WO2021248521A1

WO2021248521A1 - Audio signal adjustment method and apparatus, computer device, and storage medium

Info

Publication number: WO2021248521A1
Application number: PCT/CN2020/096684
Authority: WO
Inventors: 吴锐兴; 田晓晖; 叶利剑
Original assignee: 瑞声声学科技(深圳)有限公司; 瑞声科技(新加坡)有限公司
Priority date: 2020-06-12
Filing date: 2020-06-18
Publication date: 2021-12-16
Also published as: CN111741406B; CN111741406A

Abstract

Disclosed in embodiments of the present application is an audio signal adjustment method, comprising: acquiring an excitation signal to be input to a micro speaker, and predicting a diaphragm amplitude produced when the excitation signal is input to the micro speaker; determining whether the diaphragm amplitude exceeds a preset amplitude threshold; if the diaphragm amplitude exceeds the preset amplitude threshold, determining, according to the diaphragm amplitude and the preset amplitude threshold, a target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; and using an equalizer algorithm to adjust the excitation signal according to the target adjustment gain to obtain a target audio signal, thereby avoiding airflow noise in the target audio signal, and preventing the subjective perception of fluctuations in loudness, thus increasing the degree of freedom of audio signal adjustment and improving the effect and efficiency of audio signal adjustment. In addition, also provided are an audio signal adjustment apparatus, a computer device, and a storage medium.

Description

Audio signal adjustment method, device, computer equipment and storage medium

Technical field

This application relates to the field of computer technology, and in particular to an audio signal adjustment method, device, computer equipment, and storage medium.

Background technique

The internal structure of the micro-speaker cavity is complicated and the space is small. The airflow turbulence caused by the vibration of the diaphragm can cause "sand" and "hissing" noise at certain frequencies. This situation is particularly serious when playing music under high voltage.

technical problem

At present, the commonly used audio signal adjustment method is partially solved by improving the structure of the speaker cavity or the internal material, but this method has a higher process cost, a longer period, and limited versatility. On the other hand, the dynamic range compression technology is used to control the excitation voltage to avoid airflow noise under excessively high voltage values. But this method can easily cause the sound to be loud and small, which affects the auditory perception. In view of this, there is an urgent need to provide a new audio signal adjustment method.

Technical solutions

In view of this, the present application provides an audio signal adjustment method, device, computer equipment, and storage medium, which are used to solve the problems of poor audio signal adjustment effect and low adjustment freedom in the prior art.

The specific technical solutions of the embodiments of this application are:

In a first aspect, an embodiment of the present application provides an audio signal adjustment method, and a micro speaker includes:

Acquiring an excitation signal to be input to the micro speaker, and predicting the vibration amplitude of the diaphragm generated when the excitation signal is input to the micro speaker;

Judging whether the amplitude of the diaphragm exceeds a preset amplitude threshold;

When the amplitude of the diaphragm exceeds the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold ；

An equalizer algorithm is used to adjust the excitation signal according to the target adjustment gain to obtain a target audio signal.

In a second aspect, an embodiment of the present application also provides an audio signal adjustment device, the device including:

An amplitude prediction module for obtaining an excitation signal to be input to the micro speaker, and predicting the vibration amplitude of the diaphragm generated when the excitation signal is input to the micro speaker;

A judging module for judging whether the amplitude of the diaphragm exceeds a preset amplitude threshold;

A gain determination module, configured to determine that the vibration diaphragm amplitude of the excitation signal is reduced to be less than the preset amplitude according to the vibration diaphragm amplitude and the preset amplitude threshold value when the vibration diaphragm amplitude exceeds the preset amplitude threshold value Target adjustment gain at threshold;

The signal adjustment module is used to adjust the excitation signal according to the target adjustment gain by using an equalizer algorithm to obtain a target audio signal.

In the third aspect, the embodiments of the present application also provide a computer device, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, The steps of the audio signal adjustment method described above are implemented.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, including computer instructions, which when run on a computer, cause the computer to execute the steps of the audio signal adjustment method described above.

