Method and hearing device for automatically adjusting sounding gain based on PID (Proportion Integration Differentiation)

Abstract

The invention relates to a method and hearing equipment for automatically adjusting sound production gain based on PID, and the method comprises the steps: obtaining a sound signal collected by a built-in microphone of an audiometer, converting the sound signal to obtain the spectrum data of the sound signal, and enabling the sound signal to be a sound production signal to be adjusted; presetting a target sound production signal and a gain parameter of the target sound production signal, and extracting a spectrum feature of a to-be-adjusted sound production signal from the spectrum data according to the spectrum feature of the target sound production signal; training to obtain a frequency point identification model and a sounding gain prediction model; inputting the extracted spectrum features of the to-be-adjusted sounding signal into a frequency point identification model, and identifying to form a frequency point set of the to-be-adjusted sounding signal; and dynamically adjusting the gain of each frequency point in the frequency point set by using a PID technology, so that the sounding signal to be adjusted is infinitely close to the gain parameter of the target sounding signal. Therefore, the smooth target sounding signal is obtained, and the technical problem that the target sounding signal cannot be accurately controlled is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of audio control, and in particular, relates to a method for automatically adjusting vocalization gain based on PID and a hearing device. Background Art

[0002] During the hearing test, the audiometer needs to accurately control the gain of the sound to ensure the accuracy of the test results. However, due to the differences in the earphone devices of the audiometer, the sound signal emitted is often mixed with interference signals, which is different from the target sound signal and interferes with the user's judgment of the hearing test. Therefore, it is necessary to perform gain processing on the sound signal emitted.

[0003] Specifically, while the audiometer is outputting sound, it collects sound in real time through the built-in microphone and calculates the current actual vocal gain based on the collected sound signal. Ideally, the audiometer should automatically adjust the gain of the output sound based on the difference between the calculated actual vocal gain and the target gain to achieve precise vocal control. However, due to the influence of the vocal signal to be adjusted, the intensity and spectral characteristics of the sound signal collected by the audiometer have changed, making it impossible to accurately calculate the actual vocal gain. This causes errors in the automatic gain adjustment function of the audiometer, which is unable to provide subjects with stable and consistent hearing test sounds, ultimately affecting the accuracy of the test results.

[0004] Therefore, in the process of automatically adjusting the vocal gain, the audiometer faces the technical challenge of how to accurately separate the normal vocal signal from the complex sound environment. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method and a hearing device for automatically adjusting the vocal gain based on PID.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for automatically adjusting sound gain based on PID, comprising the following steps:

[0008] Acquire a sound signal collected by a built-in microphone of the audiometer, and convert it to obtain spectrum data of the sound signal, wherein the sound signal is a sound signal to be adjusted;

[0009] Preset a target sound signal and a gain parameter of the target sound signal, and extract the spectrum characteristics of the sound signal to be adjusted from the spectrum data according to the spectrum characteristics of the target sound signal;

[0010] Constructing a mapping relationship between the spectral characteristics of the to-be-adjusted vocalization signal and the to-be-adjusted vocalization type, as well as a mapping relationship between the spectral characteristics of the target vocalization signal and the vocalization gain, and training to obtain a frequency point recognition model and a vocalization gain prediction model;

[0011] Inputting the extracted frequency spectrum features of the sound signal to be adjusted into a frequency point recognition model to identify a frequency point set that forms the sound signal to be adjusted;

[0012] The PID technology is used to dynamically adjust the gain of each frequency point in the frequency point set, so that the sound signal to be adjusted is infinitely close to the gain parameter of the target sound signal.

[0013] Furthermore, the construction of the mapping relationship between the spectral characteristics of the to-be-adjusted sound signal and the to-be-adjusted sound type, and the mapping relationship between the spectral characteristics of the target sound signal and the sound gain, further includes the following steps:

[0014] By constructing a mapping relationship between the spectral characteristics of the sound signal to be adjusted and the sound type to be adjusted, the support vector machine algorithm is used for training to obtain a frequency point recognition model. According to the mapping relationship between the spectral characteristics of the target sound signal and the sound gain, a sound gain prediction model is obtained to determine the frequency point set and predict the sound gain.

[0015] Furthermore, after the extracted frequency spectrum feature of the sound signal to be adjusted is input into the frequency point recognition model and the frequency point set in the sound signal is recognized, the method further includes:

[0016] The extracted spectral features of the target vocalization signal are input into the vocalization gain prediction model to predict the current actual vocalization gain;

[0017] By extracting the spectral features of the sound signal to be adjusted and the spectral features of the normal sound signal in the sound signal, the spectral features of the sound signal to be adjusted are input into the frequency point recognition model to identify the frequency point set, and the spectral features of the target sound signal are input into the sound gain prediction model to obtain the current actual sound gain.

