method is applied).

[0056] In this embodiment, the collected waveform diagram of the ambient audio is a waveform diagram obtained by connecting all the collected points of the ambient audio (the audio reflecting the playback environment except the main audio).

[0057] In this embodiment, the waveform correction is a process of obtaining a processing waveform of the main audio and a processing waveform of the ambient audio based on a collection waveform of the main audio and a collection waveform of the ambient audio.

[0058] In this embodiment, the processed waveform diagram of the main audio is a waveform diagram obtained based on the collected waveform diagram of the main audio and can reflect the actual waveform condition of the main audio.

[0059] In this embodiment, the processing waveform of the ambient audio is a waveform obtained based on the collected waveform of the ambient audio, which can reflect the actual waveform of the ambient audio (the main audio playback environment, such as indoors, in a car, etc.).

[0060] In this embodiment, the difference comparison frames are comparison frames in which the waveform changes of the main audio and the ambient audio in all groups of comparison frames are obviously different within the time period corresponding to the difference comparison frames.

[0061] In this embodiment, the non-difference comparison frames are comparison frames in which there is no obvious difference in the waveform changes of the main audio and the ambient audio in all groups of comparison frames within the time period corresponding to the difference comparison frames.

[0062] In this embodiment, the difference distinction of the calculated comparison frames is a numerical value obtained based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculated comparison frames, which can characterize the degree of distinction between the waveform changes of the main audio and the ambient audio in the calculated comparison frames and the waveform changes in the difference comparison frames.

[0063] In this embodiment, the non-difference distinctiveness of the calculated comparison frames is a numerical value obtained based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculated comparison frames, which can characterize the degree of difference between the waveform changes of the main audio and the ambient audio in the calculated comparison frames and the waveform changes in the non-difference comparison frames.

[0064] In this embodiment, the control judgment result of the calculated comparison frame is a control judgment result of whether the amplitude of the main audio at the current moment needs to be controlled based on the difference distinction and non-difference distinction of the calculated comparison frame, wherein the control judgment result includes whether control is needed or not.

[0065] In this embodiment, the audio playback control result is an audio playback result obtained based on the regulation and judgment result of the calculated comparison frame.

[0066] The beneficial effects of the above technology are as follows: according to the processing waveform diagram of the main audio and the processing waveform diagram of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained; according to each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained, which is convenient for the subsequent calculation of difference distinction and non-difference distinction; further, according to all class feature parameters of all groups of difference comparison frames and all class feature parameters of calculation comparison frames, the difference distinction of calculation comparison frames is obtained, and there is a difference between the waveform changes of the main audio and the ambient audio in the calculation comparison frames and the waveform changes in the difference comparison frames. The difference degree of difference is quantified, and the non-difference distinction of the calculated comparison frames is obtained according to all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculated comparison frames. The difference degree between the waveform changes of the main audio and the ambient audio in the calculated comparison frames and those in the non-difference comparison frames is quantified. According to the difference distinction and non-difference distinction of the calculated comparison frames, the regulation and judgment results of the calculated comparison frames are accurately obtained. According to the regulation and judgment results of the calculated comparison frames, the audio playback control result at the current moment is obtained, which effectively improves the audio playback quality and enables users to enjoy the best audio effects under various environmental conditions.

[0067] Embodiment 2:

[0068] Based on Example 1, the audio playback method, S1: obtaining a collection waveform of the main audio and a collection waveform of the ambient audio, and performing waveform correction on the collection waveform of the main audio and the collection waveform of the ambient audio to obtain a processing waveform of the main audio and a processing waveform of the ambient audio, including:

[0069] Obtain the amplitude of the main audio at each moment in a preset time period before the current moment, and use all moments of the main audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the main audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the acquisition points of the main audio, and connect all the acquisition points of the main audio in order from small to large according to the horizontal coordinate value to obtain the acquisition waveform of the main audio;

[0070] Obtain the amplitude of the ambient audio at each moment in a preset time period before the current moment, and use all moments of the ambient audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the ambient audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the collection points of the ambient audio, and connect all the collection points of the ambient audio in order from small to large according to the horizontal coordinate value to obtain the collection waveform of the ambient audio;

[0071] Waveform correction is performed on the collected waveform graph of the main audio and the collected waveform graph of the ambient audio to obtain the processed waveform graph of the main audio and the processed waveform graph of the ambient audio.

