Hearing detection system and method based on hearing state and hearing threshold

Abstract

The invention relates to a hearing detection system and method based on a hearing state and a hearing threshold, and belongs to the technical field of hearing system detection, and the system comprises a collection and transmission module which is used for transmitting a stimulation signal and collecting an auditory meatus signal. And the fine structure detection mechanism comprises a DPOAEs fine structure detection module and an SFOAEs fine structure detection module which are respectively used for extracting DPOAEs fine structure information and SFOAEs fine structure information of otoacoustic emission from the auditory meatus signal. The hearing detection analysis and prediction mechanism comprises a hearing threshold detection module and a hearing state screening module which are respectively used for acquiring DPOAEs fine structure information and SFOAEs fine structure information of multiple frequency points and multiple test intensities through the fine structure detection mechanism, constructing an input feature matrix, and screening the hearing threshold detection module and the hearing state screening module; and calling a pre-trained deep learning model to predict hearing thresholds and hearing screening under different frequencies according to the input feature matrix.

Description

Technical Field

[0001] The present invention relates to the technical field of auditory system detection, and in particular to a hearing detection system and method based on hearing status and hearing threshold. Background Art

[0002] Otoacoustic emissions (OAEs) are weak audio frequencies generated in the cochlea of ​​the inner ear, transmitted through the ossicular chain and the eardrum, and released into the external auditory canal. They are part of the normal function of the human ear. Depending on the presence or absence of external stimuli, OAEs can be divided into two categories: spontaneous Otoacoustic Emissions (SOAEs) and evoked Otoacoustic Emissions (EOAEs). EOAEs are further divided into three categories based on the evoked stimuli: transient-evoked Otoacoustic Emissions (TEOAEs), distortion-product Otoacoustic Emissions (DPOAEs), and stimulus-frequency Otoacoustic Emissions (SFOAEs).

[0003] Because the pure-tone audiometry currently used in clinical practice is a behavioral test requiring subjective feedback from the subject, it is significantly affected by subjective factors such as attention and cooperation. This makes this method unsuitable for individuals with limited cooperation, such as infants and young children. Stimulus-frequency otoacoustic emissions (SFOAEs) are weak, voluntary acoustic signals emitted by the cochlea in response to a single-frequency stimulus. Distortion-product otoacoustic emissions (DPOAEs) are weak, voluntary acoustic signals proportional to the frequency of a pair of proportionally spaced tones in response to the cochlea's stimulation. Because the evoked signal frequency and stimulus frequency are highly correlated, both DPOAEs and SFOAEs exhibit excellent frequency specificity. Furthermore, due to their different generation mechanisms, they produce distinct active response patterns in cochlear outer hair cells. DPOAEs are more sensitive to mild to moderate hearing loss, while SFOAEs can detect moderate to severe hearing loss. Therefore, the combination of SFOAEs and DPOAEs has the potential to accurately, objectively and quantitatively reflect hearing thresholds, and is particularly suitable for hearing testing in people who lack cooperation.

[0004] The prior art discloses portable, full-function otoacoustic emission detection systems, specifically a portable otoacoustic emission detection system based on a USB multimedia sound card, which implements full-function quantitative detection and analysis of transient evoked otoacoustic emissions (TEOAEs) and distortion otoacoustic emissions (DPOAEs) signals. However, these systems do not involve the acquisition of high-frequency resolution DPOAEs or TEOAEs, i.e., the fine structure, nor do they involve detection techniques and methods for utilizing these fine structures to estimate hearing thresholds and screen hearing status in the auditory system. The prior art also discloses a hearing threshold and / or hearing status detection system based on the I / O function of stimulus frequency otoacoustic emissions (SFOAEs), which only involves detection techniques for estimating hearing thresholds using multiple intensity input / output (I / O) functions of stimulus frequency otoacoustic emissions. They also disclose an auditory sensitivity detection system based on stimulus frequency otoacoustic emissions, which only involves intensity sensitivity detection using the waveform shape of each point in the SFOAEs. However, these systems also do not involve the acquisition of high-frequency resolution SFOAEs or the techniques and methods for utilizing them to detect hearing thresholds. In addition, none of the existing public technologies involve a technical method for synchronously collecting DPOAEs and SFOAEs and jointly applying them to detect hearing thresholds or screen hearing status.

[0005] In summary, existing technologies do not perform fine structure detection of SFOAEs or DPOAEs with high frequency resolution, and do not jointly apply the complete information of DPOAEs or SFOAEs to detect hearing thresholds. The accuracy of hearing threshold detection results needs to be further improved. Summary of the Invention

[0006] Based on this, it is necessary to provide a hearing detection system and method based on hearing status and hearing threshold that can perform fine structure detection of SFOAEs or DPOAEs with high frequency resolution, and at the same time jointly apply the complete information of DPOAEs or SFOAEs to detect hearing thresholds, and the hearing threshold detection results have a high accuracy rate.

