CN115040117B - Portable hearing test evaluation method and system - Google Patents
Portable hearing test evaluation method and system Download PDFInfo
- Publication number
- CN115040117B CN115040117B CN202210823217.7A CN202210823217A CN115040117B CN 115040117 B CN115040117 B CN 115040117B CN 202210823217 A CN202210823217 A CN 202210823217A CN 115040117 B CN115040117 B CN 115040117B
- Authority
- CN
- China
- Prior art keywords
- signal
- test
- hearing
- noise
- feedback
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012074 hearing test Methods 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 316
- 230000005236 sound signal Effects 0.000 claims abstract description 137
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 63
- 210000000613 ear canal Anatomy 0.000 claims description 52
- 206010011878 Deafness Diseases 0.000 claims description 38
- 230000010370 hearing loss Effects 0.000 claims description 38
- 231100000888 hearing loss Toxicity 0.000 claims description 38
- 208000016354 hearing loss disease Diseases 0.000 claims description 38
- 238000001228 spectrum Methods 0.000 claims description 37
- 238000010586 diagram Methods 0.000 claims description 30
- 230000008859 change Effects 0.000 claims description 22
- 230000004044 response Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000000638 stimulation Effects 0.000 claims description 9
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 208000032041 Hearing impaired Diseases 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005251 gamma ray Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 2
- 230000003750 conditioning effect Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 description 10
- 210000005069 ears Anatomy 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/12—Audiometering
- A61B5/121—Audiometering evaluating hearing capacity
- A61B5/123—Audiometering evaluating hearing capacity subjective methods
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/04—Constructional details of apparatus
- A61B2560/0431—Portable apparatus, e.g. comprising a handle or case
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Otolaryngology (AREA)
- Biomedical Technology (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Epidemiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Human Computer Interaction (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a portable hearing test evaluation method and a system, wherein the method comprises the following steps: control portable equipment and generate the test sound signal of presetting frequency and sound intensity scope, based on test sound signal adjust with the broadcast gain of the bluetooth headset that portable equipment connects, the back that finishes is adjusted, will test sound signal passes through bluetooth headset feeds back to the tester duct, gathers tester's duct feedback signal, according to the duct signal constructs tester's hearing curve graph, according to tester's hearing threshold value is evaluateed out to the hearing curve graph, based on tester's hearing obstructed condition is judged to the hearing threshold value. The invention utilizes the portable equipment and the Bluetooth earphone to carry out the hearing test on the tester, which not only can overcome the scene limitation and the equipment limitation of the hearing test, but also can ensure that the tester can carry out the test at any place and time slot, thereby improving the test efficiency and the practicability.
Description
Technical Field
The invention relates to the technical field of hearing tests in otology, in particular to a portable hearing test evaluation method and system.
Background
In the modern society, hearing loss is a very common phenomenon, and young people are no longer few due to various reasons (such as frequent wearing of earphones, which is good in the environment of ktv, bars, and the like, or various stresses of work, home, study, and the like). For children, sustained hearing loss affects intellectual and emotional development; for the elderly, hearing loss in the elderly can affect the elderly's quality of life, functional status, and cognitive, emotional, and social communication abilities. Concern over ear or hearing health has been a very necessary issue.
For this reason, periodic hearing tests are indispensable, and in the existing hearing tests, a tester is required to go to an otology clinic of a hospital or a special hearing test mechanism to test hearing by adopting a special hearing device, which not only wastes precious time of the tester, but also greatly influences the test efficiency due to various objective reasons such as queuing, device debugging and the like, and reduces the experience of the tester.
Disclosure of Invention
In view of the above-mentioned problems, the present invention provides a portable hearing test evaluation method and system to solve the problems mentioned in the background art that when a tester goes to a hospital or a specialized hearing test institution tests hearing by using a dedicated hearing device, the precious time of the tester is wasted, and meanwhile, the test efficiency is greatly affected due to various objective reasons such as queuing, device debugging, etc., and the experience of the tester is reduced.
A portable hearing test evaluation method, suitable for portable devices, comprising the steps of:
controlling the portable equipment to generate a test sound signal with a preset frequency and sound intensity range;
adjusting a play gain of a Bluetooth headset connected with the portable device based on the test sound signal;
after the adjustment is finished, feeding the test sound signal back to the auditory canal of a tester through the Bluetooth earphone;
collecting ear canal feedback signals of a test person, and constructing a hearing curve graph of the test person according to the ear canal signals;
and evaluating the hearing threshold of the test personnel according to the hearing curve graph, and judging the hearing resistance condition of the test personnel based on the hearing threshold.
Preferably, the controlling the portable device to generate the test sound signal with the preset frequency and sound intensity range includes:
acquiring a volume decibel range acceptable by a standard human ear;
determining the human ear response index corresponding to each decibel volume value in the decibel range;
determining a target volume decibel range without hearing damage to a test person according to the human ear response index;
acquiring a frequency parameter range and a sound intensity parameter range corresponding to the target sound volume decibel range;
calling a test sound wave from a preset sound wave database, setting the wavelength of the test sound wave, and generating a plurality of sections of test signals of the test sound wave according to the frequency parameter range and the sound intensity parameter range after the setting is finished;
and integrating the plurality of sections of test signals to obtain the test sound signal.
Preferably, the adjusting the play gain of the bluetooth headset connected to the portable device based on the test sound signal includes:
acquiring the frequency response of the Bluetooth headset when the testing sound signal is played;
determining an average amplitude gain of the Bluetooth headset for each frequency variation point of the test sound signal based on the frequency response;
acquiring audio file attribute information of the test sound signal;
obtaining an initial gain value of a test sound signal according to the audio file attribute information;
calculating a quotient of the average magnitude gain and the initial gain value to determine a gain factor;
and adjusting the playing gain of the Bluetooth headset according to the gain coefficient.
Preferably, the ear canal feedback signal of the test person is collected, and a hearing profile of the test person is constructed according to the ear canal signal, including:
calculating the stimulation index of each section of test signal to the auditory canal of the test person according to the first same-section frequency of the test sound signal and the second same-section frequency of the auditory canal feedback signal;
determining the receiving frequency band of each section of test signal for the tester according to the ear canal feedback signal by using a trained network model based on the stimulation index;
generating a hearing data graph of the test personnel for the test sound signal according to the receiving frequency band of the test personnel for each segment of test signal;
determining a feedback frequency change graph of the test person for each section of test signal according to the hearing data graph and the ear canal feedback signal;
and constructing a hearing curve graph of the test person according to the feedback frequency change graph.
Preferably, the evaluating the hearing threshold of the test person according to the hearing graph and determining the hearing resistance of the test person based on the hearing threshold includes:
determining the change condition of the hearing threshold of the test person under different frequencies according to the hearing curve graph;
comprehensively evaluating the maximum hearing threshold value and the minimum hearing threshold value of the test personnel according to the hearing threshold value change conditions of the test personnel under different frequencies;
determining a degree of drop between the maximum hearing threshold and the minimum hearing threshold;
determining the hearing loss type of the test personnel according to the fall degree, and judging the hearing resistance condition of the test personnel based on the hearing loss type.