Beneficial effect

Implementing the embodiments of this application will have the following beneficial effects:

After adopting the above audio signal adjustment method, device, computer equipment and storage medium, the excitation signal obtains the excitation signal to be input into the micro speaker, and calculates the diaphragm amplitude of the excitation signal; judges whether the diaphragm amplitude exceeds a preset Amplitude threshold; when the amplitude of the diaphragm exceeds the preset amplitude threshold, the excitation signal determines the target adjustment gain of the excitation signal according to the diaphragm amplitude and the preset amplitude threshold; the equalizer algorithm is used according to the target The gain is adjusted to adjust the excitation signal to obtain the target audio signal. The adjustment of the audio signal is realized by adopting the dynamic equalizer algorithm, and when adjusting the audio signal, since only the audio signal of the narrow frequency band that will produce airflow noise is processed, the overall volume is limited, so as to avoid sudden loudness to the greatest extent The phenomenon of sudden smallness is subjectively perceived, and at the same time, since the audio signal adjustment is determined according to the preset threshold value, the degree of freedom of audio signal adjustment is improved.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

in:

FIG. 1 is a schematic flowchart of the audio signal adjustment method in an embodiment;

FIG. 2 is a schematic flowchart of the method for predicting the amplitude of the diaphragm in an embodiment;

FIG. 3 is a schematic flowchart of the method for predicting the amplitude of the diaphragm in another embodiment;

FIG. 4 is a schematic flowchart of the method for determining the target adjustment gain in an embodiment;

FIG. 5 is a schematic flowchart of the method for determining the target adjustment gain in another embodiment;

FIG. 6 is a schematic flowchart of the audio signal adjustment method in another embodiment;

FIG. 7 is a schematic diagram of the structure of the audio signal adjusting device in an embodiment;

FIG. 8 is a schematic diagram of the internal structure of a computer device running the above audio signal adjustment method in an embodiment.

Embodiments of the present invention

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

In order to solve the traditional technology, the speaker cavity structure or internal material is improved, or the dynamic range compression technology is used to control the excitation voltage, to avoid airflow noise under excessively high voltage values, and the resulting audio signal is poorly adjusted, and the vertical and horizontal freedom is improved. The problem is not high.

Based on the above problems, in this embodiment, an audio signal adjustment method is specially proposed. The realization of the method can rely on a computer program, which can run on a computer system based on the von Neumann system.

As shown in FIG. 1, the audio signal adjustment method provided in this embodiment is applied to a micro speaker, and the audio signal adjustment method specifically includes the following steps:

Step 102: Obtain an excitation signal to be input to the micro speaker, and predict the vibration amplitude of the diaphragm generated by the excitation signal input to the micro speaker.

Among them, the excitation signal refers to the signal excitation source that is the music file (such as a song) played during the test, and the played audio signal is the input signal corresponding to the audio signal recorded by the microphone. Specifically, the signal excitation source can be determined in advance from the server, and the audio signal generated by the analog signal excitation source input into the micro speaker is used as the excitation signal. The diaphragm amplitude is the index data used to reflect the intensity of the airflow noise generated by the excitation signal. The larger the vibration diaphragm amplitude, the greater the intensity of the airflow noise generated by the excitation signal. Specifically, the amplitude of the diaphragm generated by the excitation signal input to the micro-speaker can be predicted by the speaker model, or the diaphragm amplitude generated by the input of the excitation signal into the micro-speaker can be predicted by a predictive model based on machine learning.

Step 104: Determine whether the amplitude of the diaphragm exceeds a preset amplitude threshold.