[0072] In this embodiment, the preset time period is a preset time period for obtaining the amplitudes of the main audio and the ambient audio, and the preset time period is an integer multiple of a preset time width.

[0073] In this embodiment, each moment is a moment selected from a preset time period before the current moment, and the time length between each adjacent moment is the same.

[0074] The beneficial effects of the above technology are: according to the amplitude of the main audio and the ambient audio at each moment in a preset time period before the current moment, all the acquisition points of the main audio and the ambient audio are obtained, and then according to all the acquisition points of the main audio and the ambient audio, the acquisition waveform graph of the main audio and the acquisition waveform graph of the ambient audio are obtained; according to the acquisition waveform graph of the main audio and the acquisition waveform graph of the ambient audio, the processing waveform graph of the main audio and the processing waveform graph of the ambient audio are obtained. This embodiment gives in detail a specific method for drawing the acquisition waveform graph of the main audio and the acquisition waveform graph of the ambient audio.

[0075] Embodiment 3:

[0076] On the basis of Example 2, the audio playback method performs waveform correction on the collected waveform of the main audio and the collected waveform of the ambient audio to obtain the processed waveform of the main audio and the processed waveform of the ambient audio, including:

[0077] Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the main audio and all adjacent acquisition points is greater than a preset first threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the main audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the main audio;

[0078] The ordinate of each abnormal acquisition point of the acquisition waveform of the main audio is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point, to obtain a new main audio acquisition waveform, and the new main audio acquisition waveform is used as the processing waveform of the main audio;

[0079] Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the ambient audio and all adjacent acquisition points is greater than a preset second threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the ambient audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the ambient audio;

[0080] The ordinate of each abnormal acquisition point of the ambient audio acquisition waveform is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point to obtain a new ambient audio acquisition waveform, and the new ambient audio acquisition waveform is used as the ambient audio processing waveform.

[0081] In this embodiment, the preset first threshold is a pre-set vertical coordinate difference threshold for determining whether each acquisition point of the acquisition waveform of the main audio is an abnormal acquisition point.

[0082] In this embodiment, the preset second threshold is a pre-set vertical coordinate difference threshold for determining whether each acquisition point of the acquisition waveform of the ambient audio is an abnormal acquisition point.

[0083] In this embodiment, the abnormal acquisition point is a acquisition point in all acquisition points of the acquisition waveform of the main audio or the acquisition waveform of the ambient audio, indicating that data acquisition errors occur.

[0084] In this embodiment, the non-abnormal acquisition point is a acquisition point within all acquisition points of the acquisition waveform of the main audio or the acquisition waveform of the ambient audio, indicating that data acquisition is normal.

[0085] The beneficial effects of the above technology are: according to all the acquisition points of the acquisition waveform of the main audio and the preset first threshold, all the abnormal acquisition points and all the non-abnormal points of the acquisition waveform of the main audio are accurately obtained; according to all the acquisition points of the acquisition waveform of the ambient audio and the preset second threshold, all the abnormal acquisition points and all the non-abnormal points of the acquisition waveform of the ambient audio are accurately obtained; according to all the abnormal acquisition points and all the non-abnormal points of the acquisition waveform of the main audio and the ambient audio, the processing waveform of the main audio and the processing waveform of the ambient audio are obtained; this embodiment gives in detail a specific method for performing waveform correction on the acquisition waveform of the main audio and the acquisition waveform of the ambient audio to obtain the processing waveform of the main audio and the processing waveform of the ambient audio.

[0086] Embodiment 4:

[0087] On the basis of Example 1, the audio playback method obtains all groups of difference comparison frames and all groups of non-difference comparison frames based on the processing waveform diagram of the main audio and the processing waveform diagram of the ambient audio, including:

[0088] Segmenting the processing waveform graph of the main audio and the processing waveform graph of the ambient audio according to a preset time width to obtain all segmented frames of the processing waveform graph of the main audio and all segmented frames of the processing waveform graph of the ambient audio;

[0089] Defining ordinal numbers of all the segmented frames of the processing waveform graph of the main audio and all the segmented frames of the processing waveform graph of the ambient audio in sequence according to the time sequence of the segmented frames, and treating the segmented frames of the processing waveform graph of the main audio and the segmented frames of the processing waveform graph of the ambient audio with the same ordinal definition as a group of comparison frames to obtain all groups of comparison frames;

