31 results about "Pure tone" patented technology

The invention relates to the technical field of health data processing, in particular to an intelligent health data processing method and device and a storage medium, and the method comprises the steps: collecting the pure tone hearing threshold of a user under a standard frequency table, constructing a pure tone audiometry map of the user, extracting the hearing threshold features of the user, constructing the hearing sensitive state index of the user, and obtaining the hearing sensitive state index of the user; then determining a basic hearing state of the user; collecting health data of the user in real time; calibrating an otoacoustic emission amplitude and an ABR wave V amplitude of the user; constructing a peripheral-central function coupling index of the user; and constructing an occult hearing loss model based on the peripheral-central function coupling index and the hearing processing disorder index of the user so as to output the occult hearing loss state of the user, and performing hearing health early warning on the user by integrating the occult hearing loss state of the user and the basic hearing state. According to the invention, the efficiency of health data processing is effectively improved.

The invention relates to the technical field of Bluetooth, and discloses a dynamic bass enhancement method and system for Bluetooth equipment, and the method comprises the steps: separating a complex tone signal component and a pure tone signal component from an audio signal, so as to calculate a harmonic proportion attenuation factor of the audio signal; determining an auditory transmission distance between the Bluetooth device and the audience, and calculating a low-frequency attenuation amount of the audio signal in a transmission process; calculating the bass perception loudness of the audience, and obtaining the target bass enhancement intensity of the audience; determining a harmonic balance equivalent of an output sound field of the Bluetooth device, and calculating an effective bass enhancement amount of the Bluetooth device; and performing bass enhancement processing on the audio signal based on the effective bass enhancement quantity and the target bass enhancement intensity to obtain an enhanced audio signal. According to the invention, the dynamic bass enhancement effect of the Bluetooth device can be improved.

The invention discloses a noise online monitoring microphone sensitivity comparison calibration device and method. The device comprises an open cavity, a microphone to be calibrated, a monitoring microphone, a pure tone generator, a sound guide tube and a control unit, wherein the open type cavity is provided with a first connecting end and a second connecting end which are oppositely arranged, the first connecting end is used for being communicated with the sound inlet side of the microphone to be calibrated, the second connecting end is used for being communicated with the sound inlet side of the monitoring microphone, and the side wall of the open type cavity is provided with a plurality of through holes communicated with the external environment. External noise can enter the open type cavity; the sound guide tube is used for communicating the pure tone generator with the sound guide interface of the open cavity so as to guide the pure tone output by the pure tone generator into the open cavity; and the control unit is in signal connection with the pure tone generator, the monitoring microphone and the microphone to be calibrated, and is used for adjusting the output of the pure tone generator based on a feedback signal of the monitoring microphone, so that after a pure tone sound field in the open cavity reaches a preset reference condition, the microphone to be calibrated is calibrated. And reading a return signal of the microphone to be calibrated to obtain the sensitivity or the sensitivity characterization value of the microphone to be calibrated.

The invention provides an automatic debugging method and system, electronic equipment and a storage medium. The method is used for a sound sensing device and comprises the steps that a test audio is played to a user, and the test audio is any one of words, syllables, music, voice, vocal music and pure tone; receiving response information of the user; determining whether the response information is matched with the test audio; when the response information is not matched with the test audio, storing the test audio as a reference optimized audio; determining a target distinctive speech feature corresponding to the reference optimized audio; determining a target operation parameter corresponding to the target distinctive speech feature according to a corresponding relationship between the distinctive speech feature and the operation parameter of the sound sensing device; and adjusting the target operation parameters to optimize the sound sensing equipment. The method is favorable for reducing the debugging cost and simplifying the debugging process.

