CN106714062B - Digital hearing aid intelligent fitting method based on BP artificial neural network - Google Patents
Digital hearing aid intelligent fitting method based on BP artificial neural network Download PDFInfo
- Publication number
- CN106714062B CN106714062B CN201611087426.0A CN201611087426A CN106714062B CN 106714062 B CN106714062 B CN 106714062B CN 201611087426 A CN201611087426 A CN 201611087426A CN 106714062 B CN106714062 B CN 106714062B
- Authority
- CN
- China
- Prior art keywords
- neural network
- artificial neural
- network
- fitting
- gain
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R25/00—Deaf-aid sets, i.e. electro-acoustic or electro-mechanical hearing aids; Electric tinnitus maskers providing an auditory perception
- H04R25/50—Customised settings for obtaining desired overall acoustical characteristics
- H04R25/505—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing
- H04R25/507—Customised settings for obtaining desired overall acoustical characteristics using digital signal processing implemented by neural network or fuzzy logic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2225/00—Details of deaf aids covered by H04R25/00, not provided for in any of its subgroups
- H04R2225/43—Signal processing in hearing aids to enhance the speech intelligibility
Abstract
The invention discloses a digital hearing aid intelligent fitting algorithm based on a BP artificial neural network, which is based on the BP artificial neural network, trains the network through a large amount of training data to obtain a satisfactory mature network, and corrects the network by utilizing a self-established formula model to obtain the mature intelligent fitting algorithm; the invention optimizes the initial weight and threshold of the BP artificial neural network by using the principle of genetic algorithm, trains the BP artificial neural network by using the existing audiogram and spectrum gain response as training data, and corrects the network by a fitting formula model to obtain a mature BP artificial neural network to replace the existing fitting formula, thereby obtaining parameters of gain, maximum sound output, compression ratio, compression inflection point and the like of each channel of the digital hearing aid.
Description
Technical Field
The invention belongs to an intelligent fitting algorithm in the field of digital hearing aids, and particularly relates to an intelligent fitting algorithm of a digital hearing aid based on a BP artificial neural network.
Background
At present, the aging problem of the Chinese population is getting more and more serious, the proportion of the Chinese population is close to 30 percent by 2030, deafness is a common disease of the old, the number of the old with deafness is increasing along with the increase of the old population, and the demand of people for hearing aids is increasing day by day.
The development of digital hearing aids lays a solid foundation for the development of hearing aids, and both the accuracy of speech signal processing and the convenience of application make great progress, the optimization of the performance mainly depends on a dynamic range compressor, and how the dynamic compressor works mainly depends on gain parameters obtained by fitting formulas. Fitting formulas for digital hearing aids are numerous and are largely classified into threshold-based and loudness-based, with threshold-based again being classified into linear and non-linear. For the loudness-based LGOB, linear, NAL, DSL and the like, and nonlinear, NAL-NL1, FIG6, DSL (i/o) and the like are mainly used, and POGO, NAL and DSL are the three most widely used at present.
Different fitting formulas have different results for the same patient, and the effect achieved by fitting is also beneficial and disadvantageous. The POGO formula is a simple half-gain method, namely, half of the hearing threshold of a patient is obtained, and an empirical constant is added to obtain the channel gain. The development of NAL has gone through four generations, and the present NAL-NL2 is very mature, especially for the selection of patients with moderate deafness. The DSL fitting formula is mainly applicable to children. Although these conventional prescription formulas have advantages, they have poor effect on deaf patients with severe hearing impairment, and because different patients need to select different prescription formulas to achieve the optimal prescription effect, they bring great inconvenience to the prescription work.
