Community hearing screening method and system based on environmental noise adaptive correction
By using smartphones for standardized training and real-time noise correction, the problems of shortage of professionals, difficulty in obtaining equipment, and environmental noise interference in community hearing screening have been solved, enabling low-cost and efficient hearing screening and improving screening coverage and accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-15
- Publication Date
- 2026-04-14
AI Technical Summary
Community hearing screening suffers from problems such as a shortage of professional personnel, difficulty in obtaining equipment, non-standard procedures, and environmental noise interference, resulting in inaccurate screening results and difficulty in promoting its use.
An environmental noise adaptive correction method is adopted, which uses smartphones for standardized training, real-time noise monitoring and adaptive correction to lower the professional technical threshold. A single microphone and STFT algorithm are used for environmental assessment and noise correction to ensure the reliability of the audiometry results.
It significantly reduces human error and environmental interference in non-ideal community environments, improves screening coverage and accuracy, reduces hardware costs, supports data management and decision-making, and is suitable for large-scale deployment.
Smart Images
Figure CN121845569A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of community healthcare technology, and in particular relates to a community hearing screening method and system based on adaptive correction of environmental noise. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] Hearing loss is one of the leading causes of disability worldwide, and early detection and intervention are crucial for improving patients' quality of life. However, existing hearing screening methods have the following shortcomings in community application: Shortage of professionals: Most communities lack trained audiology professionals, making it difficult to conduct large-scale hearing screenings in a timely manner, resulting in many cases of hearing loss not being detected early; Difficulty in obtaining equipment: Traditional hearing screening equipment is expensive, bulky, and complex to operate, making it difficult for ordinary community institutions to equip themselves with it, which limits the promotion and popularization of screening work; Non-standard procedures: When non-professionals attempt to conduct screenings, the lack of standardized guidance and training often leads to non-standard operating procedures, which can easily result in erroneous results and affect the accuracy and reliability of the screenings. Environmental noise interference: Community environments often fail to meet the standards of professional soundproof rooms, and environmental noise significantly affects the accuracy of audiometry results, especially when operated by non-professionals. Summary of the Invention
[0004] To address the technical problems mentioned above, this invention provides a community hearing screening method and system based on adaptive environmental noise correction. Through standardized processes, embedded quality control, and especially real-time noise monitoring and adaptive noise correction, it significantly reduces human error and environmental interference, ensuring the reliability of hearing test results even in non-ideal community environments.
[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a community hearing screening method based on adaptive correction for environmental noise, comprising: Acquire the sound signal in the test environment and perform a short-time Fourier transform to obtain the frequency domain spectrum; Set multiple key frequencies; for each key frequency, find the index closest to the key frequency on the frequency axis in the frequency domain spectrum, take the intensity value of the index in all time frames, and calculate the average value to obtain the average value of the original noise amplitude corresponding to the key frequency, and perform smoothing to obtain the smoothing result; calculate the average value of the smoothing results corresponding to all key frequencies to obtain the average noise. If the average noise is lower than the set value, the test environment is considered suitable for testing. For each key frequency, a pure tone is played, and the minimum volume that the subject can hear is recorded as the initial baseline threshold. The initial baseline threshold is then noise-corrected to obtain the noise-compensated baseline threshold. If the noise-compensated baseline threshold exceeds the clinical cutoff value, potential hearing loss is considered to have been detected.
[0006] Furthermore, the original noise amplitude average value is expressed by the formula: noise_levelx=Mean(magnitude[idx,:]); where idx represents the index on the frequency axis that is closest to the x-th key frequency in the time-frequency graph, magnitude[idx,:] represents the intensity value of index idx in all time frames, Mean represents the average value, and noise_levelx represents the original noise amplitude average value corresponding to the x-th key frequency.
[0007] Furthermore, the smoothing process includes: for each key frequency, adding the average value of the original noise amplitude to a queue; whenever a new average value of the original noise amplitude is added to the queue, automatically removing the oldest value; and calculating the average value of all values in the queue as the smoothing result.