The invention discloses an intelligent self-service pure tone threshold test method and device and a medium, and relates to the technical field of threshold test, and the method comprises the steps: executing a pure tone threshold test process based on an information gain selection mechanism according to the recognition difficulty level in noise, the matching degree score and a pure tone threshold test starting strategy, the key pressing behavior of the testee is judged in real time in combination with the personal operation rhythm template, the hearing threshold estimation result of each frequency band and the corresponding uncertainty index and behavior event mark are output, and fixed-point deviation correction complementary measurement and weight correction are carried out based on the hearing threshold estimation result of each frequency band, the uncertainty index and the behavior event mark; obtaining a final hearing threshold result and an overall credibility grade; by establishing the candidate test set and introducing the pure tone threshold measurement process based on the information gain selection mechanism, the dynamic adjustment of the test path according to the hearing threshold estimation result and the uncertainty index of each frequency band is realized, and the test efficiency and the result stability are improved.

This patent application discloses a method for constructing a risk prediction system for age-related hearing loss based on metabolomics, belonging to the interdisciplinary field of biomedicine and artificial intelligence. The method first acquires peripheral blood metabolomics data, pure-tone audiometry results, and age information of subjects, and then screens out age-related hearing loss patients with symmetrical hearing loss and healthy controls. Next, a hierarchical screening strategy is used to identify multiple core metabolites related to the age-related hearing loss state itself from massive amounts of data. Subsequently, based on these core metabolites, a predictive model is constructed using machine learning algorithms, and rigorously validated through independent internal and external clinical cohorts. This invention achieves early, accurate, and interpretable risk warning for age-related hearing loss, exhibiting excellent predictive performance.

The invention discloses an otoacoustic emission instrument probe which is characterized by comprising a probe body, a first shell and a second shell, the first shell is a cylinder, the middle of the first shell is of a hollow structure provided with at least one through hole, one end of the hollow structure and the outer wall of the first shell form a first cavity, the first cavity is connected with the probe body, the other end of the hollow structure and the outer wall of the first shell form a second cavity, and the second cavity is connected with the second shell. An annular groove is formed in the inner wall of the upper end of the second shell. According to the otoacoustic emission instrument probe, a through hole of a first shell provides a fixed installation position for a loudspeaker and a microphone, an annular groove of a second shell provides a fixed installation position for a circuit board, the circuit board and the loudspeaker are connected with the circuit board through a fixed-length wire, internal crosstalk is effectively restrained, a physical isolation barrier is formed by the hole wall of the first shell, and the sound emission effect is improved. And the accuracy of acoustic immittance measurement and pure tone threshold judgment is further ensured.

The invention relates to the technical field of psychoacoustic and electroacoustic measurement, and provides an equal-loudness-level curve calculation method suitable for a plug-in headphone, and the method comprises the steps: firstly, calculating a free field equal-loudness-level curve based on a standard, and deducing an increment function representing a human ear loudness perception growth rate; then, acquiring a pure tone reference equivalent threshold sound pressure level of the plug-in earphone in a blocked ear environment, and realizing full-frequency-point reference data fitting by using an interpolation algorithm; and finally, superposing the loudness increment function on the reference equivalent threshold sound pressure level reference anchor point, thereby constructing an equal loudness level curve suitable for the plug-in earphone. The technical blank that the plug-in earphone lacks an equal-loudness evaluation standard in a blocked ear scene is solved, and an important support and an application basis are provided for application expansion of an equal-loudness-level curve relation.

The application discloses a noise environment test method and system applied to a pure tone audiometer, and the method comprises the following steps: obtaining an anti-interference noise signal stream through a feedforward microphone embedded in a specific curvature area outside an earmuff; inputting the anti-interference noise signal stream into a noise reduction processing module, combining an original pure tone signal input by the audiometer, and outputting a pure tone reservation type reverse signal; superimposing and synthesizing the pure tone reservation type reverse signal and the original pure tone signal to obtain a high-fidelity synthesized audio signal; performing real-time frequency domain analysis on the high-fidelity synthesized audio signal to generate multi-dimensional quality verification data containing distortion characteristics, response speed and fidelity level; and outputting an environment noise adaptive final hearing threshold result based on the comparison result of the multi-dimensional quality verification data and a preset standard threshold. According to the embodiment of the application, efficient suppression of environmental noise and accurate reservation of pure tone signals can be realized, and the reliability and environmental adaptability of hearing threshold test are improved.