The dispenser hopes to have a simple dispensing scheme, which can obtain a very accurate dispensing parameter according to the audiogram of the patient, and will gradually improve with the increase of the dispensing cases, so as to achieve a satisfactory dispensing effect.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a digital hearing aid intelligent fitting algorithm based on a BP artificial neural network, the algorithm is based on the BP artificial neural network, the network is trained through a large amount of training data to obtain a satisfactory mature network, and the network is corrected by utilizing a self-established formula model, so that the mature intelligent fitting algorithm is obtained; the invention optimizes the initial weight and threshold of the BP artificial neural network by using the principle of genetic algorithm, trains the BP artificial neural network by using the existing audiogram and spectrum gain response as training data, and corrects the network by a fitting formula model to obtain a mature BP artificial neural network to replace the existing fitting formula, thereby obtaining parameters of gain, maximum sound output, compression ratio, compression inflection point and the like of each channel of the digital hearing aid.
The purpose of the invention is realized by the following technical scheme:
a digital hearing aid intelligent fitting algorithm based on a BP artificial neural network utilizes the existing audiogram and spectral gain response as training data to train the BP artificial neural network, and estimates and predicts a new patient through the trained network, which comprises the following steps:
(1) constructing a BP artificial neural network, which comprises an input layer, a hidden layer and an output layer;
(2) optimizing the initial weight and the initial threshold of the BP artificial neural network established in the step (1) by using a genetic algorithm;
(3) training the optimized BP artificial neural network in the step (2), wherein the training data adopt the cases of real patients, and the BP artificial neural network is continuously trained to gradually mature, so that a relatively mature digital hearing aid fitting algorithm based on the BP artificial neural network is finally obtained;
(4) building a formula model for optimizing the gain output obtained by the fitting algorithm in the step (3);
(5) and (4) correcting the fitting algorithm in a weighting mode by using the formula model established in the step (4) to obtain gain output, wherein the weighting coefficient is gradually close to 1 along with the continuous increase of subsequent training data, and finally obtaining the mature and perfect digital hearing aid intelligent fitting algorithm based on the BP artificial neural network.
The BP artificial neural network parameter in the step (1) comprises a weight W between an input layer and a hidden layerijAnd the weight W between the hidden layer and the output layerjkAnd also includes the thresholds of the hidden layer and the output layer.
The node numbers of the input layer, the hidden layer and the output layer are respectively 10, 20 and 30, and the input layer, the hidden layer and the output layer are divided into 10 channels according to frequency spectrums, namely the frequency of the channels is 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000 and 8000Hz, and the target is gain, compression ratio and compression inflection point of 40 dB.
The optimization process in the step (2) is as follows: a. setting the population scale and the iteration times of a genetic algorithm; b. performing GA coding on the initial weight and the threshold of the BP artificial neural network, and obtaining the fitness of each individual through the audiogram and the frequency spectrum gain response of a patient; c. and finally, calculating the population fitness of the initial weight and the threshold through selection operation, cross operation and mutation operation of a genetic algorithm, and finally optimizing the network threshold and the weight.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. in order to more accurately determine the initial weight and the threshold of the neural network, the neural network is optimized by utilizing the genetic algorithm, the optimization algorithm is very mature, and the genetic algorithm follows the principle of 'number competition and human selection and survival of superior persons' to complete the optimization of the initial weight and the threshold of the network; after the BP artificial neural network is optimized through a genetic algorithm, the BP artificial neural network has inherent advantages compared with the original BP artificial neural network, the network is trained through audiogram and spectrum gain response in a large number of fitting cases, and with the continuous increase of training data, the intelligent fitting algorithm of the digital hearing aid based on the BP artificial neural network is more and more mature.
2. In order to enable the fitting result to be more accurate, the invention also utilizes a formula model established by the invention to correct the BP artificial neural network, gains of all channels are obtained through weighting of the BP artificial neural network and the BP artificial neural network, and finally a mature digital hearing aid intelligent fitting algorithm is obtained.
3. In the fitting stage, the fitting operator can obtain satisfactory parameters such as gain, compression ratio, compression inflection point and the like of each channel only by taking the result of the hearing test as input data and calculating through the intelligent fitting algorithm, and because the digital hearing aid algorithm based on the BP artificial neural network is a mature network obtained through training of a large number of fitting cases, the output result of the digital hearing aid algorithm inevitably approaches the real fitting effect of the patient.