Preferably, after the adjusting, before the test sound signal is fed back to the ear canal of the test person through the bluetooth headset, the method further comprises:
detecting a noise signal within a test environment;
acquiring a signal frequency spectrum of the noise signal, and determining a noise type according to the signal frequency spectrum;
acquiring the frequency distribution of each phoneme in the test sound signal;
determining the signal distortion condition of the target phoneme seriously influenced under the influence of the noise signal according to the frequency distribution and the noise type;
establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme;
and compensating the output signal of each target phoneme in the test business signal by using the signal compensation function of each target phoneme so as to enable the output signal to be completely fed back to the auditory canal of the test person through the Bluetooth headset.
Preferably, the process of determining the signal distortion condition of the target phoneme seriously affected by the noise signal according to the first frequency distribution and the noise type and establishing the signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme includes:
calling a target noise model corresponding to the noise signal from a preset noise model library according to the noise type;
inputting the signal frequency of the noise signal and the target noise model into a preset cyclic neural network to generate a noise cyclic model corresponding to the noise signal;
inputting the test sound signal into the noise circulation model, and performing sound coincidence training to obtain a training result;
analyzing the training result to obtain an output sound signal;
acquiring a plurality of second phonemes contained in the output sound signal;
establishing a phoneme database according to a first phoneme contained in the test sound signal;
inputting each second phoneme into the phoneme database for matching, extracting the second phonemes with the matching degree lower than the preset matching degree, and recording the second phonemes as target phonemes;
acquiring a second frequency distribution corresponding to each target phoneme;
analyzing a phoneme weight corresponding to each target phoneme according to the second frequency distribution corresponding to each target phoneme;
analyzing the distortion degree corresponding to each target phoneme based on the phoneme weight;
acquiring a first sub-signal corresponding to each target phoneme acquired on the output sound signal;
acquiring a first position area of the first sub-signal on the output sound signal;
marking a second location area on the test sound signal that coincides with the first location area;
acquiring a second sub-signal corresponding to the second position area;
acquiring a signal difference between the second sub-signal and the second sub-signal, and analyzing a signal distortion type corresponding to each first position area;
analyzing a phoneme distortion type corresponding to each target phoneme according to the signal distortion type corresponding to each first position region;
searching a target function in a preset function library based on the phoneme distortion type corresponding to each target phoneme;
generating a correction function according to the distortion degree corresponding to each target phoneme;
correcting the corresponding target function by using the correction function;
and acquiring a correction result, and generating a signal compensation function corresponding to each target phoneme.
Preferably, the process of determining a feedback frequency variation graph of the test person for each segment of the test signal according to the hearing data graph and the ear canal feedback signal, and constructing a hearing profile of the test person according to the feedback frequency variation graph includes:
acquiring a test sound signal and the playing gain of the Bluetooth headset;
recording the playing gain of the test sound signal as an original gain, and analyzing the data gain of the hearing data diagram and the signal gain of the ear canal feedback signal by combining the playing gain of the Bluetooth earphone;
constructing a first reduction function based on the data gain;
restoring the hearing data graph by using the first restoring function to generate a restored hearing data graph;
constructing a second reduction function based on the signal gain;
restoring the auditory canal feedback signal by using the second restoring function to generate a restored auditory canal feedback signal;
comparing the restored hearing data graph with a standard hearing data graph, and analyzing the hearing loss degree of the testing personnel;
establishing a corresponding hearing loss ear model based on the hearing loss degree, and inputting the restored auditory canal feedback signal into the hearing loss ear model to generate an auditory canal feedback data graph;
acquiring the signal length of each section of test signal corresponding to the test sound signal, and extracting the standard specification corresponding to the section of test signal from a preset specification library based on the signal length;
adjusting the reduced data diagram and the ear canal feedback data diagram in proportion according to the standard specification, dividing the adjusted reduced data diagram and the ear canal feedback data diagram into preset sub-specifications, and generating a plurality of first sub-data diagrams and second sub-data diagrams;
comparing the first sub data graph and the second sub data graph at the same position to obtain a comparison result;
generating a feedback frequency variation graph corresponding to each section of test signal by a tester based on the comparison result;
respectively acquiring a frequency threshold corresponding to a feedback frequency variation graph corresponding to each section of test signal of a tester, and determining the hearing threshold of the tester for the section of test signal according to the frequency threshold;
establishing a hearing range corresponding to each section of test signal based on the hearing threshold;
and analyzing each feedback frequency change graph, inputting the analysis result into a corresponding hearing range, and generating a hearing curve graph.
Preferably, the signal distortion condition of the target phoneme seriously influenced under the influence of the noise signal is determined according to the frequency distribution and the noise type; establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme, wherein the signal compensation function comprises the following steps:
when a noise signal is detected, updating a signal spectrum of the noise signal in real time to obtain any frame of noise signal as a target frame, and obtaining a second frequency distribution of the target frame according to a first frequency distribution of each phoneme in a matched frame test sound signal corresponding to the target frame;
determining a noise score of a noise signal according to the noise type, and determining a target phoneme seriously influenced under the influence of the noise signal according to the noise score, the second frequency distribution and a signal frequency interval of each phoneme in the test sound signal;
confirming the corresponding relation between a target phoneme and the target frame, and dividing the target frame into a plurality of noise subframes according to the corresponding relation;
wherein, the corresponding relation means that each frame of the noise signal corresponds to a plurality of target phonemes, and each noise subframe corresponds to a target phoneme;
meanwhile, a signal frame of a target phoneme is divided into N signal subframes, each signal subframe is provided with a plurality of points, each point on the signal subframe is subjected to Fourier transform, the average value of the plurality of points is solved, and a low variance amplitude spectrum of the signal frame is obtained;
acquiring the frequency distribution of a noise subframe corresponding to the signal frame of the target phoneme for processing to obtain a low variance amplitude spectrum of the noise subframe corresponding to the target phoneme;
calculating the current influence index of the noise signal on the target phoneme according to the low variance amplitude spectrum of the noise subframe corresponding to the target phoneme and the low variance amplitude spectrum of the signal frame of the target phoneme:
wherein γ (k) represents the influence index of the ith noise subframe on the kth target phoneme, k represents the number of the target phoneme, and l represents the number of the noise subframe; x 1 (k) A low variance magnitude spectrum representing a signal frame of the kth target phoneme; alpha represents the smooth coefficient of the noise signal, namely the similarity degree of the low variance amplitude spectrum of the l-1 st noise subframe and the low variance amplitude spectrum of the l-1 st noise subframe, and the value range is [0.5,0.95 ]]；X 2 (l-1) a low variance amplitude spectrum representing the l-1 st noisy subframe; (1-alpha) | X 1 (k)| 2 +αX 2 (l-1) a low variance amplitude spectrum representing the l-th noise subframe, wherein the l-th noise subframe is obtained by updating in real time on the basis of the l-1-th noise subframe according to a signal frame of a target factor detected in real time;
calculating and obtaining the current influence index of each target factor based on a formula (1), and judging the signal of the target factor to be first-level distortion when the current influence index of the target factor is greater than a preset influence index value;
otherwise, judging the signal of the target factor to be second-level distortion; wherein the distortion degree of the first-order distortion is greater than the distortion degree of the second-order distortion:
establishing a signal compensation function of the target phoneme according to the signal distortion condition of the target factor:
where M (l, k) represents the signal compensation function θ of the kth target phoneme l-1 Representing the posterior signal-to-noise ratio of the l-1 noise subframe; theta l Representing the posterior signal-to-noise ratio of the l noise subframe; gamma ray 0 Representing a predetermined value of influence index, if gamma (k) > gamma 0 If so, the signal of the kth target phoneme is first-order distortion; if gamma (k) is less than or equal to gamma 0 Then the signal of the kth target phoneme is a second order distortion.