The invention provides a noise deafness early-stage self-test system, and relates to the medical field, the noise deafness early-stage self-test system comprises a housing, the front surface of the housing is provided with a display screen used for displaying system content and an operation key group used for operating an system, and the side edge of the housing is provided with an earphone interface. According to the invention, the portable self-test at the early stage of noise deafness is realized, the problem of no targeted portable equipment is solved, a self-testee is helped to find the problem in time at the damage stage (reversible stage) at the frequency band of 3000Hz-6000Hz, the development of permanent noise deafness is avoided, the self-testee does not need to go back and forth to professional organizations (the traffic and time cost is saved), the single-time self-test cost is low, and based on the pure tone audiometry principle, the self-test efficiency is greatly improved. The error between a high-frequency test of a key frequency band and a detection result of a professional institution is less than or equal to 3dB, the precision requirement of early damage identification is met, the pure tone signal strength is limited to be 30dB-85dB, the battery has multiple protections, and the full-sound-insulation earmuff is made of a medical-grade material, so that potential safety hazards are avoided.

The invention relates to an audio-based interaction method and device, equipment and a storage medium, and relates to the technical field of multimedia. According to the method, the recognition result is upgraded from pure tone source judgment to deep understanding of complete information and intention of the audio, and the degree parameter is output to indicate the expression degree of each audio feature in the audio, so that the fine degree of the recognition result is improved; moreover, multiple audio feature templates corresponding to the multiple audio features and the degree parameter of each audio feature template are provided, and on the basis, a user can adjust the degree parameter of any audio feature of the audio and can select any audio feature template to be mixed with the multiple audio features of the audio to generate a new audio. Therefore, the user can finely adjust the audio features of the audio and can integrate other audio features, so that the audio meeting the personalized requirements of the user is generated, the user does not need to perform excessive operations, and the quality of the generated audio is improved on the basis of ensuring the generation efficiency.

The application relates to a noise adjustment method of an audiometer and a noise generator thereof, comprising the following steps: constructing a noise database, the types of the noise including simulated noise, random noise and mixed noise; acquiring frequency range and amplitude data when pure tone is output, and generating a preselected scheme of masking noise adapted to the pure tone from the corresponding type according to an input instruction, the preselected scheme including the duration, the expected frequency range and the expected amplitude of the selected masking noise; superimposing and outputting the selected masking noise and the pure tone, and acquiring the mixed tone segment signal again at the eardrum, and generating a waveform spectrum through time-frequency conversion; based on the waveform spectrum, removing the waveform spectrum calculated according to the frequency range and the amplitude data of the pure tone, and recalculating the actual frequency range and the actual amplitude of the masking noise, and adjusting the frequency range and the amplitude of the masking noise output according to the actual frequency range and the actual amplitude, so that the actual frequency range and the actual amplitude are infinitely close to the expected frequency range and the expected amplitude respectively.

The invention discloses a subjective and objective evaluation method for order noise of a new energy vehicle. The method is realized through the following steps: building a test environment and arranging acoustic sensors, setting transient and steady working conditions, and collecting noise data of four key positions in the vehicle; parameters such as linearity and pure tone highlight ratio are calculated, and scoring indexes are extracted; and finally, establishing a 10-person review group to carry out 7-level subjective scoring, and carrying out weighted fusion on subjective and objective scores according to working condition characteristics to obtain a comprehensive evaluation result. The method breaks through subjective and objective evaluation split states, covers all working conditions, improves the comprehensiveness and accuracy of order noise evaluation, can accurately recognize noise risk points, reduces the after-sales cost, and is suitable for systematic evaluation of new energy vehicle order noise.