[0018] Furthermore, after identifying the frequency point set, the corresponding frequency point elimination algorithm is obtained from the preset frequency point library according to the identified frequency point set, and the sound signal is processed using the frequency point elimination algorithm. The control parameters of the PID algorithm are fine-tuned for different frequency point sets, and the frequency point of the sound signal to be adjusted is dynamically adjusted.

[0019] Furthermore, the difference between the target gain of the current sound output by the audiometer and the predicted actual phonation gain is calculated. If the difference between the two exceeds a preset threshold, it is determined that there is a deviation in the current phonation gain control and automatic adjustment is required.

[0020] Furthermore, according to the difference between the actual phonation gain and the target gain, a gradient descent algorithm is used to optimize and solve the phonation gain control parameter of the audiometer to obtain the target phonation gain control parameter value.

[0021] Furthermore, an error function is constructed according to the difference between the actual vocalization gain and the target gain, and the control parameters are iteratively optimized using a gradient descent algorithm. The optimal vocalization gain control parameter value is obtained through parameter updating and convergence judgment.

[0022] Furthermore, the target utterance gain control parameter value is set in the audiometer, and automatic gain control is performed on the output sound of the audiometer.

[0023] On the other hand, the present invention also discloses a hearing device for automatically adjusting the sound gain based on PID, comprising a microphone array, a speaker and a processor, wherein the microphone array and the speaker are electrically connected to the processor respectively;

[0024] The processor is used to execute the steps of the aforementioned method for automatically adjusting the sound gain based on PID.

[0025] Beneficial effects of the present invention:

[0026] The present invention provides a method for automatically adjusting the sound gain based on PID, which identifies the frequency point set in the sound signal, and dynamically adjusts the gain of each frequency point in the frequency point set using PID technology, so as to ensure that when the audiometer judges the hearing condition of the subject, the sound signal to be adjusted is a target sound signal that approaches a smoothness, thus solving the technical problem that the target sound signal cannot be accurately controlled. Thus, reliable test results are provided, which is of great significance for accurately evaluating the hearing health of the subject and for timely discovering and diagnosing hearing diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 This is a flowchart of the overall steps of a method for automatically adjusting the sound gain based on PID in an embodiment of the present invention;

[0029] Figure 2 This is a flowchart of the specific steps of step S3 in an embodiment of the present invention;

[0030] Figure 3 4 is a flowchart of the specific steps of step S4 in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] PID control is a feedback control technology widely used in industrial control systems. The PID controller calculates the error between the set value and the current value and adjusts the control input according to the error to achieve stable and precise control of the system.

[0033] The performance of the controller is optimized by adjusting the proportional gain Kp, integral gain Ki and differential gain Kd to achieve the goals of fast response, reducing steady-state error and improving system stability.

[0034] A method for automatically adjusting the sound gain based on PID, such as Figure 1 As shown, the following steps are included:

[0035] Step S1, obtaining a sound signal collected by a built-in microphone of an audiometer, and converting it to obtain spectrum data of the sound signal, wherein the sound signal is a sound signal to be adjusted;

[0036] Step S2, presetting a target sound signal and a gain parameter of the target sound signal, and extracting a spectrum feature of the sound signal to be adjusted from the spectrum data according to the spectrum feature of the target sound signal;

[0037] Step S3, constructing a mapping relationship between the spectral characteristics of the to-be-adjusted utterance signal and the to-be-adjusted utterance type, and a mapping relationship between the spectral characteristics of the target utterance signal and the utterance gain, and training to obtain a frequency point recognition model and a utterance gain prediction model;

[0038] Step S4, inputting the extracted frequency spectrum features of the sound signal to be adjusted into a frequency point recognition model to identify a frequency point set forming the sound signal to be adjusted;

[0039] Step S5: dynamically adjust the gain of each frequency point in the frequency point set by using PID technology, so that the sound signal to be adjusted is infinitely close to the gain parameter of the target sound signal.

[0040] The basic idea of ​​the present application to automatically adjust the sound gain based on the PID control algorithm is to use a PID controller to dynamically adjust the gain so that the sound output reaches the set target value, including the target volume or sound quality.