[0008] Furthermore, the noise correction includes: for each key frequency, calculating the difference between the smoothing result and the initial baseline threshold; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, then no compensation is performed.
[0009] Furthermore, the noise correction includes: for each key frequency, based on the frequency domain spectrum and the initial baseline threshold, obtaining the noise-compensated baseline threshold through a noise correction model.
[0010] A second aspect of the present invention provides a community hearing screening system based on adaptive correction for environmental noise, comprising: The signal transformation module is configured to acquire sound signals in the test environment and perform short-time Fourier transform to obtain a frequency domain spectrum. The environmental assessment module is configured to: set multiple key frequencies; for each key frequency, find the index closest to the key frequency on the frequency axis in the frequency domain spectrum, take the intensity value of the index in all time frames, calculate the average value, obtain the average value of the original noise amplitude corresponding to the key frequency, and perform smoothing to obtain the smoothing result; calculate the average value of the smoothing results corresponding to all key frequencies to obtain the average noise; if the average noise is lower than the set value, the test environment is considered suitable for testing. The hearing screening module is configured to: play a pure tone for each key frequency, record the minimum volume that the subject can hear as the initial baseline threshold, perform noise correction on the initial baseline threshold to obtain the noise-compensated baseline threshold, and if the noise-compensated baseline threshold exceeds the clinical threshold, then potential hearing loss is considered to have been detected.
[0011] Furthermore, the noise correction includes: for each key frequency, calculating the difference between the smoothing result and the initial baseline threshold; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, then no compensation is performed.
[0012] Furthermore, the noise correction includes: for each key frequency, based on the frequency domain spectrum and the initial baseline threshold, obtaining the noise-compensated baseline threshold through a noise correction model.
[0013] A third aspect of the invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the community hearing screening method described above, which is based on adaptive correction of ambient noise.
[0014] A fourth aspect of the present invention provides a computer device including a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, wherein the processor executes the program to implement the steps of the community hearing screening method based on adaptive correction of ambient noise described above.
[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention significantly reduces human error and environmental interference through standardized processes, embedded quality control, and especially real-time noise monitoring and adaptive noise correction, ensuring the reliability of audiometry results even in non-ideal community environments. Attached Figure Description
[0016] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0017] Figure 1 This is a flowchart of a community hearing screening method based on adaptive correction of environmental noise according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of a computer device according to Embodiment 4 of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.
[0019] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0020] Example 1 This embodiment provides a community hearing screening method based on adaptive correction of environmental noise.
[0021] This embodiment provides a community hearing screening method based on adaptive environmental noise correction. By optimizing the environmental noise detection and correction methods, it reduces the professional technical threshold, improves the screening coverage, and ensures the quality of results.
[0022] This embodiment provides a community hearing screening method based on adaptive correction for environmental noise, such as... Figure 1 As shown, it includes the following steps: Step 1: Operator training.
[0023] Smartphones and other mobile devices provide standardized operational training to operators through multimedia courseware, animations, and quizzes. Before actual screening, operators are required to complete online training and pass an assessment and certification to ensure they master the standardized testing procedures and key points.
[0024] (1) Present the test question: "Please distinguish between the left and right ears of the headphones and do not put them in the wrong ones." (2) Obtain a clear response from the operator and proceed to step 2.
[0025] Among them, smartphones and other mobile terminals are equipped with intelligent guidance interfaces that provide step-by-step guidance to operators during the screening process. The interface prompts operators to perform various operations step by step according to the preset hearing test standard procedures (such as wearing headphones, playing test audio, etc.), and automatically proceeds to the next step based on the subject's response, ensuring that even people without professional backgrounds can complete the test in accordance with the specifications.
[0026] Step 2, Environmental Assessment.