A portable hearing test evaluation system adapted for use with a portable device, the system comprising:
a generating module for controlling the portable device to generate a test sound signal with a preset frequency and sound intensity range,
the adjusting module is used for adjusting the playing gain of a Bluetooth headset connected with the portable equipment based on the test sound signal;
the feedback module is used for feeding the test sound signal back to the auditory canal of the tester through the Bluetooth headset after the adjustment is finished;
the device comprises a construction module, a detection module and a feedback module, wherein the construction module is used for collecting the ear canal feedback signal of a test person and constructing the hearing curve graph of the test person according to the ear canal signal;
and the judging module is used for evaluating the hearing threshold of the test personnel according to the hearing curve graph and judging the hearing resistance condition of the test personnel based on the hearing threshold.
Compared with the prior art, the invention has the following beneficial effects:
(1) The portable equipment and the Bluetooth headset are used for conducting hearing test on the tester, so that the scene limitation and the equipment limitation of the hearing test can be overcome, meanwhile, the tester can conduct the test at any place and in any time period, the practicability is improved while the test efficiency is improved, the problem that in the prior art, the tester is required to go to a hospital or a special hearing test mechanism adopts special hearing equipment to test the hearing, the test efficiency is greatly influenced due to various objective reasons such as queuing, equipment debugging and the like while the precious time of the tester is wasted, and the experience feeling of the tester is reduced is solved.
(2) By constructing the test sound signal without hearing damage to the tester, the hearing damage to the ears of the tester can be avoided, and the generated test signal can better meet the actual test requirement, so that the practicability is further improved.
(3) The hearing data graph of the test personnel for the test sound signal is generated, so that the feedback condition of the human ear of the test personnel for the test sound signal can be visually determined, the feedback frequency change graph of the test personnel for each section of test signal can be rapidly determined, the hearing curve graph of the test personnel can be reasonably constructed, and the working efficiency and the stability are improved.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
FIG. 1 is a flowchart illustrating a method for portable hearing test evaluation according to the present invention;
FIG. 2 is another flowchart of a portable hearing test evaluation method according to the present invention;
FIG. 3 is a further flowchart of a portable hearing test evaluation method according to the present invention;
fig. 4 is a schematic structural diagram of a portable hearing test evaluation system according to the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the disclosure, as detailed in the appended claims.
The embodiment discloses a portable hearing test evaluation method, which is suitable for portable equipment, and as shown in fig. 1, the method comprises the following steps:
step S101, controlling the portable equipment to generate a test sound signal with a preset frequency and sound intensity range;
step S102, adjusting the playing gain of a Bluetooth headset connected with the portable equipment based on the test sound signal;
step S103, after the adjustment is finished, feeding the test sound signal back to the auditory canal of a tester through the Bluetooth earphone;
step S104, collecting ear canal feedback signals of a test person, and constructing a hearing curve graph of the test person according to the ear canal signals;
step S105, evaluating a hearing threshold of a test person according to the hearing curve graph, and judging the hearing resistance condition of the test person based on the hearing threshold;
in this embodiment, the play gain is expressed as a play effect gain of the bluetooth self-set parameter for the test sound signal;
in this embodiment, the ear canal feedback signal is represented as a feedback wave signal of the ear canal of the test person with respect to the test sound signal.
The working principle of the technical scheme is as follows: control portable equipment and generate the test sound signal of presetting frequency and sound intensity scope, based on test sound signal adjust with the broadcast gain of the bluetooth headset that portable equipment connects, the back that finishes is adjusted, will test sound signal passes through bluetooth headset feeds back to the tester duct, gathers tester's duct feedback signal, according to the duct signal constructs tester's hearing curve graph, according to tester's hearing threshold value is evaluateed out to the hearing curve graph, based on tester's hearing obstructed condition is judged to the hearing threshold value.
The beneficial effects of the above technical scheme are: the portable equipment and the Bluetooth headset are used for conducting hearing test on the tester, so that the scene limitation and the equipment limitation of the hearing test can be overcome, meanwhile, the tester can conduct the test at any place and in any time period, the practicability is improved while the test efficiency is improved, the problem that in the prior art, the tester is required to go to a hospital or a special hearing test mechanism adopts special hearing equipment to test the hearing, the test efficiency is greatly influenced due to various objective reasons such as queuing, equipment debugging and the like while the precious time of the tester is wasted, and the experience feeling of the tester is reduced is solved.
In one embodiment, the controlling the portable device to generate the test sound signal of the preset frequency and sound intensity range includes:
acquiring a decibel range of sound volume acceptable to a standard human ear;
determining the human ear response index corresponding to each decibel volume value in the decibel range;
determining a target volume decibel range without hearing damage to a test person according to the human ear response index;
acquiring a frequency parameter range and a sound intensity parameter range corresponding to the target volume decibel range;
calling a test sound wave from a preset sound wave database, setting the wavelength of the test sound wave, and generating a plurality of sections of test signals of the test sound wave according to the frequency parameter range and the sound intensity parameter range after the setting is finished;
and integrating the multiple sections of test signals to obtain the test sound signal.
In this embodiment, the ear response index is expressed as a stimulation of a decibel volume value to a human ear in a standard case;
in this embodiment, the above-mentioned determining of the ear reaction index corresponding to each decibel volume value within the volume decibel range may be performed by performing a stimulus test on the ears by using a preset sound signal corresponding to each decibel volume value, and the ear reaction index corresponding to each decibel volume value is determined according to the facial expression and muscle reaction of the tester.
In this embodiment of the present invention,
the beneficial effects of the above technical scheme are: by constructing the test sound signal without hearing damage to the tester, the hearing damage to the ears of the tester can be avoided, and the generated test signal can better meet the actual test requirement, so that the practicability is further improved.
In one embodiment, the adjusting the play gain of the bluetooth headset connected to the portable device based on the test sound signal includes:
acquiring the frequency response of the Bluetooth headset when the testing sound signal is played;
determining an average amplitude gain of the Bluetooth headset for each frequency variation point of the test sound signal based on the frequency response;
acquiring audio file attribute information of the test sound signal;
obtaining an initial gain value of a test sound signal according to the audio file attribute information;
calculating a quotient of the average magnitude gain and the initial gain value to determine a gain factor;
and adjusting the playing gain of the Bluetooth headset according to the gain coefficient.
In this embodiment, the initial gain value is represented as a composite gain value of the playing volume and the tone of the test sound signal in the standard playing environment;
the beneficial effects of the above technical scheme are: the Bluetooth earphone can meet the standard playing parameter requirement of the test sound signal as far as possible when the test sound signal is played, so that the condition is laid for the subsequent hearing test, and the objectivity and the accuracy of the test result are ensured.