[0007] A first aspect of the present invention provides a hearing detection system based on hearing status and hearing threshold, the system comprising: An acquisition and transmission module, which is used to transmit stimulation signals and acquire ear canal signals; A fine structure detection mechanism, comprising a DPOAEs fine structure detection module and an SFOAEs fine structure detection module, for respectively extracting DPOAEs fine structure information and SFOAEs fine structure information of otoacoustic emissions from the ear canal signal; A hearing detection, analysis and prediction mechanism includes a hearing threshold detection module and a hearing status screening module, which are respectively used to obtain DPOAEs fine structure information and SFOAEs fine structure information at multiple frequency points and multiple test intensities through the fine structure detection mechanism, construct an input feature matrix, and call a pre-trained deep learning model to predict hearing thresholds and hearing screening at different frequencies based on the input feature matrix.

[0008] In one embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module both include: A test sound signal generating module, the test sound signal generating module is used to generate a corresponding test sound signal according to preset test sound parameters; A test sound signal stimulation module, the test sound signal stimulation module is used to emit the preset test sound signal; The test sound signal monitoring module, the test sound signal stimulation module is used to monitor the test sound signal emitted by the test sound signal stimulation module to obtain corresponding test sound parameters.

[0009] In one embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: a stimulation signal emitting structure, the stimulation signal emitting structure comprising a headphone amplifier and a micro speaker connected in sequence; The headphone amplifier is connected to the output end of the signal conversion structure, and the micro-speaker is divided into a first electroacoustic transducer for transmitting stimulation sound and suppression sound and a second electroacoustic transducer for inducing DPOAEs signal and SFOAEs signal respectively; The first electroacoustic transducer and the second electroacoustic transducer are inserted into the earplug via two sound tubes, and the input ends are respectively connected to the headphone amplifier via TRS interfaces; The micro speaker is used to convert the analog voltage signal into an acoustic signal through electroacoustic conversion, and transmit the acoustic signal to the ear of the person to be tested through the earplug.

[0010] In one embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: A signal recovery structure, comprising a miniature microphone and a microphone amplifier connected in sequence; The miniature microphone includes an acoustic-electric transducer, which is used to convert the acoustic signal into an analog voltage signal. The input end of the miniature microphone is inserted into the earplug through a transmission sound tube, the output end of the miniature microphone is connected to the input end of the microphone amplifier, and the output end of the microphone amplifier is connected to the input end of the signal conversion structure.

[0011] In one embodiment, the hearing threshold detection module includes: A first characteristic matrix generation module, the first characteristic matrix generation module is used to construct a first characteristic matrix based on the DPOAEs fine structure information and the SFOAEs fine structure information extracted by the fine structure detection mechanism; Different acquisition sequences of the fine structure information of DPOAEs and the fine structure information of SFOAEs in the first feature matrix are listed as different frequency points; The hearing threshold detection module selects different matrix column frequency ranges according to different hearing threshold prediction frequencies.

[0012] In one embodiment, the hearing threshold detection module further includes: a hearing threshold prediction module, configured to use the first feature matrix generated by the first feature matrix generation module as input to a pre-trained deep learning model according to different hearing threshold frequencies, so as to call the pre-trained deep learning model to predict the hearing threshold at the corresponding frequency; The characteristic sequence of the first characteristic matrix includes SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio spectrum.

[0013] In one embodiment, the hearing status screening module includes: A second characteristic matrix generation module, the second characteristic matrix generation module is used to construct a second characteristic matrix based on the DPOAEs fine structure information and the SFOAEs fine structure information; The behavior of the second characteristic matrix is ​​the acquisition sequence of the DPOAEs fine structure information and the SFOAEs fine structure information, which is listed as different frequency points; The hearing status screening module selects different matrix column frequency ranges according to different hearing screening classification frequencies; A hearing screening classification module, configured to use the second feature matrix as input to a pre-trained deep learning model according to different hearing screening frequencies, so as to call the pre-trained deep learning model to perform a binary classification on the hearing status of the corresponding hearing screening frequency; The characteristic sequence of the second characteristic matrix includes SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio spectrum.

[0014] A second aspect of the present invention provides a hearing detection method based on hearing status and hearing threshold, which is implemented by the hearing detection system based on hearing status and hearing threshold described in the first aspect. The method includes: Selecting a detection mode, wherein the detection mode includes a hearing threshold detection mode and a hearing status screening mode; After selecting the detection mode, the preset test sound parameters are obtained, and the DPOAEs fine structure information and SFOAEs fine structure information at the specified intensity point and frequency range are detected to construct the input feature matrix within the corresponding frequency range; Using the input feature matrix as input to a pre-trained deep learning model, so as to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened; Based on the selected detection mode, different test sound signals are sent to the person to be tested to obtain corresponding ear canal signals, and the ear canal signals are subjected to hearing threshold detection and hearing status screening.

[0015] In one embodiment, the method of sending different test sound signals to the subject based on the selected detection mode to obtain corresponding ear canal signals, and performing hearing threshold detection and hearing status screening on the ear canal signals includes: When the selected detection mode is the hearing threshold detection mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted into the ear canal of the subject according to the preset test sound parameters to obtain a first ear canal signal; Based on the first ear canal signal, sequentially calculating the SFOAEs signal and the DPOAEs signal of each frequency to obtain corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively; Based on the DPOAEs fine structure information and the SFOAEs fine structure information, corresponding frequency ranges are intercepted from the original spectrum group according to different hearing threshold prediction frequencies, and the intercepted frequency ranges are input into a pre-trained deep learning model to predict the hearing threshold at the corresponding frequency; The DPOAEs fine structure information and SFOAEs fine structure information include SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio.

