CN108711419B - Environmental sound sensing method and system for cochlear implant - Google Patents

Environmental sound sensing method and system for cochlear implant Download PDF

Info

Publication number
CN108711419B
CN108711419B CN201810856692.8A CN201810856692A CN108711419B CN 108711419 B CN108711419 B CN 108711419B CN 201810856692 A CN201810856692 A CN 201810856692A CN 108711419 B CN108711419 B CN 108711419B
Authority
CN
China
Prior art keywords
module
sound
neural network
characteristic values
group
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
Application number
CN201810856692.8A
Other languages
Chinese (zh)
Other versions
CN108711419A (en
Inventor
张晓薇
韩彦
孙晓安
黄穗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Nurotron Nerve Electronic Technology Co ltd
Original Assignee
Zhejiang Nurotron Nerve Electronic Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Nurotron Nerve Electronic Technology Co ltd filed Critical Zhejiang Nurotron Nerve Electronic Technology Co ltd
Priority to CN201810856692.8A priority Critical patent/CN108711419B/en
Publication of CN108711419A publication Critical patent/CN108711419A/en
Priority to PCT/CN2019/096648 priority patent/WO2020024807A1/en
Priority to ES202190003A priority patent/ES2849124B2/en
Application granted granted Critical
Publication of CN108711419B publication Critical patent/CN108711419B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • 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
    • G10L15/00—Speech recognition
    • G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
    • G10L15/063—Training
    • 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
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • 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
    • G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
    • G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
    • G10L21/0208—Noise filtering
    • 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
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Neurosurgery (AREA)
  • Otolaryngology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Circuit For Audible Band Transducer (AREA)
  • Prostheses (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The invention discloses an environment sound sensing method and system of a cochlear implant, wherein the method comprises the following steps: the sound collection module collects environmental sound in real time by adopting a microphone and outputs a section of collected discrete sound signal to the sound characteristic extraction module; the sound characteristic extraction module processes the sound signals sent by the sound acquisition module, extracts a group of characteristic values representing the characteristics of the sound signals and outputs the characteristic values to the neural network classification module; the neural network classification module receives a group of characteristic values extracted by the sound characteristic extraction module, classifies the group of characteristic values through the trained neural network, and then outputs the classification result to the comprehensive decision module; after receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes and gives judgment of the current scene, and outputs the judgment result to the voice processing selection module; and the voice processing selection module selects an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.