In one embodiment, as shown in fig. 2, the ear canal feedback signal of the test person is collected, and a hearing profile of the test person is constructed according to the ear canal signal, including:
step S201, calculating the stimulation index of each section of test signal to the auditory canal of a test person according to the first same-section frequency of the test sound signal and the second same-section frequency of the auditory canal feedback signal;
step S202, determining the receiving frequency band of each section of test signal by the tester according to the ear canal feedback signal by using the trained network model based on the stimulation index;
step S203, generating a hearing data graph of the test personnel for the test sound signal according to the receiving frequency band of the test personnel for each section of test signal;
step S204, determining a feedback frequency variation graph of the test person for each section of test signal according to the hearing data graph and the ear canal feedback signal;
and S205, constructing a hearing curve graph of the test person according to the feedback frequency variation graph.
The beneficial effects of the above technical scheme are: the hearing data graph of the test personnel for the test sound signal is generated, so that the feedback condition of the human ear of the test personnel for the test sound signal can be visually determined, the feedback frequency change graph of the test personnel for each section of test signal can be rapidly determined, the hearing curve graph of the test personnel can be reasonably constructed, and the working efficiency and the stability are improved.
In one embodiment, as shown in fig. 3, the evaluating the hearing threshold of the test person according to the hearing profile and determining that the hearing of the test person is blocked based on the hearing threshold includes:
step S301, determining the hearing threshold variation condition of the test person under different frequencies according to the hearing curve graph;
step S302, comprehensively evaluating a maximum hearing threshold value and a minimum hearing threshold value of a test person according to the hearing threshold value change conditions of the test person under different frequencies;
step S303, determining the fall degree between the maximum hearing threshold and the minimum hearing threshold;
and S304, determining the hearing loss type of the test personnel according to the fall degree, and judging the hearing resistance condition of the test personnel based on the hearing loss type.
The beneficial effects of the above technical scheme are: the hearing-impaired condition of the testing personnel can be rapidly and accurately determined according to the recording parameters corresponding to the hearing loss type by determining the hearing loss type of the testing personnel, so that the precision and the evaluation efficiency are improved.
In one embodiment, after the adjusting, before feeding back the test sound signal to the ear canal of the test person through the bluetooth headset, the method further comprises:
detecting a noise signal within the test environment;
acquiring a signal frequency spectrum of the noise signal, and determining a noise type according to the signal frequency spectrum;
acquiring the frequency distribution of each phoneme in the test sound signal;
determining the signal distortion condition of the target phoneme seriously influenced under the influence of the noise signal according to the frequency distribution and the noise type;
establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme;
and compensating the output signal of each target phoneme in the test business signal by using the signal compensation function of each target phoneme so as to enable the output signal to be completely fed back to the auditory canal of the test person through the Bluetooth headset.
The beneficial effects of the above technical scheme are: the influence of external noise signals on target testers can be effectively avoided by determining the distortion condition of the noise signals to the signals corresponding to each phoneme in the test sound signals and then compensating the phoneme signals, so that the human ears of the testers can completely and clearly receive the test sound signals and then perform hearing evaluation on the test sound signals, the practicability is further improved, and meanwhile, the accuracy and the objectivity of a hearing test result are also guaranteed.
In one embodiment, the process of determining the signal distortion condition of the target phoneme seriously affected by the noise signal according to the first frequency distribution and the noise type and establishing the signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme includes:
calling a target noise model corresponding to the noise signal from a preset noise model library according to the noise type;
inputting the signal frequency of the noise signal and the target noise model into a preset cyclic neural network to generate a noise cyclic model corresponding to the noise signal;
inputting the test sound signal into the noise circulation model, and performing sound coincidence training to obtain a training result;
analyzing the training result to obtain an output sound signal;
acquiring a plurality of second phonemes contained in the output sound signal;
establishing a phoneme database according to a first phoneme contained in the test sound signal;
inputting each second phoneme into the phoneme database for matching, extracting the second phonemes with the matching degree lower than the preset matching degree, and recording the second phonemes as target phonemes;
acquiring a second frequency distribution corresponding to each target phoneme;
analyzing a phoneme weight corresponding to each target phoneme according to the second frequency distribution corresponding to each target phoneme;
analyzing the distortion degree corresponding to each target phoneme based on the phoneme weight;
acquiring a first sub-signal corresponding to each target phoneme acquired on the output sound signal;
acquiring a first position area of the first sub-signal on the output sound signal;
marking a second location area on the test sound signal that coincides with the first location area;
acquiring a second sub-signal corresponding to the second position area;
acquiring a signal difference between the second sub-signal and the second sub-signal, and analyzing a signal distortion type corresponding to each first position area;
analyzing a phoneme distortion type corresponding to each target phoneme according to the signal distortion type corresponding to each first position region;
searching a target function in a preset function library based on the phoneme distortion type corresponding to each target phoneme;
generating a correction function according to the distortion degree corresponding to each target phoneme;
correcting the corresponding target function by using the correction function;
and acquiring a correction result, and generating a signal compensation function corresponding to each target phoneme.
In this example, the noise types include: white noise, band pass noise, impulse noise, speech noise;
in this example, the output sound signal represents the output result of the noise circulation model, and is substantially the sound signal that the test sound signal presents in the circulating noise environment;
in this example, the phoneme database represents a statistical library of all factors in the test sound signal;
in this example, the first sub information represents a sub signal included in the first position region on the output sound signal;
in this example, the second sub information represents a sub signal included in the second position region on the test sound signal;
in this example, the signal distortion types include: signal harmonic distortion, signal intermodulation distortion and signal transient distortion;
in this example, the phoneme distortion types include: phoneme harmonic distortion, phoneme intermodulation distortion, phoneme transient distortion.
The working principle of the technical scheme is as follows: firstly, a noise circulation model is established, sound coincidence training is carried out on a test sound signal, an output sound signal can be obtained, a plurality of second phonemes contained in the output sound signal are further obtained, then a phoneme database is established and matched with the second phonemes, the distortion degree corresponding to each target phoneme is further obtained by analyzing the phoneme weight corresponding to the target phoneme, in order to analyze the distortion degree type, the phoneme distortion type of each target phoneme can be further obtained according to the signal difference between the first sub-signal and the second sub-signal corresponding to the output sound signal and the test sound signal of each target phoneme, then the target function in the preset function library can be further corrected, and finally, the signal compensation function corresponding to each target phoneme is generated.
The beneficial effects of the above technical scheme are: because the characters of each phoneme are different, the requirements for the compensation function are different, in order to establish a corresponding signal compensation function for each phoneme, a test sound signal is input into an established noise environment for sound coincidence training, then the distortion condition of each factor is analyzed according to the output result, and a corresponding signal compensation function is established for the test sound signal, so that the purpose of signal compensation is realized, and the test sound is restored to the maximum extent.
