Cardiopulmonary sound noise reduction method and system based on sound stethoscope

Abstract

The invention relates to a heart and lung sound noise reduction method and system based on a sound stethoscope. A traditional heart and lung sound data noise reduction algorithm is poor in performance in a complex environment, so that a doctor cannot give an accurate diagnosis result. The heart and lung sound is acquired through the acquisition module, the heart and lung sound is converted into a digital form through the analog-to-digital converter and stored, then the stored heart and lung sound data is subjected to traditional time-frequency noise reduction processing and deep learning algorithm noise reduction processing, and the deep learning algorithm noise reduction processing comprises construction of a clean heart and lung sound data set and a noise data set. The heart and lung sound data with noise is obtained by randomly synthesizing clean heart and lung sound data and a noise data set, and the obtained data set is subjected to noise reduction and noise removal processing. According to the method, noise reduction and noise removal are further carried out on the sound signals by adopting the traditional and deep learning model algorithms, the signal-to-noise ratio is obviously improved compared with noise data and a traditional method, and cardiopulmonary sound extraction can be carried out in a more complex external environment.

Description

Technical Field

[0001] The invention relates to the technical field of electronic stethoscopes and processing of collected heart and lung sound data, in particular to a heart and lung sound noise reduction method and system based on a sound stethoscope. Background Art

[0002] Cardiovascular disease is recognized as the leading cause of death worldwide, with approximately one-third of global deaths being cardiovascular-related. In addition to clinical manifestations, specific clinical examination findings can also aid in the treatment and prevention of cardiovascular disease, which may initially manifest as pulmonary lesions, so accurate cardiopulmonary auscultation is essential to establish an accurate diagnosis.

[0003] Traditional cardiopulmonary sound data noise reduction algorithms can achieve a signal-to-noise ratio gain of 5-10dB in simple noise environments, such as environments that only include fixed noise and burst noise. However, they do not perform particularly well in more complex environments, including those with multiple noise sources such as mixed human voices and outdoor motor vehicles. The use of stethoscopes in real clinics will affect the collection of cardiopulmonary sound data, directly resulting in doctors being unable to give diagnostic results, which will greatly reduce the clinic doctors' experience of using stethoscope products. Summary of the invention

[0004] In view of the above problems, the present invention provides a method and system for reducing the noise of cardiopulmonary sounds based on an acoustic stethoscope, which significantly improves the signal-to-noise ratio compared with noise data and traditional methods.

[0005] To this end, the present invention adopts the following technical solution: a heart and lung sound denoising method based on a sound stethoscope, wherein the heart and lung sounds are collected by an acquisition module, converted into digital form by an analog-to-digital converter and stored, and the stored heart and lung sound data are subjected to traditional time-frequency denoising processing and deep learning algorithm denoising processing, wherein the deep learning algorithm denoising processing includes the construction of a clean heart and lung sound data set and a noise data set:

[0006] The clean heart and lung sound dataset includes self-collected data, open-source heart sound dataset and open-source lung sound dataset. The self-collected data includes more than 10,000 heart and lung sound data collected by stethoscope in night environment (actual monitoring clinic environment volume is below 20dB) (each no more than 30s) and in daytime environment (actual monitoring clinic environment volume is below 40dB) (each no more than 30s), with a total time of more than 100 hours. The actual data collection comes from various groups of people;

[0007] The noise dataset consists of two parts. One part is the real clinic environment noise collected by the stethoscope in the daytime noise environment and the environmental sound data collected by the stethoscope in the night environment, with a total time of more than 50 hours. The other part is to select multiple different categories of audio from the open source datasets Audioset and Freesound and play them to the stethoscope through the speaker, with a total time of more than 20 hours.

[0008] The noisy heart and lung sound data is obtained by randomly synthesizing the clean heart and lung sound data and the noise data set. The obtained data set is subjected to denoising and noise removal processing. The steps are as follows:

[0009] (1) Divide the synthesized noisy heart and lung sound data and the clean heart and lung sound data into training, testing and validation ratios;

[0010] (2) Perform short-time Fourier transform (STFT) on each data with a short-time window of 20 ms, a minimum frequency of 50 Hz, and an overlap of 50% to obtain the frequency domain data of the data (including the real and imaginary data of the frequency domain graph);

[0011] (3) Extract the frequency domain data through the ERB equivalent rectangular bandwidth feature extractor and the complex feature extractor;

[0012] (4) The data extracted in step 3 are temporally encoded by the ERB self-attention encoder and the imaginary part self-attention decoder respectively. The input of the encoder is the ERB feature + temporal feature (imaginary feature + temporal feature). The temporal feature is temporally encoded according to the order of the short time frame window.