Description

Environmental sound sensing method and system for cochlear implant
Technical Field
The invention belongs to the field of signal processing, and relates to an environment sound sensing method and system for a cochlear implant.
Background
The artificial cochlea is the only medical instrument which can effectively recover the hearing of the patients with severe or extremely severe deafness in the current market. The general working principle of the cochlear implant is that a sound signal collected by a microphone is converted into a stimulation code through a signal processing unit and is sent to an implant, and the implant stimulates an auditory nerve through a microelectrode according to the stimulation code, so that an implant recovers the hearing. Like other hearing aids, such systems lack an important function of the hearing system of a regular person, i.e. the target signal can be distinguished and extracted in a complex sound scene. Such as listening to words spoken by chat objects in a group of people or in a relatively noisy environment. The common solution is to reduce the influence of noise on the hearing through a certain denoising algorithm. However, the denoising algorithm and the parameter configuration of the algorithm are different under different environments (such as pure voice, voice to be denoised or noise environments).
In order to solve the problems, an ambient sound perception algorithm is introduced, and the system can pertinently start the noise reduction algorithm and configure related parameters according to the judgment result of the ambient sound perception algorithm. In early cochlear implant or hearing aid systems, hidden markov models were used as classifiers for the ambient sound perception algorithm. The model is relatively simple, the theory is mature earlier, the requirement on training data is not high, and a certain correct recognition rate is also kept. And the operation amount is low, and the method can be suitable for the device with limited operation capability, such as the cochlear implant. With continuous innovation in the fields of pattern recognition, machine learning and the like and continuous progress in computational algorithm in recent years, more classification algorithms (support vector machines, neural networks and the like) are more prominent in the field of environmental sound perception, and the classification accuracy is higher. And classifiers such as support vector machines, neural networks, and the like place the center of gravity on the distinguishing categories without providing prior probability of category transformation, relative to the hidden Markov model. That is, only data of different ambient sounds need to be analyzed, without considering what the probability of converting one ambient sound to another. It is very difficult to obtain such transition probabilities and the analysis from the data is not accurate enough. However, the neural network varies greatly, and the network structure can be combined in many ways according to the number of input characteristic values, the number of hidden layers and the number of nodes in each layer. In addition, the classification accuracy of the neural network is generally proportional to the scale of the neural network, and thus the required computation amount is relatively large.
Disclosure of Invention
In order to solve the problems, the invention provides an environmental sound sensing method of an artificial cochlea aiming at the defects of the existing sound sensing processing, a neural network is adopted to classify the environmental sound, the input characteristic value and the network structure of the neural network are optimized on an artificial cochlea system, and the calculation amount is minimized under the condition of meeting a certain classification accuracy.
In order to achieve the above object, the technical solution of the present invention is an ambient sound sensing method for a cochlear implant, including the steps of:
the sound collection module collects environmental sound in real time by adopting a microphone and then outputs a section of collected discrete sound signal to the sound feature extraction module;
the sound characteristic extraction module processes the sound signals sent by the sound acquisition module, extracts a group of characteristic values representing the characteristics of the sound signals and outputs the characteristic values to the neural network classification module;
after receiving a group of characteristic values extracted by the sound characteristic extraction module, the neural network classification module classifies the group of characteristic values through the trained neural network and then outputs the classification result to the comprehensive decision-making module;
after receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes and gives judgment of the current scene, and outputs the judgment result to the voice processing selection module;
and the voice processing selection module selects an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.
Preferably, the microphones collect ambient sound in real time using an omni-directional microphone or a microphone array.
Preferably, the sampling rate of the sound collection module is 16K.
Preferably, the number of feature values extracted from the set of feature values representing the characteristics of the sound signal is 8.
Preferably, the neural network classification module employs a deep neural network or a delayed neural network comprising two hidden layers, 15 neurons per layer.
Preferably, 8 of said characteristic values are selected from 60 characteristic values.
Preferably, the feature value screening adopts a method of comprehensively analyzing statistics of feature values and a gaussian mixture model, an average influence value algorithm, a sequence forward selection algorithm and classifier training result evaluation.
Preferably, the calculation amount of the characteristic value and the calculation amount of the neural network do not exceed 20% of the operation capacity of the artificial cochlear speech processor.
Based on the above purpose, the invention also provides an environmental sound perception system of the cochlear implant, which comprises a sound collection module, a sound feature extraction module, a neural network classification module, a comprehensive decision module and a voice processing selection module which are connected in sequence, wherein,
the sound collection module is used for collecting environmental sound in real time by adopting a microphone and then outputting a section of collected discrete sound signal to the sound feature extraction module;
the sound feature extraction module is used for processing the sound signals sent by the sound acquisition module, extracting a group of feature values representing the characteristics of the sound signals and outputting the feature values to the neural network classification module;
the neural network classification module is used for classifying a group of characteristic values extracted by the sound characteristic extraction module through the trained neural network after receiving the group of characteristic values, and then outputting the classification result to the comprehensive decision module;
the comprehensive decision-making module is used for comprehensively analyzing and giving judgment of the current scene after receiving the classification result of the neural network classification module and outputting the judgment result to the voice processing selection module;