[0016] In one embodiment, the method of sending different test sound signals to the subject based on the selected detection mode to obtain corresponding ear canal signals, and performing hearing threshold detection and hearing status screening on the ear canal signals further includes: When the selected detection mode is the hearing status screening mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted into the ear canal of the subject according to the preset test sound parameters to obtain the second ear canal signal; Based on the second ear canal signal, sequentially calculating the SFOAEs signal and the DPOAEs signal of each frequency to obtain corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively; Based on the DPOAEs fine structure information and SFOAEs fine structure information, the corresponding frequency range is intercepted from the original spectrum group according to different hearing screening frequencies, and the intercepted frequency range is input into the pre-trained deep learning model to screen the hearing status at the corresponding frequency.

[0017] A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the hearing detection method based on hearing status and hearing threshold as described in the second aspect above is implemented.

[0018] A fourth aspect of the present invention provides a computer storage medium storing a computer program, which, when executed by a processor, implements the hearing detection method based on hearing status and hearing threshold as described in the second aspect above.

[0019] A fifth aspect of the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the hearing detection method based on hearing status and hearing threshold as described in the second aspect above.

[0020] The hearing detection system and method based on hearing status and hearing threshold have the following beneficial effects: (1) The present invention is based on the combined fine structure detection function of SFOAEs and DPOAEs. According to the different test contents required by the test subject, the hearing test analysis and prediction system generates test parameters of different test frequency ranges and intensities, sends test signals through the acquisition and transmission system, and then collects signals in the ear canal of the test subject and inputs them into the fine structure detection system. The fine structure data of DPOAEs and SFOAEs are calculated and input into the hearing test analysis and prediction system for hearing threshold detection or hearing screening test, thereby realizing objective, rapid and accurate detection of the hearing threshold or hearing condition of the auditory system.

[0021] (2) The hearing threshold detection module of the present invention is used to objectively and quantitatively extract the hearing thresholds of multiple frequency points, and can objectively detect the hearing thresholds in clinical practice; the hearing status screening module can objectively obtain the binary classification results of the hearing status of multiple frequency points, realizing rapid screening of the hearing status. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A schematic diagram of the structure of a hearing detection system based on hearing status and hearing threshold provided by the present invention; Figure 2 A schematic structural diagram of the acquisition and transmission module in a specific embodiment provided by the present invention; Figure 3 A schematic diagram of the hearing threshold detection and hearing status screening process in a specific embodiment provided by the present invention; Figure 4 A schematic diagram of a flow chart of detecting a hearing threshold based on a hearing detection module in a specific embodiment provided by the present invention; Figure 5 A schematic diagram of the deep learning model architecture in a specific embodiment provided by the present invention; Figure 6 A schematic diagram of the flow of the hearing detection method based on hearing status and hearing threshold provided by the present invention; Figure 7 This is a diagram of the internal structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0025] The following combination Figures 1 to 7 The present invention describes a hearing detection system and method based on hearing status and hearing threshold.

[0026] like Figure 1 As shown, in one embodiment, a hearing detection system based on hearing status and hearing threshold includes: The acquisition and transmission module is used to transmit stimulation signals and acquire ear canal signals.

[0027] The fine structure detection mechanism includes a DPOAEs fine structure detection module and an SFOAEs fine structure detection module, which are respectively used to extract DPOAEs fine structure information and SFOAEs fine structure information of otoacoustic emissions from ear canal signals.

[0028] The hearing detection, analysis and prediction mechanism includes a hearing threshold detection module and a hearing status screening module, which are respectively used to obtain DPOAEs fine structure information and SFOAEs fine structure information of multiple frequency points and multiple test intensities through the fine structure detection mechanism, construct an input feature matrix, and call a pre-trained deep learning model to predict hearing thresholds and hearing screening at different frequencies based on the input feature matrix.

[0029] In this embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module both include: The test sound signal generating module is used to generate a corresponding test sound signal according to preset test sound parameters.

[0030] The test sound signal stimulation module is used to send out a preset test sound signal.

[0031] The test sound signal monitoring module is used to monitor the test sound signal emitted by the test sound signal stimulation module to obtain corresponding test sound parameters.

[0032] In this embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: The stimulation signal emitting structure includes a headphone amplifier and a micro-speaker connected in sequence. The headphone amplifier is connected to the output end of the signal conversion structure, and the micro-speaker is divided into a first electroacoustic transducer and a second electroacoustic transducer for transmitting stimulation sound and suppression sound, which are used to induce DPOAEs signals and SFOAEs signals, respectively. The first electroacoustic transducer and the second electroacoustic transducer are inserted into the earplug via two sound tubes, and the input ends are respectively connected to the headphone amplifier via a TRS interface. The micro-speaker is used to convert the analog voltage signal into an acoustic signal through electroacoustic conversion, and transmit the acoustic signal to the ear of the subject through the earplug.