[0013] (5) Perform cross attention, which is to associate the ERB encoder and the imaginary decoder to learn the parameter matrix of the temporal feature correlation between the real and imaginary features of the spectrum;

[0014] (6) synthesizing and filtering the ERB coded and imaginary coded data passed through the decoder, and splicing them into frequency domain data of the output data;

[0015] (7) Convert the signal represented in the frequency domain back to the time domain to obtain denoised audio data.

[0016] Preferably, the self-attention function of the self-attention encoder in step (4) is an embedded query of ERB features + temporal features (imaginary features + temporal features) and a set of key-value pairs mapped to the output, where Q, K, V (query, key, value) are all self-embedded vector matrices, d is the dimension size of the embedded vector, T is the matrix operation, and the self-attention calculation formula is as follows:

[0017]

[0018] Preferably, in step (1), the synthesized noisy heart and lung sound data and the clean heart and lung sound data are divided into training, testing and validation according to a total ratio of 70% / 15% / 15%.

[0019] As a preferred method, the data of heart and lung sounds were collected from 7 persons, and the age structure distribution was as follows: 1 person under 20 years old, 2 persons between 20 and 40 years old, and 4 persons over 40 years old.

[0020] Preferably, the conventional time-frequency noise reduction processing method is as follows:

[0021] (a) The heart and lung sound data collected by the stethoscope are divided into frames with 160 sampling points per frame (the maximum sampling rate is 44100 Hz), and then the energy sum (sum of square amplitude) of each frame is calculated, and a discrete Fourier transform (FFT) is performed, including the function values ​​of 256 points, and the energy spectrum, amplitude spectrum, logarithmic energy spectrum and logarithmic amplitude spectrum are calculated at the same time, and the noise spectrum is estimated based on these data;

[0022] (b) The a priori and a posteriori SNR of each frame. The so-called a priori SNR is the ratio of the power spectrum of the pure signal to the power spectrum of the noise (ideal value), while the a posteriori SNR is the ratio of the power spectrum of the noisy signal to the power spectrum of the noise. The a priori SNR (estimated value) and the instantaneous SNR calculated in the previous frame are used as the result of the a priori SNR. The calculated SNR is used to update the three features of the LRT (Likelihood Rate Test) mean feature, spectrum flatness and spectrum difference.

[0023] (c) Calculate the probability of speech and noise, and update the noise spectrum;

[0024] (d) Finally, the Wiener filter is calculated to obtain the real and imaginary correction coefficients (frequency domain) of the current frame through the calculated signal-to-noise probability, and the best noise reduction audio data is obtained through IFFT (inverse Fourier transform) and frame synthesis operations.

[0025] The present invention also discloses a cardiopulmonary sound noise reduction system based on a sound stethoscope, which is characterized by comprising a cardiopulmonary stethoscope sound signal acquisition module and a sound signal processing noise reduction module, wherein the sound signal processing noise reduction module performs noise reduction and removes noise according to the above method.

[0026] Preferably, the cardiopulmonary stethoscope sound signal acquisition module includes a transmitter and a receiver, the transmitter includes a front-end circuit, a sensor module, a microcontroller, a wifi module and a PC connection module, the front-end circuit includes a signal acquisition and preprocessing circuit: the sensor module includes a microphone with two diaphragms and a piezoelectric sensor, the stethoscope diaphragm detects the sound signal, and then transmits it to another diaphragm in the microphone and then to the piezoelectric sensor.

[0027] Preferably, the preprocessing circuit consists of a primary amplifying circuit, a filtering circuit and a secondary amplifying circuit.

[0028] The present invention synthesizes a clean cardiopulmonary sound data set and a noisy data set to obtain noisy cardiopulmonary sound data, and then trains, tests and verifies the noisy cardiopulmonary sound data and the clean cardiopulmonary sound data. By adopting the algorithms of traditional and deep learning models, the sound signal is further denoised and noise removed. Compared with the noisy data and traditional methods, the signal-to-noise ratio is significantly improved, and the cardiopulmonary sound extraction can cope with more complex external environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is the pre-sensor signal amplifier LM741 and the audio gain amplifier LM386.

[0030] Figure 2 Schematic diagram of the CrossFilterSound algorithm framework

[0031] Figure 3 Schematic diagram of the self-attention mechanism and encoder.