The invention relates to a tinnitus intervention method, device and equipment based on a brain-computer interface, and relates to the technical field of tinnitus digital intervention, and the method comprises the steps: processing a pure tone audiometry result of a target user through a matching method, and obtaining input parameters such as tinnitus frequency / loudness; and performing real-time dynamic processing on the original audio in the buffer area to generate an audio block, performing band-pass filtering in combination with the tinnitus input parameters, and constructing a band-pass / band-stop filter. And introducing key noise by adopting random noise, performing optimal superposition on the noise and an audio block, analyzing signal gain, performing incisura enhancement according to a band elimination filter and the gain based on an incisura / sound channel mode, and generating incisura music. And finally, on the basis of a brain-computer interface, combining the incisura music with the neural feedback information, and carrying out comprehensive tinnitus intervention, so that the incisura music is adjusted, and a tinnitus intervention result is determined. Therefore, the brain-computer interface and the incisura music therapy are combined to realize advantage complementation, so that the tinnitus digital intervention effect is improved.

The application relates to the technical field of tinnitus diagnosis and assistance, and discloses a tinnitus and deafness intelligent diagnosis and treatment system which comprises a patient data acquisition module, a tinnitus test module, an auxiliary diagnosis and prescription module and a treatment module, the patient data acquisition module is used for acquiring medical record data of a patient, and whether the patient is treated by a diagnosis and treatment mode prescribed by the patient is judged, the tinnitus test module comprises a pure tone audiometry test unit and a tinnitus masking test unit. The system screens out n patients with the highest similarity degrees from a medical record database according to the medical record data of the patient, reads the pure tone audiometry thresholds of the n patients, calculates the initial pure tone audiometry threshold of the current patient, and gradually tests to obtain the final pure tone audiometry threshold of the patient, so that the pure tone audiometry threshold of the patient can be quickly obtained, the process of testing the pure tone audiometry threshold from the initial value is shortened, the examination time is reduced, and the speed of the doctor's diagnosis process is accelerated.

The invention relates to the technical field of community medical treatment, and provides a community hearing screening method and system based on adaptive correction of environmental noise, and the method comprises the steps: obtaining a sound signal in a test environment, and carrying out the short-time Fourier transform, and obtaining a frequency domain spectrogram; for each key frequency, finding an index closest to the key frequency on a frequency axis in the frequency domain spectrogram, taking intensity values of the index in all time frames, calculating an average value, obtaining an original noise amplitude average value corresponding to the key frequency, carrying out smooth processing, calculating the average value, obtaining average noise, and if the intensity values are lower than a set value, outputting the average noise; if yes, determining that the testing environment is suitable for testing; and for each key frequency, playing pure tone, recording the minimum volume which can be heard by the subject as an initial baseline threshold value, performing noise correction to obtain a baseline threshold value after noise compensation, and if the baseline threshold value exceeds a clinical boundary value, determining that potential hearing loss is detected. And personal errors and environmental interference are obviously reduced.

A technique is presented in which signals are constructed from multiple tone frequencies, combined in such a way as to minimise fluctuations in the combined signal amplitude. Fluctuations in acoustic pressure, and stimulation effects, are reduced. This is achieved by configuring combinations of tones such that there is a characteristically flat signal envelope in the time domain. Presented is an apparatus for estimating motion of a target from reflections of such a combined signal.

The present application relates to a kind of sound frequency equalization energy compensation methods and systems for the treatment of tinnitus and deafness coexistence, wherein, method includes: obtaining the tinnitus parameter and tinnitus threshold of tinnitus and deafness coexistence patient, and determine the tinnitus relative sound pressure level of tinnitus and deafness coexistence patient at tinnitus frequency;Measure the pure tone sound pressure level required to keep the tinnitus sound equalization of tinnitus and deafness coexistence patient, and generate tinnitus sound equalization curve;Determine the normal hearing threshold of normal hearing person at the tinnitus frequency of tinnitus and deafness coexistence patient;According to tinnitus relative sound pressure level and normal hearing threshold, determine normal hearing person pure tone equalization curve;According to tinnitus sound equalization curve, normal hearing person pure tone equalization curve, tinnitus threshold and normal hearing threshold, calculate the sound pressure difference to be compensated;For tinnitus treatment sound signal, according to the sound pressure difference to be compensated of each frequency band, carry out audio equalization energy compensation processing, the present application can be widely applied in audio equalization compensation processing technical field.