[0027] Before the test begins, the quality control and environmental noise monitoring module uses a smart terminal with a built-in single microphone and optimized noise detection algorithms (STFT, feature extraction, data smoothing) to automatically detect the ambient noise level. If the noise exceeds the standard, it will prompt you to improve the environment or postpone the test.
[0028] Step 201: Collect sound signals in the test environment as background noise (environmental noise), and perform short-time Fourier transform (STFT) on the background noise to convert the time-domain signal into a frequency-domain spectrum in order to extract the spectral characteristics of the environmental noise. Step 202: Set the key frequencies. The key frequencies are selected from the six frequencies commonly used in hearing tests: 250Hz, 500Hz, 1000Hz, 2000Hz, 40000Hz, and 80000Hz. Step 203: Based on the frequency domain spectrum, extract the average value of the original noise amplitude at each key frequency. Specifically: (1) Noise feature extraction: Based on frequency domain analysis, the noise sound pressure level (decibels) at each target test frequency and the overall sound level of broadband noise are extracted. A noise evaluation time window is set, and STFT is repeatedly performed on the continuously acquired audio data to calculate the average spectrum of noise within the time window and obtain stable noise feature values.
[0029] Specifically, for each key frequency, the following steps are performed: Find the index on the frequency axis closest to the key frequency in the frequency domain spectrogram, take the intensity value of that index across all time frames, and calculate the average value to obtain the average raw noise amplitude corresponding to each key frequency. This can be expressed as: noise_levelx = Mean(magnitude[idx,:]), where idx represents the index on the frequency axis closest to the x-th key frequency in the time-frequency graph, magnitude[idx,:] represents the intensity value of index idx across all time frames, Mean represents the average value, and noise_levelx represents the average raw noise amplitude corresponding to the x-th key frequency.
[0030] (2) Data smoothing: For instantaneous noise pulses or short-term interference in the environment, smoothing techniques such as moving average filtering are used to process the extracted noise data, reduce the transient fluctuations caused by random noise, and obtain a smooth noise level estimate.
[0031] Specifically, for each key frequency, the following steps are performed: the average value of the raw noise amplitude is added to a queue, and whenever a new average value of the raw noise amplitude is added to the queue, the oldest value is automatically removed; the average value of all values in the queue is calculated as the smoothing result.
[0032] The default value for the data in the queue is 5, which means that the average value of the raw noise amplitude at 5 different times is saved.
[0033] Step 204, Real-time Quality Monitoring: When the detected noise level is too high and exceeds the preset threshold, a warning or test will be given, prompting the operator to improve the environment; at the same time, the system will monitor whether the operator plays the test signal as required and whether the subject responds in a timely manner; once an abnormal situation is detected (such as operational error), the system will prompt for correction or retesting.
[0034] Specifically, the mean of the smoothing results corresponding to all key frequencies is calculated to obtain the average noise; if the average noise is lower than the set value of 0.005, the environment is considered suitable for testing, and the process proceeds to step 3.
[0035] Step 3: Collect subject information.
[0036] The participant information includes name, age, gender, hearing history (such as whether they have hearing problems), contact information, and home address.
[0037] Step 4: Conduct a guided hearing test.
[0038] According to the predetermined hearing screening protocol (e.g., frequency-division pure tone audiometry), the operator and the subject are guided step by step to complete the test; during the test, the quality control module continuously monitors and dynamically compensates for the audiometry process based on the real-time noise parameters (from the STFT analysis results of a single microphone).
[0039] Step 401: For each key frequency, play a pure tone, and the subject wears headphones to respond to the pure tone at the specific frequency. Record the minimum volume that the subject can hear as the initial baseline threshold.
[0040] Step 402: For each key frequency, perform noise correction on the initial baseline threshold to obtain the noise-compensated baseline threshold.
[0041] As one implementation method, for each key frequency, noise correction is performed on the initial baseline threshold based on the smoothing result to obtain the noise-compensated baseline threshold. Specifically, the method for noise correction of the initial baseline threshold is as follows: first, the difference between the smoothing result and the initial baseline threshold is calculated; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, no compensation is performed.