[0033] In this embodiment, the DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: The signal acquisition structure includes a miniature microphone and a microphone amplifier connected in sequence. The miniature microphone includes an acoustic-electric transducer for converting acoustic signals into analog voltage signals. The input end of the miniature microphone is inserted into the earplug through a transmission sound tube. The output end of the miniature microphone is connected to the input end of the microphone amplifier, and the output end of the microphone amplifier is connected to the input end of the signal conversion structure.

[0034] In this embodiment, the hearing threshold detection module includes: The first feature matrix generation module is configured to construct a first feature matrix based on the DPOAE and SFOAE fine structure information extracted by the fine structure detection module. The first feature matrix represents different acquisition sequences of the DPOAE and SFOAE fine structure information, listed as different frequency points. The hearing threshold detection module selects different matrix column frequency ranges based on different hearing threshold prediction frequencies.

[0035] In this embodiment, the hearing threshold detection module further includes: The hearing threshold prediction module is configured to use the first feature matrix generated by the first feature matrix generation module as input to a pre-trained deep learning model based on different hearing threshold frequencies, thereby predicting the hearing threshold at the corresponding frequency using the pre-trained deep learning model. The feature sequence of the first feature matrix includes the SFOAEs amplitude spectrum, the SFOAEs signal-to-noise ratio spectrum, the DPOAEs amplitude spectrum, and the DPOAEs signal-to-noise ratio spectrum.

[0036] In this embodiment, the hearing status screening module includes: The second feature matrix generation module is used to construct a second feature matrix based on the DPOAEs fine structure information and the SFOAEs fine structure information. The rows of the second feature matrix are the acquisition sequence of the DPOAEs fine structure information and the SFOAEs fine structure information, listed as different frequency points. The hearing status screening module selects different matrix column frequency ranges based on different hearing screening classification frequencies.

[0037] The hearing screening classification module is used to use the second feature matrix as input to a pre-trained deep learning model based on different hearing screening frequencies, thereby calling the pre-trained deep learning model to perform binary classification of the hearing status at the corresponding hearing screening frequencies. The feature sequence of the second feature matrix includes the SFOAEs amplitude spectrum, the SFOAEs signal-to-noise ratio spectrum, the DPOAEs amplitude spectrum, and the DPOAEs signal-to-noise ratio spectrum.

[0038] See also Figures 2 to 5 As shown, in a specific embodiment, the hearing detection system based on hearing status and hearing threshold provided by the present invention includes: an acquisition and transmission system for transmitting stimulation signals and acquiring ear canal signals; a fine structure detection system for calculating and extracting multi-frequency SFOAEs and DPOAEs signals, that is, their fine structure information, from the acquired ear signals; and a hearing detection analysis system for performing signal processing and analysis on the fine structure information of DPOAEs and SFOAEs to complete hearing threshold prediction or hearing status screening.

[0039] Combine Figure 2As shown, the acquisition and transmission system includes a signal sending device, a signal conversion device, a stimulation signal sending structure and a signal acquisition structure.

[0040] The signal sending device is used to stimulate the signal source to send a digital signal, and the signal sending device can use a computer 1 to send the digital signal.

[0041] The signal conversion device is used to perform A / D and D / A conversion on the signal. The signal transmission device can use an acquisition card 2 to achieve signal conversion. Acquisition card 2 is an acquisition card that can be connected to computer 1 to convert the digital signal sent by computer 1 into an analog voltage signal. When performing testing, a portable acquisition card with a 24-bit sampling depth and a sampling rate of 48kHz can be used, connected to computer 1 via a USB port.

[0042] The stimulation signal emitting structure is used to transmit stimulation signals to the human ear, and may include a headphone amplifier 3 and a micro-speaker 4 connected in sequence. The headphone amplifier 3 is connected to the two output ends of the acquisition card 2 to achieve power amplification and impedance matching of the two output signals of the acquisition card 2. The micro-speaker 4 includes two electro-acoustic transducers that respectively generate stimulation sound and suppression sound, which are used to induce SFOAEs and DPOAEs signals. The two electro-acoustic transducers are inserted into the earplug through two sound tubes, and the input ends of the two electro-acoustic transducers are respectively connected to the headphone amplifier 3 through interfaces. The micro-speaker 4 is used to electroacoustically convert the analog voltage signal into an acoustic signal, which is sent to the subject's ear through the earplug. The micro-speaker 4 can adopt various products that can meet the performance indicators, such as plug-in micro-speakers.

[0043] The signal acquisition structure is used to collect otoacoustic emission signals and other signals from the external auditory canal. It includes a miniature microphone 5 and a microphone amplifier 6 connected in sequence. To isolate the sound in the subject's external auditory canal from external sounds, in this example, the miniature speaker 4 and miniature microphone 5 can be inserted into the same soft earplug. The miniature microphone 5 includes an acoustic-to-electric transducer, which is used to collect otoacoustic emission signals and other signals from the external auditory canal and convert the collected acoustic signals into electrical signals. The input of the miniature microphone 5 is inserted into the earplug via an acoustic tube. The sound signal in the ear canal passes through the acoustic-to-electric transducer, where it is converted into an analog voltage signal. The output of the miniature microphone 5 is connected to the input of the microphone amplifier 6, which is then connected to the A / D input of the acquisition card 2. The miniature microphone 5 can be a variety of products that meet performance requirements, such as plug-in miniature microphones. The microphone amplifier 6 is used to amplify the signal output by the miniature microphone 5. The amplification factor can be adjusted according to actual needs, including but not limited to 0dB, 20dB, and 40dB.