In one embodiment, the process of determining a feedback frequency variation graph of the test person for each segment of the test signal according to the hearing data graph and the ear canal feedback signal, and constructing a hearing profile of the test person according to the feedback frequency variation graph comprises the following steps:
acquiring a test sound signal and the playing gain of the Bluetooth headset;
recording the playing gain of the test sound signal as an original gain, and analyzing the data gain of the hearing data diagram and the signal gain of the ear canal feedback signal by combining the playing gain of the Bluetooth earphone;
constructing a first reduction function based on the data gain;
restoring the hearing data graph by using the first restoring function to generate a restored hearing data graph;
constructing a second reduction function based on the signal gain;
restoring the auditory canal feedback signal by using the second restoring function to generate a restored auditory canal feedback signal;
comparing the restored hearing data graph with a standard hearing data graph, and analyzing the hearing loss degree of the testing personnel;
establishing a corresponding hearing loss ear model based on the hearing loss degree, and inputting the restored auditory canal feedback signal into the hearing loss ear model to generate an auditory canal feedback data graph;
acquiring the signal length of each section of test signal corresponding to the test sound signal, and extracting the standard specification corresponding to the section of test signal from a preset specification library based on the signal length;
adjusting the reduced data diagram and the ear canal feedback data diagram in proportion according to the standard specification, dividing the adjusted reduced data diagram and the ear canal feedback data diagram into preset sub-specifications, and generating a plurality of first sub-data diagrams and second sub-data diagrams;
comparing the first sub data graph and the second sub data graph at the same position to obtain a comparison result;
generating a feedback frequency variation graph corresponding to each section of test signal by a tester based on the comparison result;
respectively acquiring a frequency threshold corresponding to a feedback frequency variation graph corresponding to each section of test signal of a tester, and determining the hearing threshold of the tester for the section of test signal according to the frequency threshold;
establishing a hearing range corresponding to each section of test signal based on the hearing threshold;
and analyzing each feedback frequency change graph, inputting the analysis result into a corresponding hearing range, and generating a hearing curve graph.
In this example, the play gain represents the sound multiple of the bluetooth headset when playing the test sound signal;
in this example, the original gain may be 1;
in this example, the data gain indicates that a certain gain occurs in the hearing data graph because the playing gain of the test sound signals is different;
in this example, the signal gain represents a situation that the ear canal feedback signal also has a certain gain due to different playing gains of the test sound signals;
in this example, the restored hearing data graph represents a hearing data graph corresponding to the test sound signal with the data gain removed;
in this example, restoring the ear canal feedback signal represents rejecting the signal gain, the ear canal feedback signal corresponding to the test sound signal;
in this example, the degree of hearing loss is classified into normal hearing (-10 db to 25 db), mild hearing loss (26-40 db), moderate hearing loss (41-55 db), moderate hearing loss (56-70 db), severe hearing loss (70-90 db), and very severe hearing loss (greater than 90 db);
in this example, the hearing loss ear model represents ear models corresponding to different hearing loss degrees.
The working principle of the technical scheme is as follows: the method comprises the steps of obtaining a test sound signal and playing gain of a Bluetooth earphone, analyzing data gain of a hearing data graph and signal gain of an auditory canal feedback signal, establishing a first reduction function and a second reduction function based on the data gain, reducing the hearing data graph and the auditory canal feedback signal respectively, generating a reduced hearing data graph and a reduced auditory canal feedback signal, comparing the reduced hearing data graph with a standard hearing data graph, analyzing hearing loss degree of a tester, establishing a corresponding hearing loss ear model, inputting the reduced auditory canal feedback signal into the hearing loss ear model to generate an auditory canal feedback data graph, carrying out proportion adjustment on the reduced hearing data graph and the auditory canal feedback data graph, dividing the adjusted reduced hearing data graph and the auditory canal feedback data graph into preset sub-specifications, generating a plurality of first sub-data graphs and second sub-data graphs, carrying out one-to-one correspondence, obtaining comparison results, generating a feedback frequency change graph corresponding to each section of the test signal, respectively obtaining a frequency threshold corresponding to each feedback frequency change graph, establishing a hearing range corresponding to each section of the test signal, inputting each feedback frequency change graph into a corresponding to the generation graph, and generating a corresponding to the hearing range.
The beneficial effects of the above technical scheme are: the hearing curve graph can accurately reflect the hearing condition of a tester, in order to generate an accurate hearing curve graph, the hearing data graph and the gain of the ear canal feedback signal are eliminated, then segmentation and comparison are carried out, a feedback frequency change graph corresponding to each segment is obtained, then the feedback frequency change graph is analyzed, and the hearing curve graph is generated.
In one embodiment, the signal distortion condition of the target phoneme seriously influenced under the influence of the noise signal is determined according to the frequency distribution and the noise type; establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme, wherein the signal compensation function comprises the following steps:
when a noise signal is detected, updating a signal spectrum of the noise signal in real time to obtain any frame of noise signal as a target frame, and obtaining a second frequency distribution of the target frame according to a first frequency distribution of each phoneme in a matched frame test sound signal corresponding to the target frame;
determining a noise score of a noise signal according to the noise type, and determining a target phoneme seriously influenced under the influence of the noise signal according to the noise score, the second frequency distribution and a signal frequency interval of each phoneme in the test sound signal;
confirming the corresponding relation between a target phoneme and the target frame, and dividing the target frame into a plurality of noise subframes according to the corresponding relation;
wherein, the corresponding relation means that each frame of the noise signal corresponds to a plurality of target phonemes, and each noise subframe corresponds to a target phoneme;
meanwhile, a signal frame of the target phoneme is divided into N signal subframes, each signal subframe is provided with a plurality of points, each point on the signal subframe is subjected to Fourier transform, and the average value of the plurality of points is solved to obtain a low variance amplitude spectrum of the signal frame;
acquiring the frequency distribution of a noise subframe corresponding to the signal frame of the target phoneme for processing to obtain a low variance amplitude spectrum of the noise subframe corresponding to the target phoneme;
calculating the current influence index of the noise signal on the target phoneme according to the low variance amplitude spectrum of the noise subframe corresponding to the target phoneme and the low variance amplitude spectrum of the signal frame of the target phoneme:
wherein γ (k) represents the influence index of the ith noise subframe on the kth target phoneme, k represents the number of the target phoneme, and l represents the number of the noise subframe; x 1 (k) A low variance magnitude spectrum representing a signal frame of the kth target phoneme; alpha represents the smoothing coefficient of the noise signal, namely the similarity between the low variance amplitude spectrum of the l-1 st noise subframe and the low variance amplitude spectrum of the l-1 st noise subframe, and the value range is [0.5,0.95 ]]；X 2 (l-1) a low variance amplitude spectrum representing the l-1 st noisy subframe; (1-alpha) | X 1 (k)| 2 +αX 2 (l-1) a low variance amplitude spectrum representing the l-th noise subframe, wherein the l-th noise subframe is obtained by updating in real time on the basis of the l-1-th noise subframe according to a signal frame of a target factor detected in real time;
calculating and obtaining the current influence index of each target factor based on a formula (1), and judging the signal of the target factor to be first-level distortion when the current influence index of the target factor is greater than a preset influence index value;
otherwise, judging the signal of the target factor to be second-level distortion; wherein the distortion degree of the first-order distortion is greater than the distortion degree of the second-order distortion:
establishing a signal compensation function of the target phoneme according to the signal distortion condition of the target factor:
where M (l, k) represents the signal compensation function θ of the kth target phoneme l-1 Representing the posterior signal-to-noise ratio of the l-1 noise subframe; theta l Representing the posterior signal-to-noise ratio of the l noise subframe; gamma ray 0 Representing a predetermined impact index value if gamma (k) > gamma 0 If so, the signal of the kth target phoneme is first-order distortion; if gamma (k) is less than or equal to gamma 0 Then the signal of the kth target phoneme is a second order distortion.