and the voice processing selection module is used for selecting an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.
Drawings
Fig. 1 is a flowchart illustrating steps of a cochlear implant ambient sound sensing method according to an embodiment of the present invention;
fig. 2 is a block diagram of an ambient sound sensing system of a cochlear implant according to an embodiment of the present invention;
fig. 3 is a detailed schematic diagram of a neural network classification module of the cochlear implant environmental sound sensing method and system according to the embodiment of the present invention;
fig. 4 is a comparison graph of the operation amount and the accuracy of the network with different hidden layers and different neuron numbers according to the method for sensing the environmental sound of the cochlear implant of the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
On the contrary, the invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details.
Referring to fig. 1, a flow chart of steps of the method for sensing environmental sound of cochlear implant according to the technical solution of the embodiment of the present invention includes the following steps:
s10, the sound collection module collects the environment sound in real time by a microphone and then outputs a section of collected discrete sound signal to the sound feature extraction module;
s20, the sound feature extraction module processes the sound signal sent by the sound collection module, extracts a group of feature values representing the characteristics of the sound signal and outputs the feature values to the neural network classification module;
s30, after receiving a group of characteristic values extracted by the sound characteristic extraction module, the neural network classification module classifies the group of characteristic values through the trained neural network, and then outputs the classification result to the comprehensive decision module;
s40, after receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes and gives the judgment of the current scene, and outputs the judgment result to the voice processing selection module;
and S50, selecting the optimal voice processing program and the parameter configuration thereof by the voice processing selection module according to the judgment result of the comprehensive decision module on the current scene.
Referring to fig. 2, the system of the present invention includes a sound collection module 10, a sound feature extraction module 20, a neural network classification module 30, a comprehensive decision module 40, and a speech processing selection module 50, which are connected in sequence, wherein,
the sound collection module 10 is configured to collect environmental sound in real time by using a microphone, and then output a section of collected discrete sound signals to the sound feature extraction module 20;
the sound feature extraction module 20 is configured to process the sound signal sent by the sound acquisition module, extract a group of feature values representing characteristics of the sound signal, and output the feature values to the neural network classification module 30;
the neural network classification module 30 is configured to, after receiving a set of feature values extracted by the sound feature extraction module, classify the set of feature values through the trained neural network, and then output a classification result to the comprehensive decision module 40;
the comprehensive decision module 40 is configured to, after receiving the classification result of the neural network classification module, comprehensively analyze the classification result to give a judgment of the current scene, and output the judgment result to the voice processing selection module 50;
and the voice processing selection module 50 is used for selecting an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.
In a specific embodiment, in S10, the microphone collects the ambient sound in real time by using an omnidirectional microphone or a microphone array, and the sampling rate of the sound collection module 10 is 16K.
In S20, a group of feature values representing characteristics of the sound signal are extracted, and 8 feature values are extracted from 60 feature values. Before extracting the characteristic value, normalization processing is carried out, and the formula is as follows:
Figure BDA0001748712160000051
wherein x isnormTo normalize the result, XmaxFor the maximum value of the training sample, X, where the characteristic value is locatedminThe minimum value of the training sample where the characteristic value is located.
The neural network classification module in S30 adopts a deep neural network or a delayed neural network including two hidden layers, 15 neurons per layer. The neural network module is obtained by training a large number of data samples, taking 4 types of environmental sounds (pure voice, noisy voice, noise, music and silence) as an example, and the neural network model thereof is shown in fig. 3. The characteristic values are selected from 1, 2, 3, 4, 5 and 6, and six types are combined into a group. The training samples are extracted from a large number of collected audio files, and comprise 144000 groups of sample characteristic values in total, and each type of environmental sound comprises 36000 groups of characteristic values. To find a balance between the amount of computation and the accuracy, we tried 1 hidden layer and 2 hidden layer, each with different numbers of neurons, see fig. 4. As can be seen from the figure, the accuracy of the neural network of the two hidden layers is obviously higher than that of the neural network of the single hidden layer, and the optimal neuron number is 15.
The neural network decision formula in S40 is as follows:
Figure BDA0001748712160000061
wherein, XinputFor inputting a matrix of eigenvalues, W1、W2、W3For each layer of the trained neural network, B1、B2、B3For each layer of bias matrix of the trained neural network, activeFcn is an activation function, YoutThe results are calculated for the network.
To reduce the amount of computation, we will use the activation function activeFcn of the hidden layerHAnd an activation function activeFcn of the output layerOAre respectively defined as:
Figure BDA0001748712160000062
where x is the input to the activation function and i is the ambient sound category.
After receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes a series of factors, mainly including the recognition result of the neural network and the sound energy in a short period of time, gives the judgment of the current scene, and outputs the judgment result to the voice processing selection module.
And the voice processing selection module selects an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.
The characteristic value screening adopts a method of comprehensively analyzing the statistic value of the characteristic value, a Gaussian mixture model, an average influence value algorithm, a sequence forward selection algorithm and classifier training result evaluation.
The calculated amount of the characteristic value and the calculated amount of the neural network do not exceed 20% of the operation capacity of the artificial cochlea speech processor.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (6)