This invention relates to the field of novel pharmaceutical uses, disclosing the application of methyl jasmonate in the preparation of drugs for delaying age-related hearing loss. This invention is the first to clearly discover that methyl jasmonate can significantly improve the auditory function of aged mice, significantly enhance the pure tone hearing threshold and speech recognition ability of aged mice, effectively protect the structural integrity of the cochlea, reduce apoptosis of cochlear hair cells and spiral ganglion cells, inhibit the inflammatory response and oxidative stress damage of the auditory system, and delay the degenerative process of the auditory system from a pathological perspective, which has important clinical translational potential and market value.

The embodiment of the invention provides a training method of a postoperative hearing recovery multi-modal fusion prediction model and related equipment, which can realize accurate prediction of a postoperative hearing recovery level. The method comprises the following steps: acquiring training data of each training user in a training user set, wherein the training data comprises a preoperative ear endoscope image, a pure tone audiometry result and a real recovery level; preprocessing the preoperative ear endoscope image to obtain an input sequence feature; capturing a spatial context in the input sequence features to obtain hierarchical visual features; a pure tone audiometry result is converted into a structured feature embedding vector; determining a multi-modal fusion feature vector of each training user according to the hierarchical visual features and the structured feature embedding vectors; and training the initial model based on the multi-modal fusion feature vector and the real recovery level corresponding to each training user to obtain a postoperative hearing recovery multi-modal fusion prediction model.

The invention provides a voice environment detection method and device, a vehicle, electronic equipment and a storage medium, and the method comprises the steps: carrying out the collection of an audio signal through equipment, such as a microphone, while playing a test audio comprising pure tones of different frequencies, generating recorded audio data based on the collected audio signal, and storing the recorded audio data. According to the method, the recording state data in the audio data recording process is acquired, the abnormal detection sub-result is determined according to at least one of the recording state data and the recording audio data, and the detection result of the voice environment is determined based on the abnormal detection sub-result, so that the detection result is determined from an objective angle instead of being judged manually and subjectively in the process; manual interference is reduced, operation is simple, accuracy is improved, and when the step of determining the detection result of the voice environment is executed while recording is carried out, detection efficiency can be remarkably improved, and the problem positioning period can be shortened.

The application discloses a hearing aid self-fitting method based on neural network deep learning, adopts pure tone and combines audiometry audio with user daily life background noise information to perform audiometry, distributes weights to obtain preset WDRC parameters, adopts KNN algorithm based on the preset WDRC parameters to perform classification to obtain characteristic labels, simultaneously performs evaluation and scoring through audition of specific speech groups, combines the characteristic labels and the evaluation and scoring to adopt a neural network deep learning model to obtain a gain and compression ratio correction vector, and finally obtains the final WDRC parameters. The application can fuse the audiometry link to obtain relatively accurate initial setting parameters containing user characteristic information, a deep learning neural network input vector containing characteristic labels, so that the model has higher accuracy.

The present disclosure provides a hearing testing system and method, the hearing testing system includes a playback module and a detection module. The playback module includes an intensity-level adjustment module connecting to a player for setting the intensity level of a test sound, and the player plays the test sound to a test ear of a user. The test sound includes a plurality of pure tones having different decibels or frequencies. The detection module is in communication with the playback module, and the user generates a single test response corresponding to the plurality of pure tones having different decibels or frequencies. The test response is that the user inputs the number of pure tones heard into the detection module.

1. The name of the design product: pure tone audiometer. 2. The use of the design product: the product is suitable for the test of human ear threshold in clinical units, which can assist doctors in diagnosing patient symptoms. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view 1.