[0032] Figure 4 Schematic diagram of cross attention and ERB (imaginary) encoder. DETAILED DESCRIPTION

[0033] The present invention is further described below in conjunction with specific embodiments.

[0034] The present invention discloses a cardiopulmonary sound denoising method based on a sound stethoscope. Cardiopulmonary sounds are collected by an acquisition module, converted into digital form by an analog-to-digital converter and stored. The stored cardiopulmonary sound data are subjected to traditional time-frequency denoising processing and deep learning algorithm denoising processing.

[0035] like Figure 1 As shown, the acquisition module is mainly designed to optimize the sensor characteristics of collecting cardiopulmonary and chest sound signals, and is mainly composed of two parts: a transmitter and a receiver.

[0036] The transmitter consists of the following components: (i) front-end circuit and sensor module: preamplifier, filter and power amplifier with variable gain (ii) microcontroller and wifi module (iii) PC ​​connection module.

[0037] 1) The front-end circuit is mainly for signal acquisition and preprocessing: the sensor system includes a microphone (containing two diaphragms) and a piezoelectric sensor. The stethoscope diaphragm detects the sound signal and then transmits it to another diaphragm in the microphone and then to the piezoelectric sensor. The two diaphragms separated by the airway may cause excessive environmental noise signals and inaccurate electrical signal transmission.

[0038] In a piezoelectric transducer, the sound collected by the stethoscope diaphragm causes the crystal material to distort, which in turn generates an electrical signal. The distortion of the crystal generates an electrical signal that may not truly capture the original sound determined by the diaphragm. The diaphragm of the stethoscope is suspended in a nominal capacitance field, where the capacitance changes according to the sound pressure formed by the heart sounds. When the piezoelectric material is subjected to force, an electric charge is generated on the surface. This charge is amplified and the impedance is transformed by the charge amplifier and measurement circuit to become an electrical output proportional to the external force. Piezoelectric sensors are used to measure non-electrical physical quantities that can be converted into electricity, such as force and energy. Its advantages are wide bandwidth, high sensitivity, high signal-to-noise ratio, simple structure, reliable operation and light weight. The results of the sensor are sent to the signal preprocessing circuit for

[0039] The signal preprocessing circuit consists of three parts, namely the primary amplification circuit, the filtering circuit and the secondary amplification circuit. The role of the signal preprocessing circuit is to adjust the signal from the sensor through a series of amplification and filtering so that it meets the subsequent A / D (analog signal / digital signal) sampling requirements and improves the signal-to-noise ratio. The circuit is mainly designed based on the operational amplifier LM741. The preamplifier is used to increase the low signal of the condenser microphone to the line level for further amplification, and the operational amplifier LM741 is used to design the preamplifier. Its gain is 20, which is calculated by the feedback resistor value. The output of the preamplifier is fed to an active low-pass filter with a cutoff frequency of 100Hz and 1000Hz to pass heart sounds and lung breathing sounds and reduce background sounds. The frequency is selected by selecting the capacitor value. The gain of the filter is 1.6. The output signal of the filter is processed by a power amplifier to provide the power required to drive the headphones for further amplification. The LM386 circuit is an audio amplifier designed mainly for low-voltage consumer applications, which can provide voltage and current gain for the signal. Therefore, a power amplifier with variable gain is designed with the help of the operational amplifier LM386. By varying the input provided to the amplifier through a potentiometer, the gain can be varied.

[0040] 2) Microcontroller and wifi module:

[0041] The output of the signal preprocessing circuit is converted into digital form through ADC MCP4822 (Analog to Digital Converter). The built-in successive approximation 12-bit ADC of the PIC18f2423 microcontroller is used. Some parameters of PIC18f2423 are as follows: 0-40MHz operating frequency; 16KB flash program memory; 768 bytes of data memory; 12-bit ADC (10 input channels); SPI and USART serial communication. The wireless transmission module ESP32-S2 has an operating frequency of 2.4GHz and a data rate of 150Mbps.

[0042] 3) PC connection module: The analog signal is provided to the PC through the auxiliary input pin for storage. The audio signal is stored in the form of a .wav file.

[0043] 2. Sound signal processing, noise reduction and noise removal algorithm module:

[0044] Considering the specific situation of using a stethoscope, it is inevitable that interference noises from the external environment and the patient talking loudly will be collected and interfere with the cardiopulmonary sound signals. The present invention uses traditional and deep learning model algorithms to further reduce noise and remove noise from the sound signals.