[0042] As another implementation, a noise correction model is used to perform noise correction on the initial baseline threshold.
[0043] To reduce the impact of environmental noise on the audiometry results, a noise correction model is introduced into the smart terminal application. The noise correction model uses historical big data and noise information monitored in real time through a built-in single microphone and STFT algorithms to dynamically adjust the audiometry signal and result judgment during the test.
[0044] The noise correction model compensates for the subject's hearing threshold based on the real-time acquired ambient noise spectrum characteristics and intensity levels (derived from STFT analysis of a single microphone). When background noise is too strong in certain frequency bands, the noise correction model will raise the threshold judgment standard for the test tone in the corresponding frequency band, or guide the application to adjust the playback volume (within a safe range) to avoid noise drowning out the test signal and causing misjudgment.
[0045] Data Training: The noise correction model is trained using machine learning algorithms (such as deep neural networks) based on a large amount of real-world environmental data. Training data includes single-microphone ambient noise recordings (and their STFT spectral analysis results) in different scenarios, as well as professional audiometry results under corresponding conditions. By comparing the differences in audiometry thresholds between quiet and noisy environments, the noise correction model learns how to correct noise in various typical noise environments. The cloud platform continuously collects new anonymized data to update and optimize the noise correction model parameters, ensuring its correction capabilities continuously improve with increased usage.
[0046] Real-time compensation: During the actual screening process, the quality control and environmental noise monitoring module transmits real-time noise parameters (such as noise intensity in each frequency band) obtained through single-microphone and STFT analysis to the noise correction model; the noise correction model instantly calculates the required compensation amount and applies it to the ongoing test. Dynamically adjust the intensity of the playback signal: while ensuring that the output volume does not exceed the safe upper limit, appropriately increase the playback intensity of the test tone according to the noise level of the corresponding frequency band; Adjust the threshold judgment algorithm: fine-tune the judgment criteria for whether the subject can hear the sound based on the noise level; Transient noise handling: When a sudden change in ambient noise is detected (such as a car honking by, which can be identified by analyzing its spectrum and intensity changes through STFT), the test can be temporarily paused, or the user interface can prompt the operator to wait until the noise decreases before continuing; or the signal playback time can be extended and multiple response judgments can be combined to minimize transient noise interference.
[0047] This application dynamically adjusts the test threshold based on the noise level obtained from the environmental assessment to counteract the interference of environmental noise on the test results and ensure test accuracy.
[0048] Step 5: The smart terminal interprets the test results.
[0049] For each key frequency, if the noise-compensated baseline threshold exceeds the clinical cutoff value of 25 dB HL, potential hearing loss is considered detected, and referral recommendations are automatically generated for those with abnormal screening results.
[0050] Each test's subject information, hearing threshold results, and test environment parameters (such as noise levels at various frequencies) are recorded in the application and can be encrypted and uploaded to the cloud. It can also automatically generate standardized reports based on the screening results, including hearing curves, result interpretations, and preliminary suggestions.
[0051] Step 6: A cloud-based management platform that communicates with smart terminal applications to centrally manage and deeply analyze screening data, providing remote support and monitoring functions.
[0052] (1) Data storage and management: Screening data from various community terminals is stored in the cloud to establish a secure database; (2) Quality indicator tracking: Continuously monitor the quality of screening in each community, such as the training and assessment of operators, the compliance of screening operations, and the average level of environmental noise; (3) Statistical analysis report: Analyze and process the collected large-scale screening data to generate a statistical report on hearing health status; (4) Remote technical support: When community operators encounter problems during use, they can obtain remote support from experts through the cloud platform; (5) Noise correction model training and update support: Provide training data support and model update services for noise correction models in smart terminal applications.
[0053] This embodiment provides a community hearing screening method based on adaptive correction of environmental noise, which lowers the professional technical threshold: through interactive training and intelligent guidance built into the application, non-professional community personnel can independently complete the screening.