Wherein, the preset amplitude threshold refers to a preset threshold value of the diaphragm amplitude of the excitation signal used to determine whether airflow noise is generated. Specifically, the preset amplitude threshold can be determined by listening test combined with experimental measurement, that is, the lowest diaphragm amplitude of the airflow noise experienced by listening is set to the preset amplitude threshold, or it can pass a large-scale test by referring to the machine learning algorithm , Such as hidden Markov model, neural network, etc., determine the probability of airflow noise at different frequencies and different diaphragm amplitudes, dynamically change the amplitude threshold according to the probability of airflow noise, and set the diaphragm amplitude when the probability exceeds a specific value as the amplitude threshold Exemplarily, the probability value is 75%. When the preset amplitude threshold is set according to the probability, the greater the probability, the greater the risk of airflow noise. When the preset amplitude threshold is set to a smaller value, the airflow can be improved. The accuracy of noise prediction.

It is worth noting that, as a preference in this embodiment, the amplitude threshold can be dynamically changed according to the probability of occurrence of airflow noise, so that subsequent dynamic audio signal adjustments can be dynamically performed, and the accuracy and freedom of audio signal adjustments can be improved.

Step 106: When the diaphragm amplitude exceeds the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold.

Among them, the target adjustment gain refers to the magnification required for the diaphragm amplitude when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold. For example, when the diaphragm amplitude of the excitation signal is A, the ideal vibration corresponding to the excitation signal The film amplitude is a, and the target adjustment gain at this time is a/A. It is understandable that when the diaphragm amplitude exceeds the preset amplitude threshold, airflow noise will appear when the excitation signal is input to the micro-speaker. Therefore, in order to avoid the occurrence of airflow noise, the diaphragm amplitude of the excitation signal needs to be reduced to It is less than the preset amplitude threshold. Therefore, it is necessary to determine the corresponding target adjustment gain, so that the diaphragm amplitude of the excitation signal is determined to be accurately adjusted before the micro-speaker plays the excitation signal, so as to avoid the appearance of airflow noise.

Step 108: Use the equalizer algorithm to adjust the excitation signal according to the target adjustment gain to obtain the target audio signal.

Among them, the equalizer algorithm is a way to divide the frequency domain into frequency bands (such as dividing into 5, 10, 12, and 15 frequency bands) and apply corresponding gains to different frequency bands to change the frequency domain energy distribution of the original data. , An audio signal processing method that changes the subjective sense of hearing. The target audio signal refers to an audio signal in which air noise is hardly felt in the sense of hearing. Considering the characteristics of real-time processing, avoiding FFT (Fast Fourier Transform algorithm) switching to frequency domain processing and adopting time domain filtering, therefore, the equalizer in this embodiment is a parametric equalizer and a time domain equalizer. Specifically, the equalizer is at 20~20K The Hz frequency range is divided into 5, 10, 15, 20 or 30 frequency bands, and a gain corresponding to the target adjustment gain is applied to this frequency band to realize the adjustment of the excitation signal, and the adjusted excitation signal is input to the micro speaker, Play the target audio signal through the micro speaker.

Further, in this embodiment, since only the diaphragm amplitude of the excitation signal whose diaphragm amplitude exceeds the preset amplitude threshold is adjusted, the diaphragm amplitude of the excitation signal whose diaphragm amplitude exceeds the preset amplitude threshold is not adjusted. Adjustment, that is, only process the excitation signal in a narrow frequency band that will produce airflow noise, and has a limited impact on the overall volume. Therefore, it can avoid the subjective perception of the fluctuations of large and small phenomena to the greatest extent. Improve the effect and efficiency of audio signal adjustment. Moreover, since the preset diaphragm amplitude in this embodiment is determined dynamically, the adjustment of the excitation signal is also dynamically adjusted through the dynamic equalizer to obtain the target audio signal, thereby increasing the degree of freedom of audio signal adjustment.