[0045] It consists of two modules:

[0046] 1) Frequency domain Wiener filter module (traditional time-frequency noise reduction processing):

[0047] 1. Divide the WAV file collected by the stethoscope into 160 sampling points per frame (the maximum sampling rate is 44100Hz), and then calculate the energy and (amplitude square sum) of each frame. Perform a discrete Fourier transform (FFT), including the function value of 256 points, and calculate the energy spectrum, amplitude spectrum, logarithmic energy spectrum and logarithmic amplitude spectrum at the same time, and estimate the noise spectrum based on these data.

[0048] 2. Next, the a priori and a posteriori SNR of each frame are calculated. The so-called a priori SNR is the ratio of the power spectrum of the pure signal to the power spectrum of the noise (ideal value), and the a posteriori SNR is the ratio of the power spectrum of the noisy signal to the power spectrum of the noise. The result of smoothing the a priori SNR (estimated value) and the instantaneous SNR calculated in the previous frame is used as the result of the a priori SNR, and the calculated SNR is used to update the three features of the LRT (Likelihood Rate Test) mean feature, spectrum flatness and spectrum difference.

[0049] 3. Calculate the probability of speech and noise, and update the noise spectrum.

[0050] 4. Finally, the Wiener filter is calculated to obtain the real and imaginary correction coefficients (frequency domain) of the current frame through the calculated signal-to-noise probability, and the best noise reduction sound data is obtained through IFFT (inverse Fourier transform) and frame synthesis operations.

[0051] 2) CrossFilterSound deep learning algorithm noise reduction module:

[0052] (I) Construction of a deep learning dataset for denoising heart and lung sounds: The denoising open source dataset used by existing machine learning algorithms is mainly used for the separation of human voices and mixed sounds of various noises, and is not suitable for the mixture of heart and lung sounds and various human voices and environmental noises. Directly using the existing trained model does not have a very good effect. Therefore, the present invention constructs a denoising dataset to train the algorithm model, which mainly includes clean heart and lung sound data and noisy heart and lung sound data.

[0053] The clean heart and lung sound datasets include the following three:

[0054] (1) More than 12,000 pieces of cardiopulmonary sound data (each no longer than 30 seconds) were collected by stethoscope at night (actual monitoring clinic ambient volume below 20 dB) and during the day (actual monitoring clinic ambient volume below 40 dB) with a total time of more than 100 hours. The data were actually collected by 7 people (1 person under 20 years old, 2 people between 20 and 40 years old, and 4 people over 40 years old. The cardiopulmonary disease population is mainly concentrated in the 40-70 age group. When collecting data, the age distribution of the cardiopulmonary disease population was taken into consideration). The clean data with noise reduction does not need to be labeled by professional doctors. It only needs to monitor the ambient dB, which is relatively easy to collect.

[0055] (2) Open Source Heart Sound Dataset (PhysioNet Challenge2016): It includes a total of 3153 heart sound files with a duration of 10-60 seconds, mainly recording the heart sounds and ECG information of four locations: the aorta, pulmonary artery, tricuspid valve, and mitral valve.

[0056] (3) Open Source Respiratory Sound Database: It includes 920 heart and lung sound data from 126 patients, with a duration of 10-90 seconds. It mainly records the sound information of eight chest and lung positions: trachea, left front, right front, left rear, right rear, left side, and right side.

[0057] The noisy heart and lung sound dataset is mainly obtained by randomly synthesizing the following noisy dataset using the clean heart and lung sound dataset:

[0058] (1) The stethoscope collected real clinic environment noise (including various mixed human voices, external environmental noise, etc.) in daytime noise environment (actual monitoring clinic environment volume is above 55dB) and in night environment (actual monitoring clinic environment volume is above 45dB, and the speaker randomly plays the daytime recorded noise), with a total time of more than 50 hours;

[0059] (2) We selected audio from ten sound categories, including breathing sounds, coughing, and vehicle sounds, from the open source datasets Audioset and Freesound, and played them through speakers (to simulate a wider range of external environments) to be recorded by a stethoscope, with a total recording time of more than 20 hours.

[0060] 2) CrossFilterSound algorithm flow and framework

[0061] The algorithm flow chart is as follows Figure 2 As shown, the main processing process is as follows:

[0062] 1. Divide the total number of synthesized noisy heart and lung sound data and pure heart and lung sound data (more than 15,000) into training, testing and validation ratios of 70% / 15% / 15%.

[0063] 2. Perform short-time Fourier transform (STFT) on each data with a short-time window of 20ms, a minimum frequency of 50Hz, and an overlap of 50% to obtain the frequency domain data of the data (including the real and imaginary data of the frequency domain graph).