4. The algorithm model related to the invention is relatively mature, compared with other prescription formula, the digital hearing aid intelligent fitting algorithm based on BP artificial neural network has wider coverage range, and because the algorithm model is a mature algorithm model obtained by a true experiment fitting case, the output result is also better than other prescription formula. The algorithm is suitable for replacing the existing fitting prescription formula in the fitting process of the digital hearing aid, and a more accurate and convenient fitting scheme is certainly provided for the fitting work.
Drawings
Fig. 1 is a schematic diagram of a topology of a BP artificial neural network used in the present invention.
FIG. 2 is a specific flowchart of optimizing and training a BP artificial neural network by using a genetic algorithm according to the present invention.
FIG. 3 is a flow chart of a formula model test scheme used in the present invention.
FIG. 4 is a flow chart of formula fitting principles and BP neural network intelligent algorithm weighted fitting used in the present invention.
Detailed Description
The invention is further described with reference to the accompanying drawings in which:
a digital hearing aid intelligent fitting algorithm based on a BP artificial neural network actually utilizes the existing audiogram and spectral gain response as training data to train the BP artificial neural network, and estimates and predicts a new patient through the trained network. Further, the BP artificial neural network optimized through the genetic algorithm principle is utilized, the existing audiogram and the spectrum gain response are used as training data to train the BP artificial neural network, meanwhile, a model of the fitting formula is utilized to correct the trained network, and finally, the mature digital hearing aid fitting algorithm based on the BP artificial neural network is obtained. The specific process steps are as follows:
(1) the BP artificial neural network used in this embodiment is a multi-level feedforward neural network, that is, forward data transfer and backward error transfer. As shown in fig. 1, a topology structure of a BP artificial neural network, the BP artificial neural network is a very mature artificial neural network, and a main structure includes an input layer, a hidden layer, and an output layer. The main parameters include the weight W between the input layer and the hidden layerijAnd the weight W between the hidden layer and the output layerjkAnd the threshold values of the hidden layer and the output layer are also included. The fitting algorithm model in the invention provides 10 input nodes of BP artificial neural network, namely the hearing threshold and the gender at the frequency of 250, 500, 1000, 2000, 3000, 4000, 6000 and 8000Hz(male and female are represented by 1, 2, respectively) and experience (first-time, short-term, experienced, and long-term users are represented by 1, 2, 3, 4, respectively). The number of hidden layer nodes is 20, the number of output nodes is 30, and the output is a 10 channel output, i.e., a gain, compression ratio and compression knee targeted at 40dB at frequencies of 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000 and 8000 Hz. The training data for training the network are all from the real fitting case of the patient, so that the reliability of the network is ensured.
(2) Optimizing the initial weight and initial threshold of the BP artificial neural network established in the step (1); fig. 2 is a specific flowchart for optimizing and training a network, and fig. 1 specifically illustrates specific parameters of a BP artificial neural network utilized by the algorithm, and in order to ensure the optimality of the network, the BP artificial neural network is optimized by a genetic algorithm. A genetic algorithm is an algorithm that optimizes numerical values, where the goal is to find optimal initial weights and thresholds for the neural network. The population size of the genetic algorithm is specified to be 50 individuals, and the iteration times are 1000 times. The specific optimization steps are that GA coding is carried out on the initial weight and the threshold of the BP artificial neural network, then the fitness of each individual is obtained through audiogram and frequency spectrum gain response of a patient in a fitting case, then population fitness calculation is carried out on the initial weight and the threshold through selection operation, cross operation and variation operation of a genetic algorithm, and finally the purpose of optimizing the network threshold and the weight is achieved. In the training process, the BP neural network obtains prediction output, namely gain, compression ratio and compression inflection point of each channel according to input audiometric data through calculation of hidden layer nodes and calculation of output nodes in sequence, the prediction output is compared with expected output to obtain errors, and the errors are reversely transmitted through the network to update threshold values and weight values in the network, so that the output result gradually approaches to a real output result.