The audio signal adjustment method described above obtains the excitation signal to be input to the micro speaker, and predicts the vibration amplitude of the diaphragm generated by the excitation signal input to the micro speaker; determines whether the diaphragm amplitude exceeds the preset amplitude threshold; when the diaphragm amplitude exceeds the preset amplitude threshold, According to the diaphragm amplitude and the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; use the equalizer algorithm to adjust the excitation signal according to the target adjustment gain to obtain the target audio signal to avoid In order to avoid airflow noise in the target audio signal, the audio signal is adjusted by adopting a dynamic equalizer algorithm. When adjusting the audio signal, since only the audio signal of a narrow frequency band that generates airflow noise is processed, it affects the overall volume. Limited, so as to avoid the phenomenon of fluctuations in large and small being subjectively perceived to the greatest extent, and at the same time, since the audio signal adjustment is determined according to the preset threshold, the freedom of audio signal adjustment and the effect and efficiency of audio signal adjustment are improved.

As shown in Fig. 2, in one embodiment, predicting the amplitude of the diaphragm generated by the excitation signal input to the micro speaker includes:

Step 102A: Extract audio parameters of the excitation signal;

Step 102B: Input the audio parameters into the preset loudspeaker model for prediction, and obtain the diaphragm amplitude.

Among them, the audio parameters refer to signal parameters related to the diaphragm amplitude in the excitation signal, such as frequency, diaphragm velocity, or diaphragm acceleration. Specifically, the audio parameters of the excitation signal can be extracted through a signal source and a signal analysis system. Then, the audio parameters are input into the preset speaker model, and the audio parameters are directly calculated through the preset speaker model, and the diaphragm amplitude is directly calculated. Understandably, by adopting the preset loudspeaker model, the diaphragm amplitude of the excitation signal can be easily and quickly predicted.

As shown in Figure 3, in one embodiment, predicting the amplitude of the diaphragm generated by the excitation signal input to the micro speaker includes:

Step 102C: Extract audio parameters of the excitation signal;

Step 102D: Obtain the diaphragm amplitude according to the preset amplitude prediction model trained based on the machine learning algorithm and according to the audio parameters.

In this embodiment, the audio parameters are consistent with the audio parameters in step 102A, and will not be repeated here. The amplitude prediction model is based on preset machine learning algorithms, such as hidden Markov models, neural networks, etc. This algorithm establishes the relationship between the audio parameters and the amplitude of the diaphragm, and uses the audio parameters as the input of the amplitude prediction model. The output of the amplitude prediction model is the diaphragm amplitude of the excitation signal.

As shown in FIG. 4, in one embodiment, determining the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold includes:

Step 106A: Determine the target amplitude according to the diaphragm amplitude and the preset amplitude threshold, and the target amplitude is less than the preset amplitude threshold;

Step 106B: Determine the target adjustment gain corresponding to the target amplitude through the built-in gain curve in the preset loudspeaker model.

Wherein, the target amplitude refers to the diaphragm amplitude of the excitation signal that can avoid the occurrence of airflow noise, and the target amplitude is less than a preset amplitude threshold. Specifically, the corresponding correction value may be determined in advance according to the diaphragm amplitude of the excitation signal, and then the difference between the preset amplitude threshold and the correction value may be determined as the target amplitude. The built-in gain curve in the preset loudspeaker model refers to the preset curve used to describe the change of the relationship between the amplitude of the diaphragm and the gain. In the gain curve, finding the gain corresponding to the target amplitude is the target adjustment gain.

As shown in FIG. 5, in one embodiment, determining the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold includes:

Step 106C: Determine the target amplitude according to the diaphragm amplitude and the preset amplitude threshold, where the target amplitude is less than the preset amplitude threshold;

Step 106D: Obtain the target adjustment gain through a preset gain calculation model based on machine learning and calculation according to the target amplitude.

The target amplitude in this embodiment is consistent with the target amplitude in step 106A, and will not be repeated here. The gain calculation model is based on a preset machine learning algorithm, such as hidden Markov model, neural network, etc. This algorithm establishes the relationship between the gain and the amplitude of the diaphragm, and uses the target amplitude as the input of the gain calculation model. The calculated model output is the target adjustment gain.