[0090] Uniformly sampling the time period of each group of comparison frames based on a preset number of samples to obtain all sampling moments of each group of comparison frames, and based on all sampling moments of each group of comparison frames, the segmented frames of the processing waveform graph of the main audio, and the segmented frames of the processing waveform graph of the ambient audio, all sampling points of the segmented frames of the processing waveform graph of the main audio and all sampling points of the segmented frames of the processing waveform graph of the ambient audio of each group of comparison frames are obtained;

[0091] The difference between the ordinates of the sampling points of the segmented frames of the processing waveform graph of the main audio and the sampling points of the segmented frames of the processing waveform graph of the ambient audio, which have the same sampling time of each group of comparison frames, is taken as the comparison difference of the sampling time, the comparison difference with the largest value among the comparison differences of all sampling times of each group of comparison frames is taken as the first comparison difference of each group of comparison frames, and the comparison difference with the smallest value among the comparison differences of all sampling times of each group of comparison frames is taken as the second comparison difference of each group of comparison frames;

[0092] Determine whether the absolute value of the difference between the first comparison difference and the second comparison difference of each group of comparison frames is greater than a preset difference threshold. If so, the corresponding group of comparison frames is regarded as a group of difference comparison frames. Otherwise, the corresponding group of comparison frames is regarded as a group of non-difference comparison frames.

[0093] In this embodiment, the preset time width is a preset time width used to divide the processing waveform graph of the main audio and the processing waveform graph of the ambient audio.

[0094] In this embodiment, the segmentation is performed by dividing the processing waveform graph of the main audio and the processing waveform graph of the ambient audio in the time domain according to a preset time width.

[0095] In this embodiment, the preset number of samples is a preset number of samples for uniformly sampling (time intervals between adjacent sampling moments are the same) the time period of each group of comparison frames (the time period of the time domain corresponding to each group of comparison frames).

[0096] In this embodiment, all sampling points of the segmented frames of the processing waveform diagram of the main audio of each group of comparison frames are acquisition points corresponding to all sampling moments in the segmented frames of the processing waveform diagram of the main audio of each group of comparison frames.

[0097] In this embodiment, all sampling points of the segmented frames of the processing waveform diagram of the ambient audio of each group of comparison frames are collection points corresponding to all sampling moments in the segmented frames of the processing waveform diagram of the ambient audio of each group of comparison frames.

[0098] In this embodiment, the preset difference threshold is a preset difference threshold used to determine whether each group of compared frames is a difference compared frame.

[0099] The beneficial effects of the above technology are: according to the processing waveform of the main audio, the processing waveform of the ambient audio and the preset time width, all group comparison frames are obtained, and then according to all group comparison frames, all group difference comparison frames and all group non-difference comparison frames are obtained. This embodiment gives in detail a specific method for obtaining all group difference comparison frames and all group non-difference comparison frames based on the processing waveform of the main audio and the processing waveform of the ambient audio.

[0100] Embodiment 5:

[0101] On the basis of Example 4, the audio playback method obtains all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames based on each group of difference comparison frames and each group of non-difference comparison frames, including:

[0102] The square of the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average difference energy of each group of difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average amplitude difference of each group of difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of difference comparison frames;

[0103] The square of the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average difference energy of each group of non-difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average amplitude difference of each group of non-difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of non-difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of non-difference comparison frames;

[0104] The average difference energy, average amplitude difference and zero-crossing difference are regarded as characteristic parameters of all classes.

[0105] In this embodiment, the average difference energy is the average value of the waveform difference (audio difference) variation energy between the main audio and the ambient audio in each group of difference comparison frames or each group of non-difference comparison frames during the time period corresponding to the difference comparison frames or non-difference comparison frames.

[0106] In this embodiment, the average amplitude difference is an average value reflecting the change in waveform difference (audio difference) between the main audio and the ambient audio in each group of difference comparison frames or each group of non-difference comparison frames during the time period corresponding to the difference comparison frames or non-difference comparison frames.

[0107] In this embodiment, the zero-crossing difference is the difference between the number of zero-crossings of the segmented frames of the processing waveform of the main audio in each group of difference comparison frames or each group of non-difference comparison frames (the number of times the processing waveform of the main audio passes through the zero point) and the number of zero-crossings of the segmented frames of the processing waveform of the ambient audio (the number of times the processing waveform of the ambient audio passes through the zero point).

[0108] The beneficial effect of the above technology is: according to each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained, which is convenient for the subsequent calculation of difference discrimination and non-difference discrimination.