(3) Training the optimized BP artificial neural network in the step (2), wherein the training data adopt the cases of real patients, and the steps are mature through continuous training of the BP artificial neural network, so that a relatively mature digital hearing aid fitting algorithm based on the BP artificial neural network is finally obtained;
(4) building a formula model for optimizing the gain output obtained by the fitting algorithm in the step (3); FIG. 3 is a flow chart of the constructed formula model fitting scheme. Firstly, acquiring input data, namely, an eight-channel hearing threshold, namely, a hearing threshold with a frequency of 250, 500, 1000, 2000, 3000, 4000, 6000 and 8000Hz and whether a conductive deaf patient (1, not 0) exists, then taking half of the hearing threshold as a gain of 40dB input and changing the input data into ten-channel (gains with a frequency of 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000 and 8000 Hz), namely, averaging the gains with a frequency of 500 and 1000Hz as a gain of 750Hz, averaging the gains at 1000 and 2000Hz as a gain of 1500Hz, simultaneously carrying out 6dB modification according to whether the conductive deaf patient exists, finally calculating the gains in 60dB and 80dB input through a compression ratio (1.2 for the conductive deaf patient and 1.4 for the sensorineural deaf patient) and a compression corner point, and simultaneously reducing the gain at 250Hz by 6dB when 80dB is input, the gain is reduced by 3dB around 3000-4000 Hz, and MPO is estimated according to the input hearing threshold.
(5) And (3) correcting the fitting algorithm by using the formula model established in the step (4) in a weighting mode, wherein fig. 4 is a flow chart of weighted fitting between a formula fitting principle used in the invention and an intelligent algorithm of the BP artificial neural network, and the purpose of weighting is to correct the output result of the intelligent algorithm based on the BP artificial neural network so that the output gain of each channel is closer to the true level. The specific method comprises obtaining formula fitting result and intelligent fitting algorithm fitting result according to input, processing the generated result to generate 3X10 gain matrix (frequency is 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000, 8000Hz, input is gain of 40, 60, 80 dB), then weighting each gain in the matrix obtained by formula fitting and the matrix obtained by intelligent algorithm to obtain a total gain matrix, and finally limiting the output result according to MPO, wherein the weighting coefficient p is a matrix of 1X10 related to the network, namely, the reciprocal of the neural network is multiplied by a constant k, the k value is gradually increased along with the gradual maturity of the network until all the coefficients in p become 1, and at the moment, the sign network is mature, so that the intelligent fitting algorithm of the digital hearing aid based on the BP artificial neural network is mature and perfect.
The present invention is not limited to the above-described embodiments. The foregoing description of the specific embodiments is intended to describe and illustrate the technical solutions of the present invention, and the above specific embodiments are merely illustrative and not restrictive. Those skilled in the art can make many changes and modifications to the invention without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (3)
1. A digital hearing aid intelligent fitting method based on a BP artificial neural network is characterized in that the BP artificial neural network is trained by using the existing audiogram and spectral gain response as training data, and a new patient is estimated and predicted through the trained network, and the method specifically comprises the following steps:
(1) constructing a BP artificial neural network, which comprises an input layer, a hidden layer and an output layer, wherein the node numbers of the input layer, the hidden layer and the output layer are respectively 10, 20 and 30, and the BP artificial neural network is divided into 10 channels according to a frequency spectrum, namely, the frequencies of the channels are 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000 and 8000Hz, and the target is gain, compression ratio and compression inflection point of 40 dB; wherein the input layer comprises 10 nodes of hearing threshold and gender and experience with frequencies at 250, 500, 1000, 2000, 3000, 4000, 6000, 8000 Hz; the output layer includes 30 nodes targeted for 40dB gain, compression ratio and compression knee at frequencies of 250, 500, 750, 1000, 1500, 2000, 3000, 4000, 6000 and 8000 Hz;
(2) optimizing the initial weight and the initial threshold of the BP artificial neural network established in the step (1) by using a genetic algorithm;
(3) training the optimized BP artificial neural network in the step (2), wherein the training data adopt the cases of real patients, and the BP artificial neural network is continuously trained to gradually mature, so that a relatively mature digital hearing aid fitting algorithm based on the BP artificial neural network is finally obtained;
(4) building a formula model for optimizing the gain output obtained by the fitting algorithm in the step (3);
(5) and (4) correcting the fitting algorithm in a weighting mode by using the formula model established in the step (4) to obtain gain output, wherein the weighting coefficient is gradually close to 1 along with the continuous increase of subsequent training data, and finally obtaining the mature and perfect digital hearing aid intelligent fitting algorithm based on the BP artificial neural network.