As shown in FIG. 6, in one embodiment, using an equalizer algorithm to adjust the excitation signal according to the target adjustment gain to obtain the target audio signal includes:

Step 108A: Obtain multiple filters and corresponding frequencies and energy included in the equalizer algorithm;

Step 108B: Calculate the quality factor of each filter according to the frequency and energy of each filter stage and the target adjustment gain;

Step 108C: Filter the excitation signal according to the quality factor of each filter to obtain the target audio signal.

Among them, the quality factor refers to the ratio of the mode of the gain corresponding to the cut-off frequency to the mode of the pass-band gain, which is used to reflect the shape of the amplitude-frequency characteristics of the low-pass filter at the cut-off frequency. The larger the quality factor, the narrower the filtering frequency band, and the better the filtering effect within the frequency band. Specifically, according to the frequency and energy of each filter stage, and the target adjustment gain, the quality factor of each filter is calculated. The calculation process can be through a built-in algorithm in the form of Q = A function of f (frequency, energy, gain), where Q represents the quality factor, and f is the function name of the built-in algorithm. The built-in algorithm for dynamically determining Q is an algorithm based on a speaker model or an algorithm based on a statistical model. According to the frequency, energy and gain, the corresponding quality factor can be calculated. According to the quality factor of each filter, the excitation signal is filtered to obtain the target audio signal, which realizes the narrow frequency band that generates airflow noise in the excitation signal. The excitation signal is filtered to realize the adjustment of the audio signal, and has a limited impact on the overall volume. It avoids the subjective perception of the fluctuation of the audio signal to the greatest extent, and improves the effect and efficiency of audio signal adjustment. And because the excitation signal is dynamically filtered according to the quality factor of each filter, the freedom of adjusting the audio signal is improved.

In one embodiment, the filter is an IIR filter or FIR filter.

Among them, the IIR filter is an infinite impulse response filter, and the FIR filter is a finite impulse response filter. The excitation signal is processed by the filter as an IIR filter or an FIR filter, and the time domain characteristics of the excitation signal can be obtained, thereby improving the real-time performance of audio signal adjustment.

It is worth noting that the order of the filter in this embodiment does not exceed 6 orders, thereby saving costs on the basis of ensuring the adjustment effect.

Based on the same application concept, an embodiment of the application provides an audio signal adjustment device 700, as shown in FIG. 7, including: an amplitude prediction module 702, configured to obtain an excitation signal to be input to the micro speaker, and predict the excitation signal Input the diaphragm amplitude generated by the micro-speaker; the determining module 704 is used to determine whether the amplitude of the diaphragm exceeds the preset amplitude threshold; the gain determining module 706 is used to when the amplitude of the diaphragm exceeds the preset amplitude threshold, According to the diaphragm amplitude and the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; the signal adjustment module 708 is configured to use an equalizer algorithm according to The target adjustment gain adjusts the excitation signal to obtain a target audio signal.

Specifically, the audio signal adjustment device 700 of this embodiment, as shown in FIG. 7, includes: an amplitude prediction module 702, configured to obtain an excitation signal to be input to the micro speaker, and predict that the excitation signal is input to the micro speaker Generated vibration diaphragm amplitude; judging module 704, used to determine whether the vibration diaphragm amplitude exceeds a preset amplitude threshold; gain determination module 706, when the vibration diaphragm amplitude exceeds the preset amplitude threshold, according to the diaphragm The amplitude and the preset amplitude threshold are used to determine the target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; the signal adjustment module 708 is configured to adjust the gain according to the target by using an equalizer algorithm The excitation signal is adjusted to obtain the target audio signal. Since it only processes audio signals in a narrow frequency band that will produce airflow noise, it has limited impact on the overall volume, so as to avoid the subjective perception of fluctuations in large and small phenomena. At the same time, it is determined whether to perform audio signals according to a preset threshold. Adjustment improves the freedom of audio signal adjustment and the effect and efficiency of audio signal adjustment.

It should be noted that the realization of the audio signal adjustment device in this embodiment is consistent with the realization idea of the aforementioned audio signal adjustment method, and its realization principle will not be repeated here. For details, please refer to the corresponding content in the aforementioned method.