[0064] 3. Feature extraction of frequency domain data includes two parts:

[0065] 1) ERB Equivalent Rectangular Bandwidth feature extractor: ERB simulates the selective attention of the human ear to sound frequencies by dividing the frequency range into equivalent rectangular bandwidths. This division takes into account the different perception abilities of the human ear to high-frequency and low-frequency sounds, resulting in different frequency resolutions in the high-frequency and low-frequency bands. The frequency bins of the spectrogram are logarithmically compressed into 32 ERB bands, and only the real-valued part of the STFT transformed data is processed;

[0066] 2) Complex Feature Extractor: The imaginary part of the STFT data is used as the input of the imaginary encoder.

[0067] 4. ERB and imaginary self-attention encoder (main structure as Figure 3 shown):

[0068] The input of the encoder is ERB feature + time series feature (imaginary feature + time series feature), and the time series feature is encoded in the order of short time frame windows. The self-attention function is the ERB feature

[0069] + time series features (imaginary features + time series features) and a set of key-value pairs are mapped to the output, where Q, K, V (query, key, value) are all self-embedding vector matrices, d is the embedding vector dimension size, T is the matrix operation, and the self-attention calculation formula is as follows:

[0070]

[0071] Where × is the dot multiplication operator, + is the addition operator, ÷ is the division operator, concat is the concatenation operator, MLP (Multilayer Perceptron) multilayer perceptron, softmax and RMSNorm normalization formulas are as follows:

[0072]

[0073]

[0074] 5. Cross-attention and ERB (imaginary number) encoder (main structure such as Figure 4 shown):

[0075] Cross attention mainly associates the ERB encoder and the imaginary decoder to learn the parameter matrix of the temporal feature correlation of the real and imaginary features of the spectrum. Its input is the Q matrix of the ERB encoder and the K, V matrix of the imaginary decoder (the symmetric imaginary encoder and ERB decoder have the Q matrix of the imaginary encoder and the K, V matrix of the ERB decoder, and Q, K, V are defined as above). ERB and proj C is the dimension of the mapping function used to align the ERB encoding and the imaginary encoding. The cross attention calculation formula is as follows:

[0076]

[0077] 6.ERB gain synthesis and imaginary part filtering:

[0078] The ERB code and the imaginary code are synthesized and filtered through the decoder data and concatenated into the frequency domain data of the output data.

[0079] 7. Inverse short-time discrete Fourier transform ISTFT:

[0080] The signal represented in the frequency domain is converted back to the time domain to obtain denoised audio data.

[0081] (III) Evaluation of noise reduction effect of CrossFilterSound algorithm:

[0082] We use the indicator: maximizing the scale-invariant signal-to-distortion ratio (SI-SDR, similar to SNR) to evaluate the quality of our deep denoising model. On average, the 15% validation set data can be improved by 15.34dB, which is a significant improvement compared to noisy data and traditional methods.

[0083]

[0084] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for reducing the noise of heart and lung sounds based on a sound stethoscope, wherein the heart and lung sounds are collected by a collection module, converted into digital form by an analog-to-digital converter and stored, and characterized in that The stored heart and lung sound data is subjected to traditional time-frequency denoising and deep learning algorithm denoising. The deep learning algorithm denoising process includes the construction of a clean heart and lung sound dataset and a noise dataset: The clean heart and lung sound dataset includes self-collected data, open-source heart sound dataset and open-source lung sound dataset. The self-collected data includes more than 10,000 heart and lung sound data collected by stethoscope in night environment (actual monitoring clinic ambient volume below 20dB) and daytime environment (actual monitoring clinic ambient volume below 40dB), with a total time of more than 100 hours. The actual data collection comes from various groups of people. The noise dataset consists of two parts. One part is the real clinic environment noise collected by the stethoscope in the daytime noise environment and the environmental sound data collected by the stethoscope in the night environment, with a total time of more than 50 hours. The other part is to select multiple different categories of audio from the open source dataset and play them to the stethoscope through the speaker, with a total time of more than 20 hours. The noisy heart and lung sound data is obtained by randomly synthesizing the clean heart and lung sound data and the noise data set. The obtained data set is subjected to denoising and noise removal processing. The steps are as follows: (1) Divide the synthesized noisy heart and lung sound data and the clean heart and lung sound data into training, testing and validation ratios; (2) Perform short-time Fourier transform (STFT) on each data with a short-time window of 20 ms, a minimum frequency of 50 Hz, and an overlap of 50% to obtain the frequency domain data of the data (including the real and imaginary data of the frequency domain graph); (3) Extract the frequency domain data through the ERB equivalent rectangular bandwidth feature extractor and the complex feature extractor; (4) The data extracted in step 3 are temporally encoded by the ERB self-attention encoder and the imaginary part self-attention decoder respectively. The input of the encoder is the ERB feature + temporal feature (imaginary feature + temporal feature). The temporal feature is temporally encoded according to the order of the short time frame window. (5) Perform cross attention, which is to associate the ERB encoder and the imaginary decoder to learn the parameter matrix of the temporal feature correlation between the real and imaginary features of the spectrum; (6) synthesizing and filtering the ERB coded and imaginary coded data passed through the decoder, and splicing them into frequency domain data of the output data; (7) Convert the signal represented in the frequency domain back to the time domain to obtain denoised audio data.