[0109] Embodiment 6:

[0110] Based on Example 1, the audio playback method, S3: based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, obtain the difference distinction of the calculation comparison frames, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, obtain the non-difference distinction of the calculation comparison frames, based on the difference distinction and non-difference distinction of the calculation comparison frames, obtain the control judgment result of the calculation comparison frames, reference Figure 2 ,include:

[0111] S301: taking the last group of comparison frames as the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, and obtaining the non-difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames;

[0112] S302: Determine whether the difference distinction of the calculated comparison frame is less than the non-difference distinction. If so, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame. Otherwise, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame.

[0113] The beneficial effects of the above technology are: according to all class feature parameters of all groups of difference comparison frames, all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of calculated comparison frames, the difference discrimination and non-difference discrimination of the calculated comparison frames are obtained; according to the difference discrimination and non-difference discrimination of the calculated comparison frames, the control judgment result of the calculated comparison frames is accurately obtained. This embodiment gives in detail a specific method for obtaining the control judgment result of the calculated comparison frames according to the difference discrimination and non-difference discrimination of the calculated comparison frames.

[0114] Embodiment 7:

[0115] On the basis of Example 6, the audio playback method obtains the difference discrimination of the calculated comparison frame based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculated comparison frame, and obtains the non-difference discrimination of the calculated comparison frame based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculated comparison frame, including:

[0116]

[0117]

[0118] Among them, β is the difference discrimination of the calculated comparison frame, δ is the non-difference discrimination of the calculated comparison frame, n is the number of all groups of difference comparison frames, m is the number of all groups of non-difference comparison frames, A is the average difference energy of the calculated comparison frame, B is the average amplitude difference of the calculated comparison frame, C is the zero-crossing difference of the calculated comparison frame, S a is the sum of the average difference energies of all group difference comparison frames, S b is the sum of the average amplitude differences of all group difference comparison frames, S c is the sum of the zero-crossing differences of all group difference comparison frames, G a is the sum of the average difference energies of all groups of non-difference alignment frames, G b is the sum of the average amplitude differences of all groups of non-differential alignment frames, G c is the sum of the zero-crossing differences of all groups of non-difference comparison frames, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0119] The beneficial effects of the above technology are: according to all class feature parameters of all groups of difference comparison frames and all class feature parameters of calculation comparison frames, the difference distinction of calculation comparison frames is obtained, and the degree of difference between the waveform changes of main audio and ambient audio in calculation comparison frames and those in difference comparison frames is quantified; according to all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of calculation comparison frames, the non-difference distinction of calculation comparison frames is obtained, and the degree of difference between the waveform changes of main audio and ambient audio in calculation comparison frames and those in non-difference comparison frames is quantified. This embodiment gives in detail a specific method for quantifying the degree of difference between the waveform changes of main audio and ambient audio in calculation comparison frames and those in difference comparison frames or non-difference comparison frames.

[0120] Embodiment 8:

[0121] On the basis of Example 6, the audio playback method, S4: based on the control judgment result of the calculated comparison frame, obtain the audio playback control result at the current moment, including:

[0122] When the result of the control judgment of the calculated comparison frame is that control is required, the maximum value of the amplitude of the main audio at all times within a preset time period before the current time is used as the control amplitude, and the amplitude of the main audio at the current time is adjusted to be the same as the control amplitude;

[0123] When the control judgment result of the calculated comparison frame is that no control is required, no processing is performed.

[0124] The beneficial effect of the above technology is: according to the control judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained, which effectively improves the audio playback quality and enables users to enjoy the best audio effect under various environmental conditions.

[0125] Embodiment 9:

[0126] The present invention provides a vehicle-mounted terminal, which includes: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the vehicle-mounted terminal device executes the audio playback method as described in any one of Examples 1-8.

[0127] The beneficial effect of the above technology is: providing a vehicle-mounted terminal that can adjust the main audio playback parameters in real time based on audio analysis, so that users can enjoy the best audio effect under various environmental conditions.

[0128] Embodiment 10:

[0129] The present invention provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the audio playback method described in any one of Examples 1-8 is implemented.

[0130] In this embodiment, the computer-readable storage medium may be a tangible device that can maintain and store instructions used by the instruction execution device, such as an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, etc., specifically a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), etc.

[0131] The beneficial effect of the above technology is: providing a storage medium that can maintain and store instructions used by an instruction execution device.