2. The intelligent fitting method for digital hearing aids based on BP artificial neural network as claimed in claim 1, wherein the BP artificial neural network parameters in step (1) include weight W between input layer and hidden layerijAnd the weight W between the hidden layer and the output layerjkAnd also includes the thresholds of the hidden layer and the output layer.
3. The intelligent fitting method for digital hearing aids based on the BP artificial neural network as claimed in claim 1, wherein the optimization process in step (2) is as follows:
a. setting the population scale and the iteration times of a genetic algorithm;
b. performing GA coding on the initial weight and the threshold of the BP artificial neural network, and obtaining the fitness of each individual through the audiogram and the frequency spectrum gain response of a patient;
c. and finally, calculating the population fitness of the initial weight and the threshold through selection operation, cross operation and mutation operation of a genetic algorithm, and finally optimizing the network threshold and the weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611087426.0A CN106714062B (en) | 2016-11-30 | 2016-11-30 | Digital hearing aid intelligent fitting method based on BP artificial neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611087426.0A CN106714062B (en) | 2016-11-30 | 2016-11-30 | Digital hearing aid intelligent fitting method based on BP artificial neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106714062A CN106714062A (en) | 2017-05-24 |
| CN106714062B true CN106714062B (en) | 2020-02-18 |
Family
ID=58935394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611087426.0A Active CN106714062B (en) | 2016-11-30 | 2016-11-30 | Digital hearing aid intelligent fitting method based on BP artificial neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106714062B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102018202429B3 (en) * | 2018-02-16 | 2019-06-06 | Sivantos Pte. Ltd. | Method for adapting parameters of a hearing system |
| CN108703761B (en) * | 2018-06-11 | 2021-01-22 | 佛山博智医疗科技有限公司 | Method for testing hearing recognition sensitivity |
| CN109147808B (en) * | 2018-07-13 | 2022-10-21 | 南京工程学院 | Speech enhancement hearing aid method |
| CN109151692B (en) * | 2018-07-13 | 2020-09-01 | 南京工程学院 | Hearing aid self-checking and matching method based on deep learning network |
| CN109714692A (en) * | 2018-12-26 | 2019-05-03 | 天津大学 | Noise reduction method based on personal data and artificial neural network |
| CN110473567B (en) * | 2019-09-06 | 2021-09-14 | 上海又为智能科技有限公司 | Audio processing method and device based on deep neural network and storage medium |
| CN111491245B (en) * | 2020-03-13 | 2022-03-04 | 天津大学 | Digital hearing aid sound field identification algorithm based on cyclic neural network and implementation method |
| CN111818436B (en) * | 2020-07-14 | 2021-09-28 | 无锡清耳话声科技有限公司 | Real ear analysis test system based on machine learning |
| CN112383870B (en) * | 2020-10-29 | 2022-03-18 | 惠州市锦好医疗科技股份有限公司 | Adaptive hearing parameter fitting method and device |
| CN112887885B (en) * | 2021-01-12 | 2021-12-21 | 天津大学 | Hearing aid fault automatic detection system and hearing aid system |
| CN116614757B (en) * | 2023-07-18 | 2023-09-26 | 江西斐耳科技有限公司 | Hearing aid fitting method and system based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1523219B1 (en) * | 2003-10-10 | 2008-08-20 | Siemens Audiologische Technik GmbH | Method for training and operating a hearing aid and corresponding hearing aid |
| CN104053112A (en) * | 2014-06-26 | 2014-09-17 | 南京工程学院 | Hearing aid self-fitting method |
| CN105611477A (en) * | 2015-12-27 | 2016-05-25 | 北京工业大学 | Depth and breadth neural network combined speech enhancement algorithm of digital hearing aid |