[0041] In the hearing test, the sound signal to be adjusted may interfere with the subject's perception of the audio signal. The PID controller can be used to monitor the level of the sound signal to be adjusted and adjust the strength of the audio signal according to the real-time situation. By real-time detection and compensation of the sound signal to be adjusted, it is ensured that the provided test signal can effectively exceed the sound signal to be adjusted and improve the signal-to-noise ratio (SNR). The specific steps are as follows:

[0042] Set target vocalization signals according to the test environment;

[0043] Using a microphone or other sensor to monitor the volume of the sound signal to be adjusted in real time, and inputting the volume of the background sound signal to be adjusted into the PID controller as feedback;

[0044] The PID controller calculates the error between the current noise level and the target noise level and adjusts the intensity of the audio signal.

[0045] By effectively compensating for frequency, errors can be reduced and the credibility of hearing test results can be improved. At the same time, hearing tests conducted by subjects in a quieter environment will be more accurate and can avoid the discomfort caused by noise interference. By applying PID control technology, the audiometer can better adapt to the test environment and dynamically adjust the signal output, thereby effectively compensating for background frequency and achieving more accurate hearing tests.

[0046] During the test, the intensity of the sound signal to be adjusted in the environment is continuously monitored and analyzed so that the change in sound can be adjusted in real time to ensure the best performance under actual working conditions.

[0047] Specifically, the PID control technology used in the embodiments of the present application specifically includes: adjusting the relationship between the sound emission time and the idle time, adjusting the change in the sound emission, etc. For example, a frequency spectrum of the sound emission signal to be adjusted identifies that there are 100 frequency point sets in the sound emission signal to be adjusted, then the relationship between the sound emission time and the idle time and the change in the sound emission are adjusted for each of the 100 frequency point sets, and the process of adjusting each frequency point set is a closed loop, that is, the target sound emission signal is obtained by 100 PID adjustment algorithms. Among them, a frequency spectrum of the sound emission signal to be adjusted forms a frequency point set according to actual conditions, for example, a frequency point set can be composed of 1K, 2K, 3K...100K, or a frequency point set can be composed of 1K, 5K, 10K...100K.

[0048] Build a feedback system to record the results and environmental conditions of each test so that the denoising algorithm can be further optimized based on historical data.

[0049] Further, in a preferred embodiment of the present application, in step S3, the mapping relationship between the spectral characteristics of the to-be-adjusted sound signal and the to-be-adjusted sound type, and the mapping relationship between the spectral characteristics of the target sound signal and the sound gain are constructed, such as Figure 2 As shown, the following steps are also included:

[0050] Step S301, by constructing a mapping relationship between the frequency spectrum characteristics of the sound signal to be adjusted and the sound type to be adjusted, a support vector machine algorithm is used for training to obtain a frequency point recognition model;

[0051] Step S302: According to the mapping relationship between the frequency spectrum characteristics of the target utterance signal and the utterance gain, a utterance gain prediction model is obtained to determine the frequency point set and predict the utterance gain.

[0052] Further, in a preferred embodiment of the present application, in step S4, the extracted spectral features of the sound signal to be adjusted are input into the frequency point recognition model, and after the frequency point set in the sound signal is recognized, Figure 3 As shown, it also includes:

[0053] Step S401: input the extracted spectrum features of the target vocalization signal into a vocalization gain prediction model to predict the current actual vocalization gain;

[0054] Step S402: extract the spectral features of the sound signal to be adjusted and the spectral features of the target sound signal in the sound signal, input the spectral features of the sound signal to be adjusted into the frequency point recognition model, identify the frequency point set, input the spectral features of the target sound signal into the sound gain prediction model, and obtain the current actual sound gain.

[0055] Furthermore, in a preferred embodiment of the present application, after identifying the frequency point set in step S402, the corresponding frequency point elimination algorithm is obtained from a preset frequency point library according to the identified frequency point set, and the sound signal is processed using the PID algorithm. The control parameters of the PID algorithm are fine-tuned for different frequency point sets, and the frequency point of the sound signal to be adjusted is dynamically adjusted.

[0056] Furthermore, in a preferred embodiment of the present application, the difference between the target gain of the current sound output by the audiometer and the predicted actual vocalization gain is calculated. If the difference between the two exceeds a preset threshold, it is determined that there is a deviation in the current vocalization gain control and automatic adjustment is required.

[0057] Furthermore, in a preferred embodiment of the present application, according to the difference between the actual phonation gain and the target gain, a gradient descent algorithm is used to optimize and solve the phonation gain control parameter of the audiometer to obtain the target phonation gain control parameter value.

[0058] Furthermore, in a preferred embodiment of the present application, an error function is constructed according to the difference between the actual vocal gain and the target gain, and the control parameters are iteratively optimized using a gradient descent algorithm, and the optimal vocal gain control parameter value is obtained through parameter updating and convergence judgment.