Fig. 8 shows an internal structure diagram of a computer device in an embodiment. The computer device may specifically be a server or a terminal. As shown in FIG. 8, the computer device 800 includes a processor 810, a memory 820, and a network interface 830 connected through a system bus. Among them, the memory 820 includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system, and may also store a computer program. When the computer program is executed by the processor, the processor can implement the audio signal adjustment method. A computer program may also be stored in the internal memory, and when the computer program is executed by the processor, the processor can execute the audio signal adjustment method. Those skilled in the art can understand that the structure shown in FIG. 8 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer components than shown in FIG. 8, or combining certain components, or having a different component arrangement.

In an embodiment, the audio signal adjustment method provided in the present application can be implemented in the form of a computer program, and the computer program can be run on a computer device as shown in FIG. 8. The memory of the computer device can store various program modules that make up the audio signal adjustment device. For example, the amplitude prediction module 702, the judgment module 704, the gain determination module 706, and the signal adjustment module 708.

A computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the following steps: Obtain an excitation signal to be input to the micro speaker , And predict the diaphragm amplitude generated by the excitation signal input to the micro speaker; determine whether the diaphragm amplitude exceeds a preset amplitude threshold; when the diaphragm amplitude exceeds the preset amplitude threshold, according to the diaphragm amplitude And the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; adjust the excitation signal according to the target adjustment gain by using an equalizer algorithm, Obtain the target audio signal.

In one embodiment, predicting the amplitude of the diaphragm generated by the excitation signal input to the micro speaker includes: extracting audio parameters of the excitation signal; inputting the audio parameters into a preset speaker model for prediction, and obtaining The amplitude of the diaphragm.

In one embodiment, predicting the amplitude of the diaphragm generated by the excitation signal input to the micro speaker includes: extracting the audio parameters of the excitation signal; using a preset amplitude prediction model trained based on a machine learning algorithm and according to the The audio parameter is used to obtain the vibration diaphragm amplitude.

In one embodiment, determining the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold includes: according to the vibration The film amplitude and the preset amplitude threshold determine a target amplitude, and the target amplitude is less than the preset amplitude threshold; the target adjustment gain corresponding to the target amplitude is determined through a gain curve built into the preset speaker model.

In one embodiment, determining the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold includes: according to the vibration The film amplitude and the preset amplitude threshold determine a target amplitude, and the target amplitude is less than the preset amplitude threshold; the target adjustment gain is calculated by a preset gain calculation model based on machine learning and calculated according to the target amplitude.

In one embodiment, using an equalizer algorithm to adjust the excitation signal according to the target adjustment gain to obtain a target audio signal includes: obtaining multiple filters included in the equalizer algorithm and corresponding frequencies and energy Calculate the quality factor of each filter according to the frequency and energy of each filter stage and the target adjustment gain; filter the excitation signal according to the quality factor of each filter to obtain the target audio signal.

In one embodiment, the filter is an IIR filter or FIR filter.

A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is characterized in that, when the computer program is executed by a processor, the following steps are implemented: obtaining an excitation signal to be input to the micro-speaker, and predicting The excitation signal is input to the diaphragm amplitude generated by the micro-speaker; it is determined whether the diaphragm amplitude exceeds a preset amplitude threshold; when the diaphragm amplitude exceeds the preset amplitude threshold, according to the diaphragm amplitude and the The preset amplitude threshold is used to determine the target adjustment gain when the diaphragm amplitude of the excitation signal is reduced to less than the preset amplitude threshold; the equalizer algorithm is used to adjust the excitation signal according to the target adjustment gain to obtain the target audio Signal.

In one embodiment, the filter is an IIR filter or FIR filter.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage medium. Here, when the program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and/or volatile memory. Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not a limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The above-disclosed are only the preferred embodiments of the application, and of course the scope of rights of the application cannot be limited by this. Therefore, equivalent changes made in accordance with the claims of the application still fall within the scope of the application.