| CN105722001A (en) * | 2014-12-23 | 2016-06-29 | 奥迪康有限公司 | Hearing Device Adapted For Estimating A Current Real Ear To Coupler Difference |
-
2016
- 2016-11-30 CN CN201611087426.0A patent/CN106714062B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1523219B1 (en) * | 2003-10-10 | 2008-08-20 | Siemens Audiologische Technik GmbH | Method for training and operating a hearing aid and corresponding hearing aid |
| CN104053112A (en) * | 2014-06-26 | 2014-09-17 | 南京工程学院 | Hearing aid self-fitting method |
| CN105722001A (en) * | 2014-12-23 | 2016-06-29 | 奥迪康有限公司 | Hearing Device Adapted For Estimating A Current Real Ear To Coupler Difference |
| CN105611477A (en) * | 2015-12-27 | 2016-05-25 | 北京工业大学 | Depth and breadth neural network combined speech enhancement algorithm of digital hearing aid |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106714062A (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106714062B (en) | Digital hearing aid intelligent fitting method based on BP artificial neural network | |
| US5729658A (en) | Evaluating intelligibility of speech reproduction and transmission across multiple listening conditions | |
| CN103079160B (en) | One is automatically tested and is joined digital hearing-aid and method thereof | |
| CN105741849A (en) | Voice enhancement method for fusing phase estimation and human ear hearing characteristics in digital hearing aid | |
| CN102612354B (en) | Determine the stimulus levels parameter in implant allotment | |
| CN105407963B (en) | Optimization passage configuration based on space profiles | |
| CN105706466B (en) | Hearing aid with probabilistic hearing compensation | |
| CN111257934B (en) | Seismic oscillation peak acceleration prediction method based on second-order neuron deep neural network | |
| CN109151692B (en) | Hearing aid self-checking and matching method based on deep learning network | |
| CN102860046A (en) | A hearing aid and a method for alleviating tinnitus | |
| CN109147808B (en) | Speech enhancement hearing aid method | |
| CN112315462B (en) | Multifunctional hearing evaluation earphone and evaluation method thereof | |
| EP2811904B1 (en) | Evaluation of sound quality and speech intelligibility from neurograms | |
| CN111968677B (en) | Voice quality self-evaluation method for fitting-free hearing aid | |
| CN110513835B (en) | Control method and device for improving comfort of air conditioner and air conditioner | |
| CN110866640A (en) | Power load prediction method based on deep neural network | |
| CN106558308A (en) | A kind of internet audio quality of data auto-scoring system and method | |
| Miller-Hansen et al. | Evaluating the benefit of speech recoding hearing aids in children | |
| Ching et al. | Comparing NAL-NL1 and DSL v5 in hearing aids fit to children with severe or profound hearing loss: Goodness of fit-to-targets, impacts on predicted loudness and speech intelligibility | |
| CN107239255A (en) | Volume automatic regulating method and system | |
| CN111414552B (en) | Method for estimating propagation range of online social network rumors | |
| CN109309536B (en) | Method for reducing approximation complexity of Nakagami inverse CDF function | |
| CN108197748B (en) | People flow prediction method based on thought evolution algorithm | |
| CN110909202A (en) | Audio value evaluation method and device and readable storage medium | |
| CN114141266A (en) | Speech enhancement method for estimating prior signal-to-noise ratio based on PESQ driven reinforcement learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221129 Address after: 518172 516, building 4, Qidi Xiexin Science Park, Qingchun Road, Longcheng street, Longgang District, Shenzhen, Guangdong Province Patentee after: SHENZHEN EARTECH Co.,Ltd. Address before: 300072 Tianjin City, Nankai District Wei Jin Road No. 92 Patentee before: Tianjin University |
|
| TR01 | Transfer of patent right |