The beneficial effects of the above technical scheme are: after the noise signal is detected, the frequency spectrum information of the noise signal is updated in real time, so that the influence of random spikes generated on a frequency domain on a test signal is reduced; meanwhile, the signal distortion condition of each target phoneme is represented according to the influence index, the influence of the noise signal on the target factors is more intuitively displayed through the specific numerical value, the target phonemes of the test signal are compensated according to the influence index, the interference of the hearing test is reduced, and a basis is provided for obtaining a more accurate hearing test result.
The embodiment also discloses a portable hearing test evaluation system, which is suitable for portable equipment, and as shown in fig. 4, the system includes:
a generating module 401, configured to control the portable device to generate a test sound signal with a preset frequency and sound intensity range;
an adjusting module 402, configured to adjust a play gain of a bluetooth headset connected to the portable device based on the test sound signal;
the feedback module 403 is configured to feed the test sound signal back to the ear canal of the test person through the bluetooth headset after the adjustment is completed;
the constructing module 404 is configured to collect an ear canal feedback signal of a test person, and construct a hearing curve graph of the test person according to the ear canal feedback signal;
and the judging module 405 is configured to evaluate a hearing threshold of the test person according to the hearing curve graph, and judge a hearing-impaired condition of the test person based on the hearing threshold.
The working principle and the advantageous effects of the above technical solution have been explained in the method claims, and are not described herein again.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (7)
1. A portable hearing test evaluation method, suitable for portable devices, comprising the steps of:
controlling the portable equipment to generate a test sound signal with a preset frequency and sound intensity range;
adjusting a play gain of a Bluetooth headset connected with the portable device based on the test sound signal;
after the adjustment is finished, feeding the test sound signal back to the auditory canal of a tester through the Bluetooth earphone;
collecting auditory canal feedback signals of a test person, and constructing a hearing curve graph of the test person according to the auditory canal feedback signals;
evaluating the hearing threshold of the test personnel according to the hearing curve graph, and judging the hearing resistance condition of the test personnel based on the hearing threshold;
the adjusting of the play gain of the bluetooth headset connected to the portable device based on the test sound signal includes:
acquiring the frequency response of the Bluetooth headset when the testing sound signal is played;
determining an average amplitude gain of the Bluetooth headset for each frequency variation point of the test sound signal based on the frequency response;
acquiring audio file attribute information of the test sound signal;
obtaining an initial gain value of a test sound signal according to the audio file attribute information;
calculating a quotient of the average magnitude gain and the initial gain value to determine a gain factor;
adjusting the playing gain of the Bluetooth headset according to the gain coefficient;
gather the ear canal feedback signal of test personnel, according to the ear canal feedback signal constructs the hearing curve graph of test personnel, includes:
calculating the stimulation index of each section of test signal to the auditory canal of the test person according to the first section frequency of the test sound signal and the second section frequency of the auditory canal feedback signal;
determining the receiving frequency band of each section of test signal for the tester according to the ear canal feedback signal by using a trained network model based on the stimulation index;
generating a hearing data graph of the test personnel for the test sound signal according to the receiving frequency band of the test personnel for each section of test signal;
determining a feedback frequency change graph of the test person for each section of test signal according to the hearing data graph and the ear canal feedback signal;
constructing a hearing curve graph of the test person according to the feedback frequency variation graph;
the process of determining a feedback frequency variation graph of the test person for each section of the test signal according to the hearing data graph and the ear canal feedback signal and constructing a hearing curve graph of the test person according to the feedback frequency variation graph comprises the following steps:
acquiring a test sound signal and the playing gain of the Bluetooth headset;
recording the playing gain of the test sound signal as an original gain, and analyzing the data gain of the hearing data graph and the signal gain of the ear canal feedback signal by combining the playing gain of the Bluetooth earphone;
constructing a first reduction function based on the data gain;
restoring the hearing data graph by using the first restoring function to generate a restored hearing data graph;
constructing a second reduction function based on the signal gain;
restoring the auditory canal feedback signal by using the second restoring function to generate a restored auditory canal feedback signal;
comparing the restored hearing data graph with a standard hearing data graph, and analyzing the hearing loss degree of the testing personnel;
establishing a corresponding hearing loss ear model based on the hearing loss degree, and inputting the restored auditory canal feedback signal into the hearing loss ear model to generate an auditory canal feedback data graph;
acquiring the signal length of each section of test signal corresponding to the test sound signal, and extracting the standard specification corresponding to the section of test signal from a preset specification library based on the signal length;
adjusting the restored hearing data diagram and the ear canal feedback data diagram in proportion according to the standard specification, dividing the adjusted restored data diagram and the ear canal feedback data diagram into preset sub-specifications, and generating a plurality of first sub-data diagrams and second sub-data diagrams;
comparing the first sub data graph and the second sub data graph at the same position to obtain a comparison result;
generating a feedback frequency variation graph corresponding to each section of test signal by a tester based on the comparison result;
respectively acquiring a frequency threshold corresponding to a feedback frequency variation graph corresponding to each section of test signal of a tester, and determining the hearing threshold of the tester for the section of test signal according to the frequency threshold;
establishing a hearing range corresponding to each section of test signal based on the hearing threshold;
and analyzing each feedback frequency change graph, inputting the analysis result into a corresponding hearing range, and generating a hearing curve graph.
2. The portable hearing test evaluation method of claim 1, wherein the controlling the portable device to generate the test sound signal at a preset frequency and sound intensity range comprises:
acquiring a decibel range of sound volume acceptable to a standard human ear;
determining the human ear response index corresponding to each decibel volume value in the decibel range;
determining a target volume decibel range without hearing damage to a test person according to the human ear response index;
acquiring a frequency parameter range and a sound intensity parameter range corresponding to the target volume decibel range;
calling a test sound wave from a preset sound wave database, setting the wavelength of the test sound wave, and generating a multi-section test signal of the test sound wave according to the frequency parameter range and the sound intensity parameter range after the setting is finished;
and integrating the multiple sections of test signals to obtain the test sound signal.
3. The portable hearing test evaluation method of claim 1, wherein the evaluating the hearing threshold of the test person from the hearing profile and determining the hearing impaired condition of the test person based on the hearing threshold comprises:
determining the change condition of the hearing threshold of the test person under different frequencies according to the hearing curve graph;
comprehensively evaluating the maximum hearing threshold value and the minimum hearing threshold value of the test personnel according to the hearing threshold value change conditions of the test personnel under different frequencies;
determining a degree of drop between the maximum hearing threshold and the minimum hearing threshold;
determining the hearing loss type of the test personnel according to the fall degree, and judging the hearing resistance condition of the test personnel based on the hearing loss type.
4. The portable hearing test evaluation method of claim 1, wherein after conditioning, prior to feeding the test sound signal back to the ear canal of the test person via the bluetooth headset, the method further comprises:
detecting a noise signal within the test environment;
acquiring a signal frequency spectrum of the noise signal, and determining a noise type according to the signal frequency spectrum;
acquiring the frequency distribution of each phoneme in the test sound signal;
determining the signal distortion condition of the target phoneme seriously influenced under the influence of the noise signal according to the frequency distribution and the noise type;
establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme;
and compensating the output signal of each target phoneme in the test business signal by using the signal compensation function of each target phoneme so as to enable the output signal to be completely fed back to the auditory canal of the test person through the Bluetooth headset.