[0054] This embodiment provides a community hearing screening method based on adaptive correction of environmental noise, which improves screening coverage: by using the widespread use of smartphones as terminals, hearing screening can be carried out anytime and anywhere, thereby increasing the coverage at the grassroots level.
[0055] This embodiment provides a community hearing screening method based on adaptive correction for environmental noise, which ensures screening quality: through standardized procedures, embedded quality control, and especially a real-time noise monitoring and adaptive correction model based on single microphone optimization, human error and environmental interference are significantly reduced, and the reliability of the hearing test results can be guaranteed even in non-ideal community environments.
[0056] This embodiment provides a community hearing screening method based on adaptive correction of environmental noise, which supports data management and decision-making: the cloud platform facilitates data collection and statistical analysis, provides a basis for public health decision-making, and provides remote support.
[0057] This embodiment provides a community hearing screening method based on adaptive correction of environmental noise, which is inexpensive and easy to deploy: it only relies on the hardware of the smartphone itself (especially the built-in single microphone), without the need for additional expensive equipment, and is easy to promote on a large scale in the community.
[0058] This embodiment provides a community hearing screening method based on adaptive correction of environmental noise, which effectively solves the pain points of existing community hearing screening in terms of manpower, equipment, process and environmental noise control. It provides a low-cost, high-efficiency and reliable initial hearing screening method with broad application prospects and social value.
[0059] Example 2 This embodiment provides a community hearing screening system based on adaptive correction for environmental noise, comprising: The signal transformation module is configured to acquire sound signals in the test environment and perform short-time Fourier transform to obtain a frequency domain spectrum. The environmental assessment module is configured to: set multiple key frequencies; for each key frequency, find the index closest to the key frequency on the frequency axis in the frequency domain spectrum, take the intensity value of the index in all time frames, calculate the average value, obtain the average value of the original noise amplitude corresponding to the key frequency, and perform smoothing to obtain the smoothing result; calculate the average value of the smoothing results corresponding to all key frequencies to obtain the average noise; if the average noise is lower than the set value, the test environment is considered suitable for testing. The hearing screening module is configured to: play a pure tone for each key frequency, record the minimum volume that the subject can hear as the initial baseline threshold, perform noise correction on the initial baseline threshold to obtain the noise-compensated baseline threshold, and if the noise-compensated baseline threshold exceeds the clinical threshold, then potential hearing loss is considered to have been detected.
[0060] Furthermore, the noise correction includes: for each key frequency, calculating the difference between the smoothing result and the initial baseline threshold; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, then no compensation is performed.
[0061] Furthermore, the noise correction includes: for each key frequency, based on the frequency domain spectrum and the initial baseline threshold, obtaining the noise-compensated baseline threshold through a noise correction model.
[0062] It should be noted that each module in this embodiment corresponds one-to-one with each step in Embodiment 1, and their specific implementation processes are the same, so they will not be repeated here.
[0063] Example 3 This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a community hearing screening method based on adaptive correction of environmental noise as described in Embodiment 1 above.
[0064] Example 4 This embodiment provides a computer device, such as... Figure 2 As shown, the system includes a computer-readable storage medium 1003, a processor 1001, a communication interface 1002, and a computer program stored on the computer-readable storage medium 1003 and executable on the processor 1001. The processor 1001, communication interface 1002, and computer-readable storage medium 1003 can be connected via a bus or other means. The communication interface 1002 is used to receive and transmit data. When the processor 1001 executes the program, it implements the steps in the community hearing screening method based on adaptive environmental noise correction as described in Embodiment 1 above.