[0132] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention, and the present invention is also intended to include these changes and modifications.

Claims

1. An audio playback method, characterized in that: include: S1: obtaining a main audio acquisition waveform and an ambient audio acquisition waveform, and performing waveform correction on the main audio acquisition waveform and the ambient audio acquisition waveform to obtain a main audio processing waveform and an ambient audio processing waveform; S2: based on the processing waveform of the main audio and the processing waveform of the ambient audio, all groups of difference comparison frames and all groups of non-difference comparison frames are obtained, and based on each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained; S3: based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, obtaining the non-difference discrimination of the calculation comparison frames, and based on the difference discrimination and non-difference discrimination of the calculation comparison frames, obtaining the control judgment result of the calculation comparison frames; S4: Based on the control judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained.

2. The audio playback method according to claim 1, characterized in that: S1: obtaining a main audio acquisition waveform and an ambient audio acquisition waveform, and performing waveform correction on the main audio acquisition waveform and the ambient audio acquisition waveform to obtain a main audio processing waveform and an ambient audio processing waveform, including: Obtain the amplitude of the main audio at each moment in a preset time period before the current moment, and use all moments of the main audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the main audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the acquisition points of the main audio, and connect all the acquisition points of the main audio in order from small to large according to the horizontal coordinate value to obtain the acquisition waveform of the main audio; Obtain the amplitude of the ambient audio at each moment in a preset time period before the current moment, and use all moments of the ambient audio in the preset time period before the current moment as the horizontal coordinate value, and use the amplitude of the ambient audio at the corresponding moment in the preset time period before the current moment as the vertical coordinate value, obtain all the collection points of the ambient audio, and connect all the collection points of the ambient audio in order from small to large according to the horizontal coordinate value to obtain the collection waveform of the ambient audio; Waveform correction is performed on the collected waveform graph of the main audio and the collected waveform graph of the ambient audio to obtain the processed waveform graph of the main audio and the processed waveform graph of the ambient audio.

3. The audio playback method according to claim 2, characterized in that: Performing waveform correction on the main audio acquisition waveform and the ambient audio acquisition waveform to obtain the main audio processing waveform and the ambient audio processing waveform, including: Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the main audio and all adjacent acquisition points is greater than a preset first threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the main audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the main audio; The ordinate of each abnormal acquisition point of the acquisition waveform of the main audio is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point, to obtain a new main audio acquisition waveform, and the new main audio acquisition waveform is used as the processing waveform of the main audio; Determine whether the ordinate difference between each acquisition point of the acquisition waveform of the ambient audio and all adjacent acquisition points is greater than a preset second threshold value, and if so, regard the corresponding acquisition point as an abnormal acquisition point of the acquisition waveform of the ambient audio; otherwise, regard the corresponding acquisition point as a non-abnormal acquisition point of the acquisition waveform of the ambient audio; The ordinate of each abnormal acquisition point of the ambient audio acquisition waveform is adjusted to the average of the ordinate values ​​of all non-abnormal acquisition points adjacent to the corresponding abnormal acquisition point to obtain a new ambient audio acquisition waveform, and the new ambient audio acquisition waveform is used as the ambient audio processing waveform.

4. The audio playback method according to claim 1, characterized in that: Based on the processing waveform of the main audio and the processing waveform of the ambient audio, all group difference comparison frames and all group non-difference comparison frames are obtained, including: Segmenting the processing waveform graph of the main audio and the processing waveform graph of the ambient audio according to a preset time width to obtain all segmented frames of the processing waveform graph of the main audio and all segmented frames of the processing waveform graph of the ambient audio; Defining ordinal numbers of all the segmented frames of the processing waveform graph of the main audio and all the segmented frames of the processing waveform graph of the ambient audio in sequence according to the time sequence of the segmented frames, and treating the segmented frames of the processing waveform graph of the main audio and the segmented frames of the processing waveform graph of the ambient audio with the same ordinal definition as a group of comparison frames to obtain all groups of comparison frames; Uniformly sampling the time period of each group of comparison frames based on a preset number of samples to obtain all sampling moments of each group of comparison frames, and based on all sampling moments of each group of comparison frames, the segmented frames of the processing waveform graph of the main audio, and the segmented frames of the processing waveform graph of the ambient audio, all sampling points of the segmented frames of the processing waveform graph of the main audio and all sampling points of the segmented frames of the processing waveform graph of the ambient audio of each group of comparison frames are obtained; The difference between the ordinates of the sampling points of the segmented frames of the processing waveform graph of the main audio and the sampling points of the segmented frames of the processing waveform graph of the ambient audio, which have the same sampling time of each group of comparison frames, is taken as the comparison difference of the sampling time, the comparison difference with the largest value among the comparison differences of all sampling times of each group of comparison frames is taken as the first comparison difference of each group of comparison frames, and the comparison difference with the smallest value among the comparison differences of all sampling times of each group of comparison frames is taken as the second comparison difference of each group of comparison frames; Determine whether the absolute value of the difference between the first comparison difference and the second comparison difference of each group of comparison frames is greater than a preset difference threshold. If so, the corresponding group of comparison frames is regarded as a group of difference comparison frames. Otherwise, the corresponding group of comparison frames is regarded as a group of non-difference comparison frames.