2. The method for reducing the noise of cardiopulmonary sounds based on a sound stethoscope according to claim 1, characterized in that The self-attention function of the self-attention encoder in step (4) is the embedding query of ERB features + temporal features (imaginary features + temporal features) and a set of key-value pairs mapped to the output, where Q, K, V (query, key, value) are all self-embedded vector matrices, d is the embedding vector dimension size, T is the matrix operation, and the self-attention calculation formula is as follows:

3. The method for reducing the noise of cardiopulmonary sounds based on a sound stethoscope according to claim 1, characterized in that In the step (1), the synthesized noisy heart and lung sound data and the clean heart and lung sound data are divided into training, testing and validation according to a total ratio of 70% / 15% / 15%.

4. The method for reducing the noise of cardiopulmonary sounds based on a sound stethoscope according to claim 1, characterized in that The data of heart and lung sounds were collected from 7 people, and the age structure was as follows: 1 person under 20 years old, 2 people aged 20-40 years old, and 4 people over 40 years old.

5. The method for reducing the noise of cardiopulmonary sounds based on a sound stethoscope according to claim 1 or 2, characterized in that The traditional time-frequency noise reduction processing method is as follows: (a) The heart and lung sound data collected by the stethoscope are divided into frames with 160 sampling points per frame (the maximum sampling rate is 44100 Hz), and then the energy sum (sum of square amplitude) of each frame is calculated, and a discrete Fourier transform (FFT) is performed, including the function values ​​of 256 points, and the energy spectrum, amplitude spectrum, logarithmic energy spectrum and logarithmic amplitude spectrum are calculated at the same time, and the noise spectrum is estimated based on these data; (b) The a priori and a posteriori SNR of each frame. The so-called a priori SNR is the ratio of the power spectrum of the pure signal to the power spectrum of the noise (ideal value), while the a posteriori SNR is the ratio of the power spectrum of the noisy signal to the power spectrum of the noise. The a priori SNR (estimated value) and the instantaneous SNR calculated in the previous frame are used as the result of the a priori SNR. The calculated SNR is used to update the three features of the LRT (Likelihood Rate Test) mean feature, spectrum flatness and spectrum difference. (c) Calculate the probability of speech and noise, and update the noise spectrum; (d) Finally, the Wiener filter is calculated to obtain the real and imaginary correction coefficients (frequency domain) of the current frame through the calculated signal-to-noise probability, and the best noise reduction audio data is obtained through IFFT (inverse Fourier transform) and frame synthesis operations.

6. A cardiopulmonary sound noise reduction system based on a sound stethoscope, characterized in that It comprises a cardiopulmonary stethoscope sound signal acquisition module and a sound signal processing and noise reduction module, and the sound signal processing and noise reduction module performs noise reduction and removes noise according to any one of the methods described in claims 1-5.

7. The cardiopulmonary sound noise reduction system based on a sound stethoscope according to claim 6, characterized in that The cardiopulmonary stethoscope sound signal acquisition module includes a transmitter and a receiver. The transmitter includes a front-end circuit, a sensor module, a microcontroller, a wifi module and a PC connection module. The front-end circuit includes a signal acquisition and preprocessing circuit: the sensor module includes a microphone with two diaphragms and a piezoelectric sensor. The stethoscope diaphragm detects the sound signal and then transmits it to another diaphragm in the microphone and then to the piezoelectric sensor.

8. The cardiopulmonary sound noise reduction system based on a sound stethoscope according to claim 7, characterized in that The pre-processing circuit is composed of a primary amplifying circuit, a filtering circuit and a secondary amplifying circuit.

Images