5. The portable hearing test evaluation method of claim 4, wherein the procedure of determining the signal distortion of the target phoneme seriously affected by the noise signal according to the frequency distribution and the noise type, and establishing the signal compensation function of each target phoneme according to the signal distortion of the target phoneme comprises:
calling a target noise model corresponding to the noise signal from a preset noise model library according to the noise type;
inputting the signal frequency of the noise signal and the target noise model into a preset cyclic neural network to generate a noise cyclic model corresponding to the noise signal;
inputting the test sound signal into the noise circulation model, and performing sound coincidence training to obtain a training result;
analyzing the training result to obtain an output sound signal;
establishing a phoneme database according to a first phoneme contained in the test sound signal;
acquiring a plurality of second phonemes contained in the output sound signal;
inputting each second phoneme into the phoneme database for matching, extracting the second phonemes with the matching degree lower than a preset matching degree, and recording the second phonemes as target phonemes;
acquiring a second frequency distribution corresponding to each target phoneme;
analyzing a phoneme weight corresponding to each target phoneme according to the second frequency distribution corresponding to each target phoneme;
analyzing the distortion degree corresponding to each target phoneme based on the phoneme weight;
acquiring a first sub-signal corresponding to each target phoneme acquired from the output sound signal;
acquiring a first position area of the first sub-signal on the output sound signal;
marking a second location area on the test sound signal that coincides with the first location area;
acquiring a second sub-signal corresponding to the second position area;
acquiring a signal difference between the second sub-signal and the second sub-signal, and analyzing a signal distortion type corresponding to each first position area;
analyzing a phoneme distortion type corresponding to each target phoneme according to the signal distortion type corresponding to each first position region;
searching a target function in a preset function library based on the phoneme distortion type corresponding to each target phoneme;
generating a correction function according to the distortion degree corresponding to each target phoneme;
correcting the corresponding target function by using the correction function;
and acquiring a correction result, and generating a signal compensation function corresponding to each target phoneme.
6. The portable hearing test evaluation method of claim 4, wherein the signal distortion of the target phoneme that is severely affected by the noise signal is determined according to the frequency distribution and the noise type; establishing a signal compensation function of each target phoneme according to the signal distortion condition of the target phoneme, wherein the signal compensation function comprises the following steps:
when a noise signal is detected, updating a signal spectrum of the noise signal in real time to obtain any frame of noise signal as a target frame, and obtaining a second frequency distribution of the target frame according to a first frequency distribution of each phoneme in a matched frame test sound signal corresponding to the target frame;
determining a noise score of a noise signal according to the noise type, and determining a target phoneme seriously influenced under the influence of the noise signal according to the noise score, the second frequency distribution and a signal frequency interval of each phoneme in the test sound signal;
confirming the corresponding relation between a target phoneme and the target frame, and dividing the target frame into a plurality of noise subframes according to the corresponding relation;
wherein, the corresponding relation means that each frame of the noise signal corresponds to a plurality of target phonemes, and each noise subframe corresponds to a target phoneme;
meanwhile, a signal frame of the target phoneme is divided into N signal subframes, each signal subframe is provided with a plurality of points, each point on the signal subframe is subjected to Fourier transform, and the average value of the plurality of points is solved to obtain a low variance amplitude spectrum of the signal frame;
acquiring the frequency distribution of a noise subframe corresponding to the signal frame of the target phoneme for processing to obtain a low variance amplitude spectrum of the noise subframe corresponding to the target phoneme;
calculating the current influence index of the noise signal on the target phoneme according to the low variance amplitude spectrum of the noise subframe corresponding to the target phoneme and the low variance amplitude spectrum of the signal frame of the target phoneme:
wherein γ (k) represents the influence index of the l-th noise subframe on the k-th target phoneme, k represents the number of the target phoneme, and l represents the noise subframeNumber of (2); x 1 (k) A low variance magnitude spectrum representing a signal frame of the kth target phoneme; alpha represents the smooth coefficient of the noise signal, namely the similarity degree of the low variance amplitude spectrum of the l-1 st noise subframe and the low variance amplitude spectrum of the l-1 st noise subframe, and the value range is [0.5,0.95 ]]；X 2 (l-1) a low variance amplitude spectrum representing the l-1 st noisy subframe; (1-alpha) | X 1 (k)| 2 +αX 2 (l-1) a low variance amplitude spectrum representing the l-th noise subframe, wherein the l-th noise subframe is obtained by updating in real time on the basis of the l-1-th noise subframe according to a signal frame of a target factor detected in real time;
calculating and obtaining the current influence index of each target factor based on a formula (1), and judging the signal of the target factor to be first-level distortion when the current influence index of the target factor is greater than a preset influence index value;
otherwise, judging the signal of the target factor to be second-level distortion; wherein the distortion degree of the first-order distortion is greater than the distortion degree of the second-order distortion:
establishing a signal compensation function of the target phoneme according to the signal distortion condition of the target factor:
wherein M (l, k) represents a signal compensation function of the kth target phoneme; theta l-1 The posterior signal-to-noise ratio of the l-1 noise subframe is represented; theta l Representing the posterior signal-to-noise ratio of the l noise subframe; gamma ray 0 Representing a predetermined value of influence index, if gamma (k) > gamma 0 If so, the signal of the kth target phoneme is first-order distortion; if gamma (k) is less than or equal to gamma 0 Then the signal of the kth target phoneme is a second order distortion.
