A wireless microphone chip integrated intelligent noise reduction processing method

Abstract

The application discloses a kind of wireless microphone chip integrated intelligent noise reduction processing method, it is related to intelligent noise reduction technical field, for improving quiet recording environment noise difficult collection, denoising algorithm single etc., including matching identification to microphone model, confirm the connection range and sound source acquisition range of microphone, the connection range and sound source acquisition range of microphone are used K-nearest neighbor algorithm to calculate sound collecting position.Comfirm user real-time position, carry out sound source acquisition, obtain microphone output voltage and calculate microphone sensitivity and frequency response, according to microphone sensitivity and frequency response, compare the recording adaptation sensitivity of noise file using logistic regression algorithm to select noise file and play, compare the SNR stored in recording database by microphone and calculate sound collecting position The noise file first SNR value is compared, analyze environmental noise, according to environmental noise, select different algorithm to carry out denoising processing and save data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent noise reduction, more particularly, to an intelligent noise reduction processing method for wireless microphone chip integration. BACKGROUND

[0002] Intelligent noise reduction technology is to use advanced algorithms and models to automatically identify and reduce unnecessary noise in audio or video signals. By applying intelligent noise reduction technology to chip integration type wireless microphones, various noises in the wireless microphone can be effectively reduced.

[0003] The prior art has the following disadvantages:

[0004] In the past, when performing noise reduction processing on a wireless microphone, a set noise reduction algorithm is used to uniformly process the audio sound source signal. However, environmental noise needs to be detected in the environment, and the subsequent noise reduction processing is performed according to the detection results. When the environment is quiet enough, the environmental noise detection is difficult, and the noise reduction accuracy of the uniform processing noise reduction algorithm is low. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide an intelligent noise reduction processing method for wireless microphone chip integration, which calculates the sound collecting position by analyzing the microphone performance, compares the file noise of the sound collecting position with the file noise of the database to analyze the environmental noise degree, and selects different algorithms for noise reduction to solve the problems raised in the background art.

[0006] To achieve the above object, the present application provides the following technical scheme:

[0007] An intelligent noise reduction processing method for wireless microphone chip integration, comprising the following steps:

[0008] Step S1: connecting the microphone to the host computer, the host computer identifying the microphone model, confirming the connection range and sound source collection range of the microphone, and using K-neighbor algorithm to calculate the sound collecting position based on the connection range and sound source collection range of the microphone;

[0009] Step S2: determining the real-time position of the user, prompting the user to perform initial sound source collection, obtaining the microphone output voltage to calculate the microphone sensitivity and frequency response, and using the logic regression algorithm to select the noise file recorded in advance in the recording database according to the microphone sensitivity and frequency response to provide to the user;

[0010] Step S3: playing the noise file at the sound collecting position, determining the collected signal power through the noise file of the sound collecting position obtained by the microphone, and calculating the SNR value through the noise file signal power recorded in the recording database to determine the environmental noise;

[0011] Step S4: Selecting a time domain denoising algorithm or an adaptive filtering algorithm according to the ambient noise level to denoise the ambient noise of the microphone acquisition file.

[0012] In a preferred embodiment, in step S1, the wireless microphone is connected to the host computer, and the host computer queries the optimal sound collecting position of the connected microphone by matching the microphone model with the stored microphone models in the software database, and marks the optimal sound collecting position. If the connected microphone has no record of the optimal sound collecting position, the connection range and the sound source collecting range of the connected microphone are obtained.

[0013] The software database stores the microphone models and the basic information corresponding to the models, including the connection range, the sound source collecting range, and the optimal sound collecting position.

[0014] In a preferred embodiment, in step S1, the connection range is the farthest distance at which the microphone can be wirelessly connected to the host computer, the sound source collecting range is the farthest distance at which the microphone can collect the sound source position, and the optimal sound collecting position is the stable collecting distance between the sound source and the microphone obtained through testing and stored in the software database along with the microphone model.

