The application of bionic wavelet transform to speech signal processing in cochlear implants using neural network simulations

Jun Yao, Yuan Ting Zhang*

*Corresponding author for this work

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

Cochlear implants (CIs) restore partial hearing to people with severe to profound sensorineural deafness; but there is still a marked performance gap in speech recognition between those who have received cochlear implant and people with a normal hearing capability. One of the factors that may lead to this performance gap is the inadequate signal processing method used in CIs. This paper investigates the application of an improved signal-processing method called bionic wavelet transform (BWT). This method is based upon the auditory model and allows for signal processing. Comparing the neural network simulations on the same experimental materials processed by wavelet transform (WT) and BWT, the application of BWT to speech signal processing in CI has a number of advantages, including: improvement in recognition rates for both consonants and vowels, reduction of the number of required channels, reduction of the average stimulation duration for words, and high noise tolerance. Consonant recognition results in 15 normal hearing subjects show that the BWT produces significantly better performance than the WT (t = -4.36276, p = 0.00065). The BWT has great potential to reduce the performance gap between CI listeners and people with a normal hearing capability in the future.

Original languageEnglish (US)
Pages (from-to)1299-1309
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Volume49
Issue number11
DOIs
StatePublished - Nov 1 2002

Fingerprint

Cochlear implants
Bionics
Wavelet transforms
Signal processing
Neural networks
Audition
Speech recognition
Acoustic noise

Keywords

  • Bionic wavelet transform
  • Cochlear implants
  • Neural networks
  • Speech signal processing

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

@article{d99c95b8e768484694fde13c03a13df5,
title = "The application of bionic wavelet transform to speech signal processing in cochlear implants using neural network simulations",
abstract = "Cochlear implants (CIs) restore partial hearing to people with severe to profound sensorineural deafness; but there is still a marked performance gap in speech recognition between those who have received cochlear implant and people with a normal hearing capability. One of the factors that may lead to this performance gap is the inadequate signal processing method used in CIs. This paper investigates the application of an improved signal-processing method called bionic wavelet transform (BWT). This method is based upon the auditory model and allows for signal processing. Comparing the neural network simulations on the same experimental materials processed by wavelet transform (WT) and BWT, the application of BWT to speech signal processing in CI has a number of advantages, including: improvement in recognition rates for both consonants and vowels, reduction of the number of required channels, reduction of the average stimulation duration for words, and high noise tolerance. Consonant recognition results in 15 normal hearing subjects show that the BWT produces significantly better performance than the WT (t = -4.36276, p = 0.00065). The BWT has great potential to reduce the performance gap between CI listeners and people with a normal hearing capability in the future.",
keywords = "Bionic wavelet transform, Cochlear implants, Neural networks, Speech signal processing",
author = "Jun Yao and Zhang, {Yuan Ting}",
year = "2002",
month = "11",
day = "1",
doi = "10.1109/TBME.2002.804590",
language = "English (US)",
volume = "49",
pages = "1299--1309",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "11",

}

The application of bionic wavelet transform to speech signal processing in cochlear implants using neural network simulations. / Yao, Jun; Zhang, Yuan Ting.

In: IEEE Transactions on Biomedical Engineering, Vol. 49, No. 11, 01.11.2002, p. 1299-1309.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The application of bionic wavelet transform to speech signal processing in cochlear implants using neural network simulations

AU - Yao, Jun

AU - Zhang, Yuan Ting

PY - 2002/11/1

Y1 - 2002/11/1

N2 - Cochlear implants (CIs) restore partial hearing to people with severe to profound sensorineural deafness; but there is still a marked performance gap in speech recognition between those who have received cochlear implant and people with a normal hearing capability. One of the factors that may lead to this performance gap is the inadequate signal processing method used in CIs. This paper investigates the application of an improved signal-processing method called bionic wavelet transform (BWT). This method is based upon the auditory model and allows for signal processing. Comparing the neural network simulations on the same experimental materials processed by wavelet transform (WT) and BWT, the application of BWT to speech signal processing in CI has a number of advantages, including: improvement in recognition rates for both consonants and vowels, reduction of the number of required channels, reduction of the average stimulation duration for words, and high noise tolerance. Consonant recognition results in 15 normal hearing subjects show that the BWT produces significantly better performance than the WT (t = -4.36276, p = 0.00065). The BWT has great potential to reduce the performance gap between CI listeners and people with a normal hearing capability in the future.

AB - Cochlear implants (CIs) restore partial hearing to people with severe to profound sensorineural deafness; but there is still a marked performance gap in speech recognition between those who have received cochlear implant and people with a normal hearing capability. One of the factors that may lead to this performance gap is the inadequate signal processing method used in CIs. This paper investigates the application of an improved signal-processing method called bionic wavelet transform (BWT). This method is based upon the auditory model and allows for signal processing. Comparing the neural network simulations on the same experimental materials processed by wavelet transform