[0044] Specifically, computer 1 may also include an acquisition card driver system. This system drives the D / A port of acquisition card 2 to receive signals from computer 1. After receiving power amplification and impedance matching through headphone amplifier 3, the signals are transmitted to the subject's ears through micro-speaker 4. Simultaneously, the A / D port of acquisition card 2 receives signals returned by microphone amplifier 6 and transmits them to the hearing threshold analysis and prediction system.

[0045] Combine Figure 3 As shown, when used to predict hearing thresholds or screen hearing status, the hearing test analysis system first obtains information about the test subject, then determines the test content and activates different test modules based on the selected test content. Based on the SFOAEs and DPOAEs information obtained by the acquisition and transmission system and the fine structure detection system, the hearing test analysis system uses the corresponding feature matrix generation module and prediction module to predict hearing thresholds or screen hearing status.

[0046] The hearing threshold test process involves the following steps: The acquisition and transmission system outputs and collects the back-acquired signals at a preset stimulus frequency range and multiple test intensities. The fine structure detection module constructs the fine structure spectra of SFOAEs and DPOAEs at multiple test intensities. The feature matrix generation module then extracts the feature matrix required for prediction based on the desired hearing threshold frequency. Finally, a pre-trained network model is used to determine the hearing threshold corresponding to the desired frequency.

[0047] The hearing screening process involves the following steps: The acquisition and transmission system outputs and collects the back-acquired signals within a preset stimulation frequency range and a single test intensity. The fine structure detection module constructs the fine structure spectra of SFOAEs and DPOAEs at their respective designated single test intensities. The feature matrix generation module then extracts the feature matrix required for prediction based on the hearing condition frequency being screened. Finally, a pre-trained network model is used to determine the hearing condition corresponding to the frequency being screened.

[0048] Specifically, Figure 4 The detailed display shows the further refined module division diagram for the instrument's hearing threshold detection, including: hearing threshold test sound signal generation module, hearing threshold test sound signal stimulation module, hearing threshold test sound signal acquisition module, hearing threshold fine structure detection module, hearing threshold waveform display module, hearing threshold feature matrix generation module, hearing threshold prediction module and hearing threshold result report generation and storage module.

[0049] The hearing threshold test sound signal generation module is used to generate the test sound signals required to induce SFOAEs and DPOAEs based on pre-set test parameters. The hearing threshold test sound signal stimulation module is used to transmit stimulation sounds to the generated test sound signals. The hearing threshold test sound signal acquisition module is used to record the echo sound signals in the external auditory canal while the stimulation module emits stimulation sounds. The hearing threshold fine structure detection module is used to calculate and extract the fine structure information of SFOAEs and DPOAEs from the recorded external auditory canal signals.

[0050] Specifically, the processing is performed based on test intensity and OAE type. First, the repeatedly acquired time-domain signals are coherently averaged and denoised. Time-frequency analysis and filtering are then performed on the denoised and coherently averaged signals to obtain the multi-frequency OAE spectra, or fine structure information. Fine structure information describes the frequency, elicited amplitude, and signal-to-noise ratio of the OAEs. The resulting extracted information structure includes the amplitude and signal-to-noise ratio spectra of the SFOAEs, as well as the amplitude and signal-to-noise ratio spectra of the SFOAEs. In this embodiment, the hearing threshold waveform display module is used to display in real time the calculated amplitude spectra and signal-to-noise ratio spectra of SFOAEs and DPOAEs under different test sound intensities. The hearing threshold feature matrix generation module is used to extract the feature matrix required for network model input from the fine structure information based on the specific hearing threshold prediction frequency. The detailed information of the matrix is ​​the behavior sequence type dimension, which includes SFOAEs amplitude, SFOAEs signal-to-noise ratio, DPOAEs amplitude, and DPOAEs signal-to-noise ratio, which are listed as frequency dimensions. The frequency value range is related to the hearing threshold frequency to be predicted. The hearing threshold prediction module uses the generated feature matrix as input and predicts the hearing thresholds of different frequencies through a pre-trained deep learning model. The hearing threshold result report generation and storage module is used to generate hearing threshold prediction results of different frequencies and save the results and the fine structure detection results in the report.

[0051] Specifically, the further refined module divisions during hearing status screening by the instrument include: hearing screening test sound signal generation module, hearing screening test sound signal stimulation module, hearing screening test sound signal acquisition module, hearing screening fine structure detection module, hearing screening waveform display module, hearing screening feature matrix generation module, hearing screening prediction module and hearing screening result report generation and storage module.