Claims

An audio signal adjustment method, characterized in that it is applied to a micro speaker, and the method includes:

Acquiring an excitation signal to be input to the micro speaker, and predicting the vibration amplitude of the diaphragm generated when the excitation signal is input to the micro speaker;

Judging whether the amplitude of the diaphragm exceeds a preset amplitude threshold;

When the amplitude of the diaphragm exceeds the preset amplitude threshold, determine the target adjustment gain when the diaphragm amplitude of the excitation signal decreases to less than the preset amplitude threshold according to the diaphragm amplitude and the preset amplitude threshold ；

An equalizer algorithm is used to adjust the excitation signal according to the target adjustment gain to obtain a target audio signal.
5. The audio signal adjustment method according to claim 1, wherein said predicting the amplitude of the diaphragm generated by the input of the excitation signal into the micro speaker comprises:

Extract the audio parameters of the excitation signal;

The audio parameters are input into a preset loudspeaker model for prediction, and the diaphragm amplitude is obtained.
5. The audio signal adjustment method according to claim 1, wherein said predicting the amplitude of the diaphragm generated by the input of the excitation signal into the micro speaker comprises:

Extract the audio parameters of the excitation signal;

Obtain the diaphragm amplitude according to a preset amplitude prediction model trained based on a machine learning algorithm and according to the audio parameters.
2. The audio signal adjustment method of claim 1, wherein the vibration amplitude of the excitation signal is determined to be less than the preset amplitude threshold according to the vibration diaphragm amplitude and the preset amplitude threshold. The target adjustment gain includes:

Determining a target amplitude according to the diaphragm amplitude and the preset amplitude threshold, where the target amplitude is less than the preset amplitude threshold;

The target adjustment gain corresponding to the target amplitude is determined by a gain curve built into the preset speaker model.
2. The audio signal adjustment method of claim 1, wherein the vibration amplitude of the excitation signal is determined to be less than the preset amplitude threshold according to the vibration diaphragm amplitude and the preset amplitude threshold. The target adjustment gain includes:

Determining a target amplitude according to the diaphragm amplitude and the preset amplitude threshold, where the target amplitude is less than the preset amplitude threshold;

The target adjustment gain is obtained through a preset gain calculation model based on machine learning and calculated according to the target amplitude.
5. The audio signal adjustment method according to claim 1, wherein said using an equalizer algorithm to adjust said excitation signal according to said target adjustment gain to obtain a target audio signal comprises:

Acquiring multiple filters and corresponding frequencies and energies included in the equalizer algorithm;

Calculate the quality factor of each filter according to the frequency and energy of each filter stage and the target adjustment gain;

According to the quality factor of each filter, the excitation signal is filtered to obtain the target audio signal.
8. The audio signal adjustment method of claim 6, wherein the filter is an IIR filter or an FIR filter.
An audio signal adjustment device, characterized in that the device includes:

An amplitude prediction module for obtaining an excitation signal to be input to the micro speaker, and predicting the vibration amplitude of the diaphragm generated when the excitation signal is input to the micro speaker;

A judging module for judging whether the amplitude of the diaphragm exceeds a preset amplitude threshold;

A gain determination module, configured to determine that the vibration diaphragm amplitude of the excitation signal is reduced to be less than the preset amplitude according to the vibration diaphragm amplitude and the preset amplitude threshold value when the vibration diaphragm amplitude exceeds the preset amplitude threshold value Target adjustment gain at threshold;

The signal adjustment module is used to adjust the excitation signal according to the target adjustment gain by using an equalizer algorithm to obtain a target audio signal.
A computer device, characterized in that it includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the rights when the computer program is executed. The steps of the audio signal adjustment method described in any one of 1 to 7 are required.
A computer-readable storage medium, characterized by comprising computer instructions, which when run on a computer, causes the computer to execute the steps of the audio signal adjustment method according to any one of claims 1 to 7.