[0059] Furthermore, in a preferred embodiment of the present application, the target voicing gain control parameter value is set in the audiometer, and automatic gain control is performed on the output sound of the audiometer.

[0060] On the other hand, the present invention also discloses a hearing device for automatically adjusting the sound gain based on PID, comprising a microphone array, a speaker and a processor, wherein the microphone array and the speaker are electrically connected to the processor respectively;

[0061] The processor is used to execute the steps of the aforementioned method for automatically adjusting the sound gain based on PID.

[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0064] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0065] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0066] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

[0067] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0068] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A method for automatically adjusting the sound gain based on PID, characterized in that: The following steps are involved: Acquire a sound signal collected by a built-in microphone of the audiometer, and convert it to obtain spectrum data of the sound signal, wherein the sound signal is a sound signal to be adjusted; Preset a target sound signal and a gain parameter of the target sound signal, and extract the spectrum characteristics of the sound signal to be adjusted from the spectrum data according to the spectrum characteristics of the target sound signal; Constructing a mapping relationship between the spectral characteristics of the to-be-adjusted vocalization signal and the to-be-adjusted vocalization type, as well as a mapping relationship between the spectral characteristics of the target vocalization signal and the vocalization gain, and training to obtain a frequency point recognition model and a vocalization gain prediction model; Inputting the extracted frequency spectrum features of the sound signal to be adjusted into a frequency point recognition model to identify a frequency point set that forms the sound signal to be adjusted; The PID technology is used to dynamically adjust the gain of each frequency point in the frequency point set, so that the sound signal to be adjusted is infinitely close to the gain parameter of the target sound signal.

2. The method for automatically adjusting the sound gain based on PID according to claim 1, characterized in that: The step of constructing a mapping relationship between the spectral characteristics of the to-be-adjusted sound signal and the to-be-adjusted sound type, and a mapping relationship between the spectral characteristics of the target sound signal and the sound gain, further includes the following steps: A mapping relationship between the frequency spectrum characteristics of the sound signal to be adjusted and the type of sound to be adjusted is constructed, and a support vector machine algorithm is used for training to obtain a frequency point recognition model; According to the mapping relationship between the spectral characteristics of the target vocal signal and the vocal gain, a vocal gain prediction model is obtained to determine the frequency point set and predict the vocal gain.

3. The method for automatically adjusting the sound gain based on PID according to claim 1, characterized in that: After the extracted frequency spectrum feature of the sound signal to be adjusted is input into the frequency point recognition model and the frequency point set in the sound signal is recognized, the method further includes: The extracted spectral features of the target vocalization signal are input into the vocalization gain prediction model to predict the current actual vocalization gain; By extracting the spectral features of the sound signal to be adjusted and the spectral features of the target sound signal in the sound signal, the spectral features of the sound signal to be adjusted are input into the frequency point recognition model to identify the frequency point set, and the spectral features of the target sound signal are input into the sound gain prediction model to obtain the current actual sound gain.

4. The method for automatically adjusting the sound gain based on PID according to claim 3 is characterized in that: After the frequency point set is identified, the sound signal is processed using the PID algorithm according to the identified frequency point set. The control parameters of the PID algorithm are fine-tuned for different frequency point sets to dynamically adjust the frequency point of the sound signal to be adjusted.

5. The method for automatically adjusting the sound gain based on PID according to claim 3 is characterized in that: The difference between the target gain of the current sound output by the audiometer and the predicted actual phonation gain is calculated. If the difference between the two exceeds a preset threshold, it is determined that there is a deviation in the current phonation gain control, and the phonation gain is automatically adjusted.

6. The method for automatically adjusting the sound gain based on PID according to claim 5, characterized in that: According to the difference between the actual phonation gain and the target gain, the phonation gain control parameter of the audiometer is optimized and solved by using the gradient descent algorithm to obtain the target phonation gain control parameter value.

7. The method for automatically adjusting the sound gain based on PID according to claim 6, characterized in that: An error function is constructed based on the difference between the actual vocal gain and the target gain, and the control parameters are iteratively optimized using the gradient descent algorithm. The optimal vocal gain control parameter value is obtained through parameter updating and convergence judgment.

8. The method for automatically adjusting the sound gain based on PID according to claim 7, characterized in that: The target voicing gain control parameter value is set in the audiometer to perform automatic gain control on the output sound of the audiometer.

9. A hearing device that automatically adjusts the sound gain based on PID, characterized in that: It includes a microphone array, a speaker and a processor, wherein the microphone array and the speaker are electrically connected to the processor respectively; The processor is used to execute the steps of a method for automatically adjusting the sound gain based on PID according to any one of claims 1 to 8.

Images