1. An ambient sound sensing method of a cochlear implant, comprising the steps of:
the sound collection module collects environmental sound in real time by adopting a microphone and then outputs a section of collected discrete sound signal to the sound feature extraction module;
the sound characteristic extraction module processes the sound signals sent by the sound acquisition module, extracts a group of characteristic values representing the characteristics of the sound signals and outputs the characteristic values to the neural network classification module;
after receiving a group of characteristic values extracted by the sound characteristic extraction module, the neural network classification module classifies the group of characteristic values through the trained neural network and then outputs the classification result to the comprehensive decision-making module;
after receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes and gives judgment of the current scene, and outputs the judgment result to the voice processing selection module;
the voice processing selection module selects an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene;
the sound characteristic extraction module processes the sound signals sent by the sound acquisition module, extracts a group of characteristic values representing the characteristics of the sound signals, outputs the characteristic values to the neural network classification module, extracts 8 characteristic values for extracting the group of characteristic values representing the characteristics of the sound signals, screens the 8 characteristic values from 60 characteristic values, and performs normalization processing before extracting the characteristic values, wherein the formula is as follows:
Figure FDA0002425958950000011
wherein x isnormTo normalize the result, XmaxFor the maximum value of the training sample, X, where the characteristic value is locatedminThe minimum value of the training sample where the characteristic value is located;
the neural network classification module classifies a group of characteristic values extracted by the sound characteristic extraction module through a trained neural network after receiving the group of characteristic values, then outputs the classification result to the comprehensive decision module, the neural network classification module adopts a deep neural network or a delayed neural network containing two hidden layers and 15 neurons in each layer, the neural network module is obtained through training of a large number of data samples to distinguish 4 types of environmental sounds including pure voice, noisy voice, noise, music and silence, the characteristic values are selected from 1, 2, 3, 4, 5 and 6 to form a group, the training samples are extracted from a large number of collected audio files and contain 144000 groups of sample characteristic values, and each type of environmental sound contains 36000 groups of characteristic values;
after receiving the classification result of the neural network classification module, the comprehensive decision module comprehensively analyzes and gives the judgment of the current scene, and outputs the judgment result to the voice processing selection module, wherein the judgment formula for the neural network is as follows:
Figure FDA0002425958950000021
wherein, XinputFor inputting a matrix of eigenvalues, W1、W2、W3For each layer of the trained neural network, B1、B2、B3For each layer of bias matrix of the trained neural network, activeFcn is an activation function, YoutThe results are calculated for the network.
2. The method of claim 1, wherein the real-time collection of ambient sound by the microphones uses an omni-directional microphone or a microphone array.
3. The method of claim 1, wherein the sound collection module has a sampling rate of 16K.
4. The method of claim 1, wherein the eigenvalue screening adopts a method of comprehensive analysis of statistics of eigenvalues and gaussian mixture model, mean influence value algorithm, sequence forward selection algorithm, and classifier training result evaluation.
5. The method of claim 1, wherein the eigenvalue and neural network are not more than 20% of the computational power of the cochlear prosthesis speech processor.
6. The system adopting the method of one of claims 1 to 5, comprising a sound collection module, a sound feature extraction module, a neural network classification module, a comprehensive decision module and a voice processing selection module which are connected in sequence, wherein,
the sound collection module is used for collecting environmental sound in real time by adopting a microphone and then outputting a section of collected discrete sound signal to the sound feature extraction module;
the sound feature extraction module is used for processing the sound signals sent by the sound acquisition module, extracting a group of feature values representing the characteristics of the sound signals and outputting the feature values to the neural network classification module;
the neural network classification module is used for classifying a group of characteristic values extracted by the sound characteristic extraction module through the trained neural network after receiving the group of characteristic values, and then outputting the classification result to the comprehensive decision module;
the comprehensive decision-making module is used for comprehensively analyzing and giving judgment of the current scene after receiving the classification result of the neural network classification module and outputting the judgment result to the voice processing selection module;
and the voice processing selection module is used for selecting an optimal voice processing program and parameter configuration thereof according to the judgment result of the comprehensive decision module on the current scene.
CN201810856692.8A 2018-07-31 2018-07-31 Environmental sound sensing method and system for cochlear implant Active CN108711419B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201810856692.8A CN108711419B (en) 2018-07-31 2018-07-31 Environmental sound sensing method and system for cochlear implant
PCT/CN2019/096648 WO2020024807A1 (en) 2018-07-31 2019-07-19 Artificial cochlea ambient sound sensing method and system
ES202190003A ES2849124B2 (en) 2018-07-31 2019-07-19 ENVIRONMENTAL SOUND DETECTION METHOD AND SYSTEM FOR A COCHLEAR IMPLANT