5. The audio playback method according to claim 4, characterized in that: Based on each group of difference comparison frames and each group of non-difference comparison frames, all class feature parameters of each group of difference comparison frames and all class feature parameters of each group of non-difference comparison frames are obtained, including: The square of the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average difference energy of each group of difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of difference comparison frames is regarded as the average amplitude difference of each group of difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of difference comparison frames; The square of the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average difference energy of each group of non-difference comparison frames, the mean of the comparison difference values ​​at all sampling moments of each group of non-difference comparison frames is regarded as the average amplitude difference of each group of non-difference comparison frames, and the difference between the number of zero crossings of the segmented frames of the processing waveform graph of the main audio of each group of non-difference comparison frames and the number of zero crossings of the segmented frames of the processing waveform graph of the ambient audio is regarded as the zero crossing difference of each group of non-difference comparison frames; The average difference energy, average amplitude difference and zero-crossing difference are regarded as characteristic parameters of all classes.

6. The audio playback method according to claim 1, characterized in that: S3: Based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, the difference discrimination of the calculation comparison frames is obtained, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, the non-difference discrimination of the calculation comparison frames is obtained, and based on the difference discrimination and non-difference discrimination of the calculation comparison frames, the control judgment result of the calculation comparison frames is obtained, including: S301: taking the last group of comparison frames as the calculation comparison frames, obtaining the difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, and obtaining the non-difference discrimination of the calculation comparison frames based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames; S302: Determine whether the difference distinction of the calculated comparison frame is less than the non-difference distinction. If so, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame. Otherwise, the need for adjustment is used as the adjustment judgment result of the calculated comparison frame.

7. The audio playback method according to claim 6, characterized in that: Based on all class feature parameters of all groups of difference comparison frames and all class feature parameters of the calculation comparison frames, the difference discrimination of the calculation comparison frames is obtained, and based on all class feature parameters of all groups of non-difference comparison frames and all class feature parameters of the calculation comparison frames, the non-difference discrimination of the calculation comparison frames is obtained, including: Among them, β is the difference discrimination of the calculated comparison frame, δ is the non-difference discrimination of the calculated comparison frame, n is the number of all groups of difference comparison frames, m is the number of all groups of non-difference comparison frames, A is the average difference energy of the calculated comparison frame, B is the average amplitude difference of the calculated comparison frame, C is the zero-crossing difference of the calculated comparison frame, S a is the sum of the average difference energies of all group difference comparison frames, S b is the sum of the average amplitude differences of all group difference comparison frames, S c is the sum of the zero-crossing differences of all group difference comparison frames, G a is the sum of the average difference energies of all groups of non-difference alignment frames, G b is the sum of the average amplitude differences of all groups of non-differential alignment frames, G c is the sum of the zero-crossing differences of all groups of non-difference comparison frames, ln is the natural logarithm, and the value of the natural constant e is 2.

718.

8. The audio playback method according to claim 6, characterized in that: S4: Based on the control judgment result of the calculated comparison frame, the audio playback control result at the current moment is obtained, including: When the result of the control judgment of the calculated comparison frame is that control is required, the maximum value of the amplitude of the main audio at all times within a preset time period before the current time is used as the control amplitude, and the amplitude of the main audio at the current time is adjusted to be the same as the control amplitude; When the control judgment result of the calculated comparison frame is that no control is required, no processing is performed.

9. A vehicle-mounted terminal, characterized in that: The vehicle-mounted terminal includes: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the vehicle-mounted terminal device executes the audio playback method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the audio playback method according to any one of claims 1 to 8 is implemented.