[0015] In a preferred embodiment, in step S1, the microphone models with the optimal sound collecting position stored in the software database are screened and marked, and the connection range and the sound source collecting range of the marked microphone are merged into a connection range dataset and a collecting range dataset, respectively. The K-neighbor algorithm is used to calculate the sound collecting position as follows:

[0016] Define input and output: set the connection range and the sound source collecting range of the connected microphone as input features, and set the sound collecting position of the connected microphone as an output feature;

[0017] Select parameter K: set parameter K, and obtain the average value of the connection range and the sound source collecting range of the connected microphone multiplied by a preset reference ratio;

[0018] Calculate distance: select the average value of the connection range and the sound source collecting range of the marked microphone of the same model in the connection range dataset and the collecting range dataset as the neighbor distance;

[0019] Find K nearest neighbors: take the average value of the two input features as the feature average value, select the marked microphone model with the K nearest neighbor distances closest to the feature average value, obtain the optimal sound collecting positions of the K nearest neighbor distances, and select the average value as the candidate sound collecting position corresponding to the K value;

[0020] Predict output: set multiple different K values through a preset number of repetitions, obtain multiple candidate sound collecting positions, calculate the average value as the sound collecting position of the connected microphone, and output.

[0021] In a preferred embodiment, in step S2, the user terminal applies for a mobile device connection, obtains the real-time position of the user to determine whether the user is in the sound collecting position, and sends a text prompt to the mobile device when the user adjusts the position to the sound collecting position. The microphone collects sound source data by reading the text prompt from the user, and the host computer calculates the microphone sensitivity and frequency response through the output voltage of the microphone.

[0022] In a preferred embodiment, in step S2, when calculating the microphone sensitivity, the host computer calculates the microphone sensitivity through the sensitivity formula: wherein dB is the microphone sensitivity, is the microphone output voltage, is the reference sound pressure, which is set as a commonly used standard sound pressure.

[0023] The frequency response is the change of the microphone sensitivity at different frequencies. Different sound frequencies are obtained through the text prompt, the microphone sensitivity at different sound frequencies is calculated respectively, and the obtained microphone sensitivity is subtracted two by two, and the calculation result obtained by subtraction is taken as the frequency response.

[0024] The calculated microphone sensitivity and frequency response are used to construct a logistic regression equation to calculate the logistic regression coefficient: wherein L is the logistic regression coefficient, e is the natural base, and D is the microphone sensitivity coefficient, which is obtained by summing the microphone sensitivity and the frequency response.

[0025] In a preferred embodiment, in step S3, the SNR value is the signal-to-noise ratio of the microphone connected to the host computer. The larger the SNR value, the lower the environmental noise intensity. The noise file of the sound collecting position obtained through the microphone determines the signal power collected, which includes the power of the audio sound source and the power of the background noise. The signal power recorded in the noise file in the recording database includes the power of the same audio sound source and the power of the background noise.

[0026] The signal power obtained by connecting the microphone is subtracted from the signal power recorded in advance to calculate the SNR value.

[0027] In a preferred embodiment, in step S4, when the calculated SNR value exceeds the preset SNR threshold value, it is determined that the environmental noise degree is low, and the time domain de-noising algorithm is used for de-noising processing of the environmental noise; when the calculated SNR value is lower than the preset SNR threshold value, it is determined that the environmental noise degree is high, and the adaptive filtering algorithm is used for de-noising processing of the environmental noise.

[0028] In a preferred embodiment, in step S4, the specific steps of using the time domain de-noising algorithm for de-noising processing of the environmental noise are as follows:

[0029] The signal is set as an analysis window in a representation of the collection time as the horizontal axis, and the ambient noise is processed by a moving average filtering formula: , wherein is the nth segment of the denoised audio sound source signal value, and N is the analysis window size, is the frequency band of the original audio sound source signal without denoising, and the denoising is performed by exchanging the calculated value with the analysis window center value during denoising;

[0030] The specific steps of using an adaptive filtering algorithm to denoise the ambient noise are as follows:

[0031] The normalized least square formula is selected to process the original audio sound source signal, and the calculation formula is: , wherein each time point of the collection time is processed to denoise the ambient noise, wherein w(n) is the filter coefficient, is the step factor, is the error tolerance, is the original audio sound source signal value, and the filter coefficient of the next time point is adjusted by each original audio sound source signal value to adjust the original audio sound source signal value of each time point for denoising.