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810856692.8A CN108711419B (en) 2018-07-31 2018-07-31 Environmental sound sensing method and system for cochlear implant

Publications (2)

Publication Number Publication Date
CN108711419A CN108711419A (en) 2018-10-26
CN108711419B true CN108711419B (en) 2020-07-31

Family

ID=63874461

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810856692.8A Active CN108711419B (en) 2018-07-31 2018-07-31 Environmental sound sensing method and system for cochlear implant

Country Status (3)

Country Link
CN (1) CN108711419B (en)
ES (1) ES2849124B2 (en)
WO (1) WO2020024807A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108711419B (en) * 2018-07-31 2020-07-31 浙江诺尔康神经电子科技股份有限公司 Environmental sound sensing method and system for cochlear implant
CN109448703B (en) * 2018-11-14 2021-05-11 山东师范大学 Audio scene recognition method and system combining deep neural network and topic model
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
CN112151056B (en) * 2020-09-27 2023-08-04 浙江诺尔康神经电子科技股份有限公司 Intelligent cochlea sound processing system and method with customization function

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103456301A (en) * 2012-05-28 2013-12-18 中兴通讯股份有限公司 Ambient sound based scene recognition method and device and mobile terminal
CN105845127A (en) * 2015-01-13 2016-08-10 阿里巴巴集团控股有限公司 Voice recognition method and system
CN107103901A (en) * 2017-04-03 2017-08-29 浙江诺尔康神经电子科技股份有限公司 Artificial cochlea's sound scenery identifying system and method

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1879449B (en) * 2003-11-24 2011-09-28 唯听助听器公司 Hearing aid and a method of noise reduction
DK2064918T3 (en) * 2006-09-05 2015-01-26 Gn Resound As A hearing-aid with histogram based lydmiljøklassifikation
CN105611477B (en) * 2015-12-27 2018-06-01 北京工业大学 The voice enhancement algorithm that depth and range neutral net are combined in digital deaf-aid
CN108172238B (en) * 2018-01-06 2021-08-13 广州音书科技有限公司 Speech enhancement algorithm based on multiple convolutional neural networks in speech recognition system
CN108231067A (en) * 2018-01-13 2018-06-29 福州大学 Sound scenery recognition methods based on convolutional neural networks and random forest classification
CN108711419B (en) * 2018-07-31 2020-07-31 浙江诺尔康神经电子科技股份有限公司 Environmental sound sensing method and system for cochlear implant

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103456301A (en) * 2012-05-28 2013-12-18 中兴通讯股份有限公司 Ambient sound based scene recognition method and device and mobile terminal
CN105845127A (en) * 2015-01-13 2016-08-10 阿里巴巴集团控股有限公司 Voice recognition method and system
CN107103901A (en) * 2017-04-03 2017-08-29 浙江诺尔康神经电子科技股份有限公司 Artificial cochlea's sound scenery identifying system and method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users;Tobias Goehring等;《Hearing Research》;20161130(第344期);第183-194页 *
自然与城市声特征及自动识别;杨铭;《声景观 新建筑》;20141231(第5期);第32-35页 *

Also Published As

Publication number Publication date
CN108711419A (en) 2018-10-26
ES2849124B2 (en) 2022-11-16
ES2849124A1 (en) 2021-08-13
WO2020024807A1 (en) 2020-02-06

Similar Documents

Publication Publication Date Title
CN108711419B (en) Environmental sound sensing method and system for cochlear implant
Agrawal et al. Novel TEO-based Gammatone features for environmental sound classification
CN102270451B (en) Method and system for identifying speaker
CN108766459B (en) Target speaker estimation method and system in multi-user voice mixing
CN108305615A (en) A kind of object identifying method and its equipment, storage medium, terminal
CN110197665B (en) Voice separation and tracking method for public security criminal investigation monitoring
CN107103901B (en) Artificial cochlea sound scene recognition system and method
CN112151056B (en) Intelligent cochlea sound processing system and method with customization function
CN111951824A (en) Detection method for distinguishing depression based on sound
CN110428843A (en) A kind of voice gender identification deep learning method
AU2020293557A1 (en) A neural network model for cochlear mechanics and processing
Hüwel et al. Hearing aid research data set for acoustic environment recognition
CN113850013B (en) Ship radiation noise classification method
CN112466284B (en) Mask voice identification method
Peng et al. An acoustic signal processing system for identification of queen-less beehives
CN116092512A (en) Small sample voice separation method based on data generation
CN115862639A (en) Artificial intelligence voice analysis method based on K-means clustering analysis
Kothapally et al. Speech Detection and Enhancement Using Single Microphone for Distant Speech Applications in Reverberant Environments.
CN114938487A (en) Hearing aid self-fitting method based on sound scene discrimination
CN113887339A (en) Silent voice recognition system and method fusing surface electromyogram signal and lip image
CN111444381B (en) Deep learning corpus-based classification method and storage device
CN111144482B (en) Scene matching method and device for digital hearing aid and computer equipment
CN113488071A (en) Pig cough recognition method, device, equipment and readable storage medium
Shen et al. Home activity monitoring based on gated convolutional neural networks and system fusion
CN113870901B (en) SVM-KNN-based voice emotion recognition method

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