The application provides a sound signal processing method based on an acoustic model, which is used for an air conduction hearing aid. The method comprises the following steps: simulating and copying available sound signals in an environment sound signal of the hearing aid, and the number of the available sound signals is at least two; performing differential filtering processing on the available sound signals based on an existing acoustic model to form different pure tone signals; and performing differential processing on the pure tone signals according to categories, and integrating and outputting the processed pure tone signals. Through analysis on the available sound signals in the environment, a related acoustic model combination can be matched, the remaining signals in the available sound signals are processed by masking through the acoustic model, different pure tone signals of different sound types can be obtained, the differential amplification of each pure tone signal is performed according to the degree of hearing impairment of a hearing-impaired patient and then the pure tone signal is output, the ratio of a specific sound to the remaining sounds can be increased, and the resolution of the specific sound is effectively improved.

The application provides a small rail transit train noise prediction method and system, and relates to the technical field of rail transit, comprising the following steps: constructing a speed correction model according to the positional relationship among a prediction point, a measurement point and a track surface; constructing a geometric divergence correction model according to train speed; constructing an air absorption attenuation model according to a pure tone attenuation coefficient and the position of the measurement point; constructing a ground effect attenuation model according to the average ground clearance of the propagation path and the position of the measurement point; constructing a line type correction model according to track information; calculating the single-event sound level of a single train passing through the prediction point according to the maximum noise source intensity, the speed correction model, the geometric divergence correction model, the air absorption attenuation model, the ground effect attenuation model and the line type correction model; and calculating the equivalent continuous sound level according to the time of the single train passing, the single-event sound level and the train logarithm. The application decomposes the noise propagation process into quantifiable physical links for correction, and outputs the equivalent sound level index meeting the engineering application requirements.

An audio signal processing device generates an output signal by alleviating a noise component in an input signal including both a sound component to be heard and the noise component. The audio signal processing device includes: a composite sound output part to output a composite sound signal; an adaptive filter to receive as an input the composite sound signal output from the composite sound output part; and a subtraction part to output an output sound signal by subtracting an output signal of the adaptive filter from an input sound signal. The adaptive filter performs adaptation operation assuming that the output sound signal from the subtraction part is an error. The composite sound signal from the composite sound output part is formed with pure tones of multiple frequencies extracted from a frequency band that is to be cancelled and that includes a frequency band of the alleviated noise component.

The application discloses a false negative reaction determination method in automatic pure tone hearing threshold test, and the method comprises the following steps: obtaining initial hearing threshold test values of a target tester at multiple frequencies in a normal test process, wherein the initial hearing threshold test values comprise frequencies and sound intensities; selecting a set frequency and adjusting the sound intensity based on the initial hearing threshold test value at the set frequency; performing secondary test on the target tester according to the adjusted sound intensity to obtain second hearing threshold test values; comparing the initial hearing threshold test values with the second hearing threshold test values to obtain test difference values of the sound intensities between the initial hearing threshold test values and the second hearing threshold test values; and adjusting the test process according to the test difference values until the test result of the target tester is determined as a false negative reaction or the test is ended. The application can identify whether the target tester has a false negative reaction through the automatic test process, and the test process is adjusted according to the reaction of the target tester, so that the accuracy and reliability of the test are improved.

This invention provides an automated pure-tone audiometry method based on Bayesian active learning and Gaussian process regression, comprising: performing a pre-test and establishing a regression model using a Gaussian process, and constructing an audiogram using the regression data; using the principle of Bayesian active learning to screen the iteration point with the greatest uncertainty, and obtaining the audiometric signal frequency and hearing level; performing audiometry on the subject to obtain data and adding it to the dataset; performing Gaussian process regression and active learning iterations until the target audiogram is obtained. This method replaces the fixed steps of traditional audiometry methods with the predictive power of machine learning, which can shorten the test time, reduce the test inaccuracy that may be caused by long test times, and provide a smooth and accurate audiogram with a much higher accuracy than traditional audiometry methods.