[0032] The technical effects and advantages of the intelligent noise reduction processing method of the wireless microphone chip integration are as follows:

[0033] The microphone and the upper computer are connected, the microphone model is matched and identified, the connection range and the sound source collection range of the microphone are confirmed, and the sound collection position is calculated based on the connection range and the sound source collection range of the microphone. The sound collection position is determined according to the performance of the microphone, the accuracy of the collected data is improved, the real-time position of the user is determined, the sound source is collected, the microphone output voltage is obtained, the microphone sensitivity and frequency response are calculated, the recording adaptability sensitivity of the noise file is compared according to the microphone sensitivity and frequency response, and the noise file is selected for playing. The noise file sound source data is obtained through the microphone, and the noise file SNR value of the sound collection position is calculated and compared with the SNR stored in the recording database. The environmental noise is analyzed, the SNR value is compared and calculated, the SNR value calculated by the traditional collection of environmental noise is more suitable for quiet environment, different algorithms are selected for denoising according to the environmental noise, and the data is saved, so that the environmental noise in the specified environment is denoised. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 The schematic diagram of the intelligent noise reduction processing method of the wireless microphone chip integration. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0036] The present application matches and identifies the microphone model by connecting the microphone and the host computer, confirms the connection range and sound source collection range of the microphone, and calculates the sound collection position by comprehensively considering the connection range and sound source collection range of the microphone. The real-time position of the user is determined, the sound source is collected, the microphone output voltage is obtained to calculate the microphone sensitivity and frequency response, the recording adaptability sensitivity of the noise file is compared according to the microphone sensitivity and frequency response, and the noise file is selected for playing, the noise file sound source data is obtained through the microphone, the noise file first SNR value of the sound collection position is calculated and compared with the SNR stored in the recording database, the environmental noise is analyzed, different algorithms are selected for noise reduction processing according to the environmental noise, and the data is saved, so that the environmental noise in the specified environment is de-noised.

[0037] Embodiment, a wireless microphone chip integrated intelligent noise reduction processing method, as shown in Figure 1 The method comprises the following steps:

[0038] Step S1: connecting the microphone to the host computer, the host computer identifying the microphone model, confirming the connection range and sound source collection range of the microphone, and calculating the sound collection position by comprehensively considering the connection range and sound source collection range of the microphone using K-neighbor algorithm;

[0039] Step S2: determining the real-time position of the user, prompting the user to collect the sound source for the first time, obtaining the microphone output voltage to calculate the microphone sensitivity and frequency response; selecting the noise file recorded in advance in the recording database according to the microphone sensitivity and frequency response using the logistic regression algorithm and providing the user with the noise file;

[0040] Step S3: playing the noise file at the sound collection position, determining the collected signal power through the microphone, and determining the environmental noise by calculating the SNR value through the noise file signal power recorded in the recording database;

[0041] Step S4: selecting the time domain de-noising algorithm or the adaptive filtering algorithm according to the degree of environmental noise to de-noise the environmental noise of the microphone collection file.

[0042] The specific steps are as follows:

[0043] In step S1, the wireless microphone is connected with the host computer. The host computer queries the optimal sound collecting position of the connected microphone by matching the microphone model with the stored microphone models in the software database, and marks the optimal sound collecting position. If the connected microphone has no record of the optimal sound collecting position, the connection range and the sound source collecting range of the connected microphone are obtained. The connection range is the farthest distance within which the microphone can be wirelessly connected with the host computer, and the sound source collecting range is the farthest distance within which the microphone can collect the sound source position. The optimal sound collecting position is the distance between the sound source and the microphone obtained through testing and stored in the software database along with the microphone model.

[0044] If the microphone model in the software database is not successfully matched with the connected microphone model, a microphone data collection pop-up box is popped up to the user end to provide manual input of the connection range and the sound source collecting range of the connected microphone, and the connected microphone model, the connection range and the sound source collecting range are recorded in the software database.

[0045] The microphone model with the optimal sound collecting position stored in the software database is screened and marked, and the connection range and the sound source collecting range of the marked microphone are merged into a connection range dataset and a collecting range dataset, respectively. The K-neighbor algorithm is used to calculate the sound collecting position, and the specific steps are as follows:

[0046] Define input and output: set the connection range and the sound source collecting range of the connected microphone as input features, and set the sound collecting position of the connected microphone as an output feature. It needs to be explained that both the input features and the output features are unitless data.

[0047] Select parameter K: set a parameter K, which can be obtained by multiplying the average value of the connection range and the sound source collecting range of the connected microphone by a preset reference ratio;

[0048] Calculate distance: select the average value of the connection range and the sound source collecting range corresponding to the marked microphone of the same model in the connection range dataset and the collecting range dataset as the nearest neighbor distance;

[0049] Find K nearest neighbors: take the average value of the two input features as the feature average value, select the K microphone models with the nearest neighbor distance closest to the feature average value, obtain the optimal sound collecting positions of the K nearest neighbor distances, and select the average value as the candidate sound collecting position corresponding to the K value;

[0050] Predict output: set multiple different K values through a preset number of repetitions, obtain multiple candidate sound collecting positions, calculate the average value as the sound collecting position of the connected microphone, and output it.

[0051] The sound collecting position of the connected microphone is marked and recorded in the software database in combination with the model of the connected microphone, the connection range and the sound source collecting range. The sound collecting position of the connected microphone is calculated preferentially by the K-neighbor algorithm, so that more detailed sound source data can be obtained to facilitate subsequent testing and analysis of environmental noise.

[0052] It should be noted that the software database involved in the present example is a database that stores microphone models and basic information, which is mainly used to match and identify the obtained connected microphone model with the microphone models in the database. The K-neighbor algorithm is a supervised learning algorithm that can be used for classification and regression tasks. Through the L-neighbor algorithm, the data provided by the connected microphone can be quickly used as input features and the comparison features in the software database to calculate the output. This is fast and convenient, greatly saving the time cost of calculating the sound collecting position. The value of the parameter K and the number of repetitions of the set K value in the prediction output can be set by the user according to the required accuracy, and the setting method is not unique.

[0053] In step S2, after calculating the sound collecting position of the connected microphone, the mobile device is connected to the user terminal. The user needs to connect the mobile device used by the user to the host computer to obtain the real-time position of the user, i.e., the positioning of the user, to determine whether the user is at the sound collecting position.

[0054] After the user connects the mobile device to the host computer, a prompt window for initial sound source collection is sent to the mobile device, and the distance between the user and the host computer is detected. The prompt window displays the real-time distance between the user and the host computer and prompts the user to adjust the distance. When the user adjusts the distance to make the distance between the user and the host computer the sound collecting position, the host computer sends a text prompt to the mobile device. The user needs to read out the content in the text prompt at the sound collecting position and collect it through the microphone as sound source data and transmit it to the host computer. The host computer calculates the microphone sensitivity and frequency response through the output voltage of the microphone.

[0055] When the host computer calculates the microphone sensitivity, it calculates it through the sensitivity formula: the microphone output voltage and the reference sound pressure are used to calculate the sensitivity, and the formula is: wherein dB is the microphone sensitivity, is the microphone output voltage, is the reference sound pressure, which can be set as a commonly used standard sound pressure.

[0056] The frequency response is the change of the microphone sensitivity at different frequencies. By reading out the content in the text prompt, multiple different sound frequencies can be obtained. The microphone sensitivity at different sound frequencies is calculated respectively, and the obtained microphone sensitivities are pairwise subtracted. The calculation results obtained by the subtraction are used as the frequency response.

[0057] The calculated microphone sensitivity and frequency response are used to construct a logistic regression equation to calculate the logistic regression coefficient using a logistic regression algorithm, and the logistic regression formula is calculated as follows: wherein L is the logistic regression coefficient, e is the natural base, D is the microphone sensitivity coefficient, which is obtained by summing the microphone sensitivity and frequency response, when the microphone sensitivity or frequency response is greater, the microphone sensitivity coefficient is greater, and the logistic regression coefficient is greater, and the connecting microphone is more sensitive.

[0058] The noise file is a pre-recorded recording, and the sensitivity and frequency response supported by each noise file are used to calculate the sensitivity coefficient and the logistic regression coefficient of each noise file and store them in the recording database. The microphone sensitivity coefficient and the logistic regression coefficient of the connecting microphone are calculated by comparing the sound source data obtained by the connecting microphone with the logistic regression coefficient in the recording database. When the logistic regression coefficient of the noise file in the recording database is higher, it means that the corresponding noise file has higher sensitivity requirements for the microphone. In the recording database, the maximum value of the logistic regression coefficient is selected, and the corresponding noise file is provided to the user's mobile device.

[0059] It should be noted that the recording database is a collection of various audio recordings, which is used for audio processing, speech recognition and analysis, and the recorded noise file can be stored in the recording database.

[0060] In step S3, the signal power of the noise file at the sound collecting position is obtained by connecting the microphone, and the signal power of the corresponding noise file in the recording database is compared to calculate the SNR value to determine the environmental noise of the noise reduction environment. The SNR value is the signal-to-noise ratio of the connecting microphone transmitted to the host computer, which is used to reflect the size of the signal strength and noise strength. The larger the SNR value, the lower the environmental noise intensity.

[0061] The calculation process of the normal signal-to-noise ratio needs to record the power of the environmental sound source without human intervention as the power of the background noise, and then obtain the power of the audio sound source with human intervention as the power of the target signal. However, when the environment is too quiet, the power detection accuracy of the environmental sound source is low, resulting in analysis error of the environmental noise.