[0052] The hearing threshold test sound signal generation module is used to generate the test sound signals required to induce SFOAEs and DPOAEs based on pre-set test parameters. The hearing screening test sound signal stimulation module is used to send stimulation sounds to the generated test sound signals. The hearing screening test sound signal acquisition module is used to record the echo sound signals in the external auditory canal while the stimulation module emits stimulation sounds. The hearing screening fine structure detection module is used to calculate and extract the fine structure information of SFOAEs and DPOAEs from the recorded external auditory canal signals.

[0053] Specifically, processing is performed based on test intensity and OAE type. First, the repeatedly acquired time-domain signals are coherently averaged and denoised. Time-frequency analysis and filtering of the denoised and coherently averaged signals yield multi-frequency OAE spectra, i.e., fine structure information. This fine structure information describes the frequency, elicited amplitude, and signal-to-noise ratio of the OAEs. The resulting extracted information structure includes the amplitude and signal-to-noise ratio spectra of SFOAEs, as well as the amplitude and signal-to-noise ratio spectra of SFOAEs. The hearing screening waveform display module displays the calculated amplitude and signal-to-noise ratio spectra of SFOAEs and DPOAEs at different test sound intensities in real time. The hearing screening feature matrix generation module extracts the feature matrix required for network model input from this fine structure information, based on the specific hearing screening prediction frequency. The matrix details the behavior sequence type dimension, which includes the SFOAE amplitude, SFOAE signal-to-noise ratio, DPOAE amplitude, and DPOAE signal-to-noise ratio, and the frequency dimension, whose frequency range is related to the predicted hearing screening frequency. The hearing screening prediction module uses the generated feature matrix as input and uses a pre-trained network model to screen hearing conditions at different frequencies. The hearing screening result report generation and storage module is used to generate hearing condition screening results at different frequencies and save these results together with the fine structure test results in a report.

[0054] Specific, combined Figure 5As shown, the network models for both hearing threshold detection and hearing status screening utilize a deep learning-based convolutional neural network (CNN). The network is trained using supervised learning techniques based on backpropagation. The typical structure consists of an input layer, a self-feature extraction layer, and an output layer. The input layer receives the feature matrix from the feature extraction module and performs preprocessing operations, including standardization. The self-feature extraction layer consists of 600 one-dimensional convolutional kernels of size 1×3 and integrates activation functions and pooling operations. After performing high-dimensional non-phenomenal operations on the feature matrix, it outputs a one-dimensional feature vector representing the hearing threshold or hearing status. The output layer, composed of a fully connected neural network, receives the one-dimensional feature vector and outputs the predicted result. For hearing threshold prediction, the output is the predicted hearing threshold; for hearing status screening, the output is the probability of hearing loss. A result with a predicted probability exceeding 0.5 is generally considered to indicate hearing loss. The initial parameters of the neural network model are random values. During training, the weights are continuously updated by forward propagating the input data and backpropagating the error signal, making the actual output closer to the expected output. The training process stops when the error signal decreases to the set minimum value or reaches the set upper limit of the training steps, and finally the weight parameters are fixed.

[0055] The following describes the hearing detection method based on hearing status and hearing threshold provided by the present invention. The hearing detection method based on hearing status and hearing threshold described below and the hearing detection system based on hearing status and hearing threshold described above can correspond to each other.

[0056] like Figure 6 As shown, in one embodiment, a hearing detection method based on hearing status and hearing threshold includes the following steps: Step S610: Select a detection mode, which includes a hearing threshold detection mode and a hearing status screening mode.

[0057] Step S620 , after the detection mode is selected, the preset test sound parameters are obtained, and the DPOAEs fine structure information and the SFOAEs fine structure information within the specified intensity point and frequency range are detected to construct an input feature matrix within the corresponding frequency range.

[0058] Step S630: Using the input feature matrix as the input of the pre-trained deep learning model to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened.

[0059] Step S640: Based on the selected detection mode, different test sound signals are sent to the subject to be tested to obtain corresponding ear canal signals, and the ear canal signals are subjected to hearing threshold detection and hearing status screening.

[0060] In this embodiment, the hearing detection method based on hearing status and hearing threshold provided by the present invention, step S640 specifically includes the following steps: Step S641 , when the selected detection mode is the hearing threshold detection mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted to the ear canal of the subject according to the preset test sound parameters to obtain a first ear canal signal.

[0061] Step S642: Based on the first ear canal signal, the SFOAEs signal and the DPOAEs signal of each frequency are calculated in sequence to obtain the corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively.

[0062] In step S643, based on the DPOAEs fine structure information and the SFOAEs fine structure information, the corresponding frequency range is intercepted from the original spectrum group according to different hearing threshold prediction frequencies, and the intercepted frequency range is input into the pre-trained deep learning model to predict the hearing threshold at the corresponding frequency.

[0063] Among them, the DPOAEs fine structure information and SFOAEs fine structure information include SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio.

[0064] In this embodiment, the hearing detection method based on hearing status and hearing threshold provided by the present invention, step S640 specifically further includes the following steps: Step S644: When the selected detection mode is the hearing status screening mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted into the ear canal of the subject according to the preset test sound parameters to obtain a second ear canal signal.