7. A portable hearing test evaluation system adapted for use with a portable device, the system comprising:
the generating module is used for controlling the portable equipment to generate a test sound signal with preset frequency and sound intensity range;
the adjusting module is used for adjusting the playing gain of a Bluetooth headset connected with the portable equipment based on the test sound signal;
the feedback module is used for feeding the test sound signal back to the auditory canal of the tester through the Bluetooth headset after the adjustment is finished;
the device comprises a construction module, a detection module and a control module, wherein the construction module is used for collecting the ear canal feedback signal of a test person and constructing the hearing curve graph of the test person according to the ear canal feedback signal;
the judging module is used for evaluating the hearing threshold of the test personnel according to the hearing curve graph and judging the hearing resistance condition of the test personnel based on the hearing threshold;
the adjusting of the playing gain of the bluetooth headset connected to the portable device based on the test sound signal includes:
acquiring the frequency response of the Bluetooth headset when the testing sound signal is played;
determining an average amplitude gain of the Bluetooth headset for each frequency variation point of the test sound signal based on the frequency response;
acquiring audio file attribute information of the test sound signal;
obtaining an initial gain value of a test sound signal according to the audio file attribute information;
calculating a quotient of the average magnitude gain and the initial gain value to determine a gain factor;
adjusting the playing gain of the Bluetooth headset according to the gain coefficient;
gather the ear canal feedback signal of test personnel, according to the ear canal feedback signal constructs the hearing curve graph of test personnel, includes:
calculating the stimulation index of each section of test signal to the auditory canal of the test person according to the first same-section frequency of the test sound signal and the second same-section frequency of the auditory canal feedback signal;
determining the receiving frequency band of each section of test signal for the tester according to the ear canal feedback signal by using a trained network model based on the stimulation index;
generating a hearing data graph of the test personnel for the test sound signal according to the receiving frequency band of the test personnel for each section of test signal;
determining a feedback frequency change graph of the test person for each section of test signal according to the hearing data graph and the ear canal feedback signal;
constructing a hearing curve graph of the test person according to the feedback frequency variation graph;
the process of determining a feedback frequency change diagram of the test person for each section of the test signal according to the hearing data diagram and the ear canal feedback signal, and constructing a hearing curve graph of the test person according to the feedback frequency change diagram comprises the following steps:
acquiring a test sound signal and the playing gain of the Bluetooth headset;
recording the playing gain of the test sound signal as an original gain, and analyzing the data gain of the hearing data graph and the signal gain of the ear canal feedback signal by combining the playing gain of the Bluetooth earphone;
constructing a first reduction function based on the data gain;
restoring the hearing data graph by using the first restoring function to generate a restored hearing data graph;
constructing a second reduction function based on the signal gain;
restoring the auditory canal feedback signal by using the second restoring function to generate a restored auditory canal feedback signal;
comparing the restored hearing data graph with a standard hearing data graph, and analyzing the hearing loss degree of the testing personnel;
establishing a corresponding hearing loss ear model based on the hearing loss degree, and inputting the restored auditory canal feedback signal into the hearing loss ear model to generate an auditory canal feedback data graph;
acquiring the signal length of each section of test signal corresponding to the test sound signal, and extracting the standard specification corresponding to the section of test signal from a preset specification library based on the signal length;
adjusting the restored hearing data diagram and the ear canal feedback data diagram in proportion according to the standard specification, dividing the adjusted restored data diagram and the ear canal feedback data diagram into preset sub-specifications, and generating a plurality of first sub-data diagrams and second sub-data diagrams;
comparing the first sub data graph and the second sub data graph at the same position to obtain a comparison result;
generating a feedback frequency variation graph corresponding to each section of test signal by a tester based on the comparison result;
respectively acquiring a frequency threshold corresponding to a feedback frequency variation graph corresponding to each section of test signal of a tester, and determining the hearing threshold of the tester for the section of test signal according to the frequency threshold;
establishing a hearing range corresponding to each section of test signal based on the hearing threshold;
and analyzing each feedback frequency change graph, inputting the analysis result into a corresponding hearing range, and generating a hearing curve graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210823217.7A CN115040117B (en) | 2022-07-14 | 2022-07-14 | Portable hearing test evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210823217.7A CN115040117B (en) | 2022-07-14 | 2022-07-14 | Portable hearing test evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115040117A CN115040117A (en) | 2022-09-13 |
| CN115040117B true CN115040117B (en) | 2023-03-21 |
Family
ID=83165536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210823217.7A Active CN115040117B (en) | 2022-07-14 | 2022-07-14 | Portable hearing test evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115040117B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2463856A1 (en) * | 2010-12-09 | 2012-06-13 | Oticon A/s | Method to reduce artifacts in algorithms with fast-varying gain |
| CN104144374A (en) * | 2013-05-06 | 2014-11-12 | 展讯通信（上海）有限公司 | Listening assisting method and system based on mobile device |
| CN106073796A (en) * | 2016-05-27 | 2016-11-09 | 深圳市易特科信息技术有限公司 | Audition health detecting system based on bone conduction and method |
| CN110650398A (en) * | 2015-11-24 | 2020-01-03 | 伯斯有限公司 | Controlling ambient sound volume |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7564979B2 (en) * | 2005-01-08 | 2009-07-21 | Robert Swartz | Listener specific audio reproduction system |
| KR101744761B1 (en) * | 2012-11-30 | 2017-06-09 | 한화테크윈 주식회사 | Method and Apparatus for processing image |
| US20160142453A1 (en) * | 2014-03-14 | 2016-05-19 | Qualcomm Incorporated | Features and optimizations for personal communication device based public addressing system |
| CN109246567A (en) * | 2018-09-29 | 2019-01-18 | 湖南可孚医疗科技发展有限公司 | A kind of hearing evaluation detection system |
| CN111447539B (en) * | 2020-03-25 | 2021-06-18 | 北京聆通科技有限公司 | Fitting method and device for hearing earphones |
-
2022
- 2022-07-14 CN CN202210823217.7A patent/CN115040117B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2463856A1 (en) * | 2010-12-09 | 2012-06-13 | Oticon A/s | Method to reduce artifacts in algorithms with fast-varying gain |
| CN104144374A (en) * | 2013-05-06 | 2014-11-12 | 展讯通信（上海）有限公司 | Listening assisting method and system based on mobile device |
| CN110650398A (en) * | 2015-11-24 | 2020-01-03 | 伯斯有限公司 | Controlling ambient sound volume |
| CN106073796A (en) * | 2016-05-27 | 2016-11-09 | 深圳市易特科信息技术有限公司 | Audition health detecting system based on bone conduction and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115040117A (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102781322B (en) | Evaluation system of speech sound hearing, method of same | |
| Healy et al. | A deep learning algorithm to increase intelligibility for hearing-impaired listeners in the presence of a competing talker and reverberation | |
| EP2603018A1 (en) | Hearing aid with speaking activity recognition and method for operating a hearing aid | |
| KR101148671B1 (en) | A method and system for speech intelligibility measurement of an audio transmission system | |
| US9319812B2 (en) | System and methods of subject classification based on assessed hearing capabilities | |
| CN105530565A (en) | Automatic sound equalization device | |
| WO2021135030A1 (en) | Hearing threshold and/or hearing state detection system and method | |
| Ferry et al. | A computer model of medial efferent suppression in the mammalian auditory system | |
| CN109982637A (en) | The method for accurately estimating pure tone threshold using the audio system not referred to | |
| CN104247460A (en) | Uncomfortable loudness level estimation system, uncomfortable loudness level estimation processor, uncomfortable loudness level estimation method, and computer program thereof | |
| CN108919962B (en) | Auxiliary piano training method based on brain-computer data centralized processing | |
| Messing et al. | A non-linear efferent-inspired model of the auditory system; matching human confusions in stationary noise | |
| CN107320109A (en) | Frequency identification method of testing | |
| CN115040117B (en) | Portable hearing test evaluation method and system | |
| KR102292544B1 (en) | Apparatus and method for evaluating cognitive response of comparative sounds | |
| CN112205981B (en) | Hearing assessment method and device based on speech intelligibility index | |
| CN108186026A (en) | A kind of hearing aid tests method of completing the square | |
| Salehi et al. | On nonintrusive speech quality estimation for hearing aids | |
| Keshishzadeh et al. | Individualized cochlear models based on distortion product otoacoustic emissions | |
| Marshall et al. | Metrics including time-varying loudness models to assess the impact of sonic booms and other transient sounds | |
| KR101798577B1 (en) | The Fitting Method of Hearing Aids Using Personal Customized Living Noise | |
| Zhang et al. | Objective evaluation system for noise reduction performance of hearing aids | |
| Neher et al. | Relating hearing aid users’ preferred noise reduction setting to different measures of noise tolerance and distortion sensitivity | |
| CN117041847B (en) | Adaptive microphone matching method and system for hearing aid | |
| CN117202075A (en) | Austenite-based hearing aid fitting method, system, medium and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |