Artificial cochlea signal processing method and device thereof and computer readable storage medium

A signal processing device and cochlear implant technology, applied in the field of signal processing, can solve the problems of inability to adapt well, limited noise reduction processing effect, and high power consumption

Active Publication Date: 2020-01-14
SHENZHEN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the embodiments of the present invention is to provide a cochlear implant signal processing method, device, and computer-readable storage medium, which can at least solve the problems of low processing efficiency, high power consumption, and low noise reduction processing effect of the noise reduction algorithm adopted in the related art. Relatively limited, and problems that cannot be well adapted to CI processing strategies

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Artificial cochlea signal processing method and device thereof and computer readable storage medium
  • Artificial cochlea signal processing method and device thereof and computer readable storage medium
  • Artificial cochlea signal processing method and device thereof and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0027] In order to solve the technical problems of low processing efficiency, high power consumption, and relatively limited noise reduction processing effect of the noise reduction algorithm adopted in the related art, as well as the technical problems that it cannot be well adapted to the CI processing strategy, this embodiment proposes a cochlear implant Signal processing methods, applied to cochlear implants such as figure 1 Shown is a schematic flow chart of the cochlear implant signal processing method provided in this embodiment. The cochlear implant signal processing method proposed in this embodiment includes the following steps:

[0028] Step 101. Obtain a training speech signal, and input the training speech signal to an envelope extraction network after preprocessing, and train the envelope extraction network.

[0029] Specifically, the envelope extraction network in this embodiment includes a first deep neural network (DNN1), a second deep neural network (DNN2) an...

no. 2 example

[0056] In order to solve the technical problems of low processing efficiency, high power consumption, limited noise reduction processing effect, and inability to be well adapted to CI processing strategies of the noise reduction algorithm adopted in the related art, this embodiment shows a cochlear implant Signal processing device, applied to cochlear implants, for details, please refer to Figure 4 , the cochlear implant signal processing device of this embodiment includes:

[0057] The training module 401 is used to obtain the training voice signal, and input the training voice signal to the envelope extraction network after preprocessing, and train the envelope extraction network; wherein, the envelope extraction network includes the first deep neural network connected sequentially. network, the second deep neural network and the third deep neural network, the first deep neural network is used to extract high-dimensional features from the input features, the second deep neu...

no. 3 example

[0068] This embodiment provides a cochlear implant, see Figure 5 As shown, it includes a processor 501, a memory 502 and a communication bus 503, wherein: the communication bus 503 is used to realize connection and communication between the processor 501 and the memory 502; the processor 501 is used to execute one or more programs stored in the memory 502 A computer program to realize at least one step in the cochlear implant signal processing method in the first embodiment above.

[0069] The present embodiment also provides a computer-readable storage medium, which includes information implemented in any method or technology for storing information, such as computer-readable instructions, data structures, computer program modules, or other data. volatile or nonvolatile, removable or non-removable media. Computer-readable storage media include but are not limited to RAM (Random Access Memory, random access memory), ROM (Read-Only Memory, read-only memory), EEPROM (Electrica...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to an artificial cochlea signal processing method and a device thereof and a computer readable storage medium. According to the invention, firstly, a training voice signal is acquired, the training voice signal is input into an envelope extraction network for network training after being preprocessed, and the envelope extraction network comprises three deep neural networks which are connected in sequence; preprocessing is carried out the acquired real-time voice signals, the preprocessed real-time voice signals are input into the trained envelope extraction network, and channel envelopes of which the number corresponds to the number of in-vivo implanted electrodes are extracted; and finally, nonlinear compression, channel selection, electrode mapping and pulse modulation are sequentially carried out on the extracted channel envelope, and a target number of electrode stimulation signals can be output to a corresponding number of in-vivo implanted electrodes. Through the lightweight envelope extraction network with relatively low calculation complexity provided by the invention, the power consumption is effectively reduced, the processing efficiency and the noise reduction processing effect are improved, and seamless fusion of CI signal processing and noise reduction is ensured.

Description

technical field [0001] The present invention relates to the technical field of signal processing, in particular to a cochlear implant signal processing method, device and computer-readable storage medium. Background technique [0002] Cochlear implant (CI, Cochlear Implant) is a kind of hearing bionic device, which is mainly used to provide speech perception for deaf patients with severe hearing peripheral damage (such as inner ear hair cell necrosis). Currently, state-of-the-art CI devices can enable CI implanters to achieve speech perception equivalent to normal people in a quiet acoustic environment. However, the background noise in real life (such as environmental noise or the situation of many people talking) will seriously affect the speech perception experience of CI implanters. [0003] In recent years, academia and industry have proposed many signal processing systems that combine noise reduction algorithms with traditional CI signal processing strategies to improv...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): A61N1/36G10L25/30G10L25/03G10L25/48G10L21/0208G06N3/04G06N3/08
CPCA61N1/36038G10L25/30G10L25/03G10L25/48G10L21/0208G06N3/084G06N3/044G06N3/045Y02D30/70
Inventor 郑能恒史裕鹏康迂勇张伟
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products