[0062] The difference between the signal power obtained by the connecting microphone and the signal power recorded in advance can more accurately reflect the difference in environmental noise after switching.

[0063] The sum of the power of the audio sound source and the power of the background noise in the signal power recorded in advance is taken as the overall target signal power, and the signal power obtained by the connecting microphone also includes the power of the same audio sound source and the power of the background noise.

[0064] It should be noted that the noise file recording needs to ensure that the recording environment is quiet, the environmental noise is low, and the noise file contains not only the pre-recorded recording, but also the signal power of the noise file during recording.

[0065] In step S4, the calculated SNR value is compared with the preset SNR threshold to judge the environmental noise level. When the calculated SNR value exceeds the preset SNR threshold, it is judged that the environmental noise level is low, and the time domain denoising algorithm is used to denoise the environmental noise. When the calculated SNR value is lower than the preset SNR threshold, it is judged that the environmental noise level is high, and the adaptive filtering algorithm is used to denoise the environmental noise.

[0066] The time domain denoising algorithm denoises the environmental noise by separately denoising a small range and then merging, which is simple, fast and suitable for environments with low noise level. The adaptive filtering algorithm denoises the environmental noise by denoising each time point and then merging, which has higher denoising accuracy and is suitable for environments with high noise level.

[0067] The specific steps of using the time domain denoising algorithm to denoise the environmental noise are as follows:

[0068] A small section of time is selected as an analysis window in the form of signal with collection time as the horizontal axis, and the environmental noise is processed by moving average filtering formula: , wherein is the nth denoised audio sound source signal value, N is the analysis window size, is the frequency band of the original audio sound source signal without denoising, and the value obtained by calculation is exchanged with the center value of the analysis window during denoising to smooth the audio sound source signal. The denoised audio sound source signal frequency band is merged, and the environmental noise denoising is completed.

[0069] The specific steps of using the adaptive filtering algorithm to denoise the environmental noise are as follows:

[0070] The normalized least mean square formula is selected to process the original audio sound source signal, and the calculation formula is: Each time point of the collection time is processed to denoise the environmental noise, wherein w(n) is the filter coefficient, is the step factor, is the error tolerance difference, is the original audio sound source signal value. The filter coefficient of the next time point is adjusted by each original audio sound source signal value, so that each time point is convergent processed. When the audio sound source is traversed, the environmental noise denoising is completed.

[0071] It should be noted that the SNR threshold can be set by averaging the SNR values of all noise files in the recording database, the average filtering formula is only one of the time domain denoising algorithms, the normalized least mean square formula is one of the adaptive filtering algorithms, and only examples are given in this example. The filter coefficients, step factors and error tolerance involved in the normalized least mean square formula are set by professionals in the field according to the actual situation, and are not analyzed here.

[0072] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product.

[0073] Those skilled in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application of the technical solution and the constraints of the invention. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0074] In addition, the functional modules in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any skilled person in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0076] Finally, the above is only the preferred embodiment of the present application and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for intelligent noise reduction processing integrated into a wireless microphone chip, characterized in that, Includes the following steps, Step S1: Connect the microphone to the host computer. The host computer identifies the microphone model, confirms the microphone's connection range and sound source acquisition range, and uses the K-nearest neighbor algorithm to calculate the sound acquisition location based on the microphone's connection range and sound source acquisition range. Step S2: Determine the user's real-time location to determine if the user is at the sound acquisition location, prompt the user to start the initial sound source acquisition, obtain the microphone output voltage, calculate the microphone sensitivity and frequency response; based on the microphone sensitivity and frequency response, use the logistic regression algorithm to select a pre-recorded noise file from the recording database and provide it to the user. Step S3: Play the noise file at the sound acquisition location, obtain the noise file at the sound acquisition location through the microphone to determine the collected signal power, calculate the difference between the signal power obtained by the microphone and the signal power recorded in the recording database, and determine the SNR value to determine the ambient noise. Step S4: Select a temporal denoising algorithm or an adaptive filtering algorithm to denoise the environmental noise in the microphone acquisition file based on the level of environmental noise; Specifically, the signal power obtained by acquiring noise files at the sound acquisition location through a microphone includes the power of the audio source and the power of the background noise; the signal power of the noise files recorded in the recording database includes the power of the same audio source and the power of the background noise.

2. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 1, characterized in that: In step S1, the wireless microphone is connected to the host computer. The host computer matches the microphone model with the various microphone models stored in the software database, queries and marks the best sound acquisition position of the connected microphone. If the best sound acquisition position of the connected microphone is not recorded, the connection range and sound source acquisition range of the connected microphone are obtained. The software database stores microphone models and their corresponding basic information, including connection range, sound source acquisition range, and optimal sound acquisition location.

3. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 2, characterized in that: In step S1, the connection range is the farthest distance at which the microphone can wirelessly connect with the host computer, the sound source acquisition range is the farthest distance at which the microphone can acquire the sound source location, and the optimal sound acquisition position is the stable acquisition distance between the sound source and the microphone obtained through testing and stored in the software database along with the microphone model.

4. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 3, characterized in that: In step S1, the microphone models with the best sound acquisition positions stored in the software database are filtered and marked. The connection range and sound source acquisition range of the marked microphones are merged into connection range dataset and acquisition range dataset, respectively. The specific steps for using the K-nearest neighbor algorithm to deduce the sound acquisition position are as follows: Define input and output: Set the connection range of the connected microphone and the sound source acquisition range as input features, and set the sound acquisition position of the connected microphone as output features; Select parameter K: Set parameter K to obtain the calculation result obtained by multiplying the average value of the connected microphone range and the sound source acquisition range by the preset reference ratio; Distance calculation: Select the connection range and sound source acquisition range of the same model of labeled microphone from the connection range dataset and acquisition range dataset, and take the average value as the nearest neighbor distance; Find the K nearest neighbors: Take the average of the two input features as the feature average, select the microphone model whose distance is closest to the feature average of the K nearest neighbors, obtain the best sound collection position of the K nearest neighbors, and select the average value as the candidate sound collection position corresponding to the K value; Predictive output: By setting multiple different K values ​​through a preset number of repetitions and obtaining multiple alternative sound sampling positions, the average value is calculated as the sound sampling position of the connected microphone for output.

5. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 1, characterized in that: In step S2, the host computer requests a mobile device connection from the user terminal to obtain the user's real-time location and determine whether the user is at the sound collection location. When the user adjusts their position to the sound collection location, the host computer sends a text prompt to the mobile device. The microphone collects sound source data by reading the text prompt from the user. The host computer calculates the microphone sensitivity and frequency response by using the microphone's output voltage.

6. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 5, characterized in that: In step S2, when calculating the microphone sensitivity, the host computer calculates the microphone sensitivity using the sensitivity formula: Where dB is the microphone sensitivity. This is the microphone output voltage. The reference sound pressure level is set to the commonly used standard sound pressure level. Frequency response is the sensitivity change of a microphone at different frequencies. Multiple different sound frequencies are obtained through text prompts, the microphone sensitivity at each sound frequency is calculated, and the difference between the obtained microphone sensitivities is taken as the frequency response. The calculated microphone sensitivity and frequency response are used to construct a logistic regression equation and calculate the logistic regression coefficients. , where L is the logistic regression coefficient, e is the natural base, and D is the microphone sensitivity coefficient, which is obtained by summing the microphone sensitivity and frequency response.

7. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 1, characterized in that: In step S4, if the calculated SNR value exceeds the preset SNR threshold, the environmental noise level is determined to be low, and a time-domain denoising algorithm is used to denoise the environmental noise; if the calculated SNR value is lower than the preset SNR threshold, the environmental noise level is determined to be high, and an adaptive filtering algorithm is used to denoise the environmental noise.

8. The intelligent noise reduction processing method integrated into a wireless microphone chip according to claim 7, characterized in that: In step S4, the environmental noise is denoised using a time-domain denoising algorithm. The specific steps are as follows: The signal is represented with the acquisition time as the horizontal axis as the analysis window, and environmental noise is processed using a moving average filtering formula: ,in It is the numerical value of the denoised audio source signal of the nth segment, where N is the size of the analysis window. These are the frequency bands in the original audio source signal that have not been denoised, obtained through calculation. The value is swapped with the value at the center of the analysis window during denoising to perform denoising; The specific steps for using an adaptive filtering algorithm to denoise environmental noise are as follows: The normalized least mean square formula is used to process the original audio source signal, and its calculation formula is as follows: The environmental noise is removed by processing each time point of the acquisition time, where w(n) are the filter coefficients. It is the step size factor. It is tolerance for errors. It is the original audio source signal value. The filter coefficient at the next time point is adjusted by adjusting the original audio source signal value at each time point to achieve noise reduction.

Images