[0065] Step S645 : Based on the second ear canal signal, the SFOAEs signal and the DPOAEs signal of each frequency are calculated in sequence to obtain the corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively.

[0066] In step S646, based on the DPOAEs fine structure information and the SFOAEs fine structure information, the corresponding frequency range is intercepted from the original spectrum group according to different hearing screening frequencies, and the intercepted frequency range is input into the pre-trained deep learning model to screen the hearing status at the corresponding frequency.

[0067] Figure 7 The following is a schematic diagram of the physical structure of an electronic device. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Figure 7As shown. The electronic device includes a processor, an internal memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a hearing detection method based on hearing status and hearing threshold is implemented, the method comprising: Select the test mode, which includes hearing threshold test mode and hearing status screening mode; After selecting the detection mode, the preset test sound parameters are obtained, and the DPOAEs fine structure information and SFOAEs fine structure information at the specified intensity point and frequency range are detected to construct the input feature matrix within the corresponding frequency range; The input feature matrix is ​​used as the input of the pre-trained deep learning model to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened; Based on the selected detection mode, different test sound signals are sent to the person being tested to obtain the corresponding ear canal signals, and the ear canal signals are then used for hearing threshold detection and hearing status screening.

[0068] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the electronic device to which the solution of the present invention is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0069] In another aspect, the present invention further provides a computer storage medium storing a computer program. When the computer program is executed by a processor, a hearing detection method based on hearing status and hearing threshold is implemented. The method comprises: Select the test mode, which includes hearing threshold test mode and hearing status screening mode; After selecting the detection mode, the preset test sound parameters are obtained, and the DPOAEs fine structure information and SFOAEs fine structure information at the specified intensity point and frequency range are detected to construct the input feature matrix within the corresponding frequency range; The input feature matrix is ​​used as the input of the pre-trained deep learning model to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened; Based on the selected detection mode, different test sound signals are sent to the person being tested to obtain the corresponding ear canal signals, and the ear canal signals are then used for hearing threshold detection and hearing status screening.

[0070] In yet another aspect, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, implements a hearing detection method based on hearing status and hearing threshold, the method comprising: Select the test mode, which includes hearing threshold test mode and hearing status screening mode; After selecting the detection mode, the preset test sound parameters are obtained, and the DPOAEs fine structure information and SFOAEs fine structure information at the specified intensity point and frequency range are detected to construct the input feature matrix within the corresponding frequency range; The input feature matrix is ​​used as the input of the pre-trained deep learning model to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened; Based on the selected detection mode, different test sound signals are sent to the person being tested to obtain the corresponding ear canal signals, and the ear canal signals are then used for hearing threshold detection and hearing status screening.

[0071] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0072] By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0073] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0074] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A hearing detection system based on hearing status and hearing threshold, characterized in that: The system comprises: An acquisition and transmission module, which is used to transmit stimulation signals and acquire ear canal signals; A fine structure detection mechanism, comprising a DPOAEs fine structure detection module and an SFOAEs fine structure detection module, for respectively extracting DPOAEs fine structure information and SFOAEs fine structure information of otoacoustic emissions from the ear canal signal; A hearing detection, analysis and prediction mechanism includes a hearing threshold detection module and a hearing status screening module, which are respectively used to obtain DPOAEs fine structure information and SFOAEs fine structure information at multiple frequency points and multiple test intensities through the fine structure detection mechanism, construct an input feature matrix, and call a pre-trained deep learning model to predict hearing thresholds and hearing screening at different frequencies based on the input feature matrix.

2. The hearing detection system based on hearing status and hearing threshold according to claim 1, characterized in that: The DPOAEs fine structure detection module and the SFOAEs fine structure detection module both include: A test sound signal generating module, the test sound signal generating module is used to generate a corresponding test sound signal according to preset test sound parameters; A test sound signal stimulation module, the test sound signal stimulation module is used to emit the preset test sound signal; The test sound signal monitoring module, the test sound signal stimulation module is used to monitor the test sound signal emitted by the test sound signal stimulation module to obtain corresponding test sound parameters.

3. The hearing detection system based on hearing status and hearing threshold according to claim 2, characterized in that: The DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: a stimulation signal emitting structure, the stimulation signal emitting structure comprising a headphone amplifier and a micro speaker connected in sequence; The headphone amplifier is connected to the output end of the signal conversion structure, and the micro-speaker is divided into a first electroacoustic transducer for transmitting stimulation sound and suppression sound and a second electroacoustic transducer for inducing DPOAEs signal and SFOAEs signal respectively; The first electroacoustic transducer and the second electroacoustic transducer are inserted into the earplug via two sound tubes, and the input ends are respectively connected to the headphone amplifier via TRS interfaces; The micro speaker is used to convert the analog voltage signal into an acoustic signal through electroacoustic conversion, and transmit the acoustic signal to the ear of the person to be tested through the earplug.