[0065] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A community hearing screening method based on adaptive environmental noise correction, characterized in that, include: Acquire the sound signal in the test environment and perform a short-time Fourier transform to obtain the frequency domain spectrum; Set multiple key frequencies; for each key frequency, find the index closest to the key frequency on the frequency axis in the frequency domain spectrum, take the intensity value of the index in all time frames, and calculate the average value to obtain the average value of the original noise amplitude corresponding to the key frequency, and perform smoothing to obtain the smoothing result; calculate the average value of the smoothing results corresponding to all key frequencies to obtain the average noise. If the average noise is lower than the set value, the test environment is considered suitable for testing. For each key frequency, a pure tone is played, and the minimum volume that the subject can hear is recorded as the initial baseline threshold. The initial baseline threshold is then noise-corrected to obtain the noise-compensated baseline threshold. If the noise-compensated baseline threshold exceeds the clinical cutoff value, potential hearing loss is considered to have been detected.
2. The community hearing screening method based on adaptive environmental noise correction as described in claim 1, characterized in that, The original noise amplitude average value is expressed by the formula: noise_levelx=Mean(magnitude[idx,:]); where idx represents the index on the frequency axis that is closest to the x-th key frequency in the time-frequency graph, magnitude[idx,:] represents the intensity value of index idx in all time frames, Mean represents the average value, and noise_levelx represents the original noise amplitude average value corresponding to the x-th key frequency.
3. The community hearing screening method based on adaptive environmental noise correction as described in claim 1, characterized in that, The smoothing process includes: for each key frequency, adding the average value of the original noise amplitude to a queue; whenever a new average value of the original noise amplitude is added to the queue, automatically removing the oldest value; and calculating the average value of all values in the queue as the smoothing result.
4. The community hearing screening method based on adaptive environmental noise correction as described in claim 1, characterized in that, The noise correction includes: for each key frequency, calculating the difference between the smoothing result and the initial baseline threshold; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, then no compensation is performed.
5. The community hearing screening method based on adaptive environmental noise correction as described in claim 1, characterized in that, The noise correction includes: for each key frequency, based on the frequency domain spectrum and the initial baseline threshold, obtaining the noise-compensated baseline threshold through a noise correction model.
6. A community hearing screening system based on adaptive correction for environmental noise, characterized in that, include: The signal transformation module is configured to acquire sound signals in the test environment and perform short-time Fourier transform to obtain a frequency domain spectrum. The environmental assessment module is configured to: set multiple key frequencies; for each key frequency, find the index closest to the key frequency on the frequency axis in the frequency domain spectrum, take the intensity value of the index in all time frames, calculate the average value, obtain the average value of the original noise amplitude corresponding to the key frequency, and perform smoothing to obtain the smoothing result; calculate the average value of the smoothing results corresponding to all key frequencies to obtain the average noise; if the average noise is lower than the set value, the test environment is considered suitable for testing. The hearing screening module is configured to: play a pure tone for each key frequency, record the minimum volume that the subject can hear as the initial baseline threshold, perform noise correction on the initial baseline threshold to obtain the noise-compensated baseline threshold, and if the noise-compensated baseline threshold exceeds the clinical threshold, then potential hearing loss is considered to have been detected.
7. A community hearing screening system based on adaptive environmental noise correction as described in claim 6, characterized in that, The noise correction includes: for each key frequency, calculating the difference between the smoothing result and the initial baseline threshold; if the smoothing result exceeds the initial baseline threshold, then the noise-compensated baseline threshold = initial baseline threshold + (difference × compensation coefficient); if the smoothing result does not exceed the initial baseline threshold, then no compensation is performed.
8. A community hearing screening system based on adaptive environmental noise correction as described in claim 6, characterized in that, The noise correction includes: for each key frequency, based on the frequency domain spectrum and the initial baseline threshold, obtaining the noise-compensated baseline threshold through a noise correction model.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in a community hearing screening method based on adaptive correction of environmental noise as described in any one of claims 1-5.
10. A computer device comprising a computer-readable storage medium, a processor, and a computer program stored on the computer-readable storage medium and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the community hearing screening method based on adaptive correction of environmental noise as described in any one of claims 1-5.