4. The hearing detection system based on hearing status and hearing threshold according to claim 3, characterized in that: The DPOAEs fine structure detection module and the SFOAEs fine structure detection module further include: A signal recovery structure, comprising a miniature microphone and a microphone amplifier connected in sequence; The miniature microphone includes an acoustic-electric transducer, which is used to convert the acoustic signal into an analog voltage signal. The input end of the miniature microphone is inserted into the earplug through a transmission sound tube, the output end of the miniature microphone is connected to the input end of the microphone amplifier, and the output end of the microphone amplifier is connected to the input end of the signal conversion structure.

5. The hearing detection system based on hearing status and hearing threshold according to claim 1, characterized in that: The hearing threshold detection module includes: A first characteristic matrix generation module, the first characteristic matrix generation module is used to construct a first characteristic matrix based on the DPOAEs fine structure information and the SFOAEs fine structure information extracted by the fine structure detection mechanism; Different acquisition sequences of the fine structure information of DPOAEs and the fine structure information of SFOAEs in the first feature matrix are listed as different frequency points; The hearing threshold detection module selects different matrix column frequency ranges according to different hearing threshold prediction frequencies.

6. The hearing detection system based on hearing status and hearing threshold according to claim 5, characterized in that: The hearing threshold detection module also includes: a hearing threshold prediction module, configured to use the first feature matrix generated by the first feature matrix generation module as input to a pre-trained deep learning model according to different hearing threshold frequencies, so as to call the pre-trained deep learning model to predict the hearing threshold at the corresponding frequency; The characteristic sequence of the first characteristic matrix includes SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio spectrum.

7. The hearing detection system based on hearing status and hearing threshold according to claim 6, characterized in that: The hearing status screening module includes: A second characteristic matrix generation module, the second characteristic matrix generation module is used to construct a second characteristic matrix based on the DPOAEs fine structure information and the SFOAEs fine structure information; The behavior of the second characteristic matrix is ​​the acquisition sequence of the DPOAEs fine structure information and the SFOAEs fine structure information, which is listed as different frequency points; The hearing status screening module selects different matrix column frequency ranges according to different hearing screening classification frequencies; A hearing screening classification module, configured to use the second feature matrix as input to a pre-trained deep learning model according to different hearing screening frequencies, so as to call the pre-trained deep learning model to perform a binary classification on the hearing status of the corresponding hearing screening frequency; The characteristic sequence of the second characteristic matrix includes SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio spectrum.

8. A hearing detection method based on hearing status and hearing threshold, characterized in that: The method is implemented by the hearing detection system based on hearing status and hearing threshold according to any one of claims 1 to 7, and comprises: Selecting a detection mode, wherein the detection mode includes a hearing threshold detection mode and a hearing status screening mode; After selecting the detection mode, the preset test sound parameters are obtained, and the DPOAEs fine structure information and SFOAEs fine structure information at the specified intensity point and frequency range are detected to construct the input feature matrix within the corresponding frequency range; Using the input feature matrix as input to a pre-trained deep learning model, so as to call the pre-trained deep learning model to output the hearing threshold of the frequency range to be predicted or the hearing status of the frequency range to be screened; Based on the selected detection mode, different test sound signals are sent to the person to be tested to obtain corresponding ear canal signals, and the ear canal signals are subjected to hearing threshold detection and hearing status screening.

9. The hearing detection method based on hearing status and hearing threshold according to claim 8, characterized in that: The method of sending different test sound signals to the subject based on the selected detection mode to obtain corresponding ear canal signals, and performing hearing threshold detection and hearing status screening on the ear canal signals includes: When the selected detection mode is the hearing threshold detection mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted into the ear canal of the subject according to the preset test sound parameters to obtain a first ear canal signal; Based on the first ear canal signal, sequentially calculating the SFOAEs signal and the DPOAEs signal of each frequency to obtain corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively; Based on the DPOAEs fine structure information and the SFOAEs fine structure information, corresponding frequency ranges are intercepted from the original spectrum group according to different hearing threshold prediction frequencies, and the intercepted frequency ranges are input into a pre-trained deep learning model to predict the hearing threshold at the corresponding frequency; The DPOAEs fine structure information and SFOAEs fine structure information include SFOAEs amplitude spectrum, SFOAEs signal-to-noise ratio spectrum, DPOAEs amplitude spectrum and DPOAEs signal-to-noise ratio.

10. The hearing detection method based on hearing status and hearing threshold according to claim 9, characterized in that: The method further includes: sending different test sound signals to the subject based on the selected detection mode to obtain corresponding ear canal signals, and performing hearing threshold detection and hearing status screening on the ear canal signals. When the selected detection mode is the hearing status screening mode, the test sound signals of SFOAEs and DPOAEs of multiple test intensities are sequentially transmitted into the ear canal of the subject according to the preset test sound parameters to obtain the second ear canal signal; Based on the second ear canal signal, sequentially calculating the SFOAEs signal and the DPOAEs signal of each frequency to obtain corresponding DPOAEs fine structure information and SFOAEs fine structure information respectively; Based on the DPOAEs fine structure information and SFOAEs fine structure information, the corresponding frequency range is intercepted from the original spectrum group according to different hearing screening frequencies, and the intercepted frequency range is input into the pre-trained deep learning model to screen the hearing status at the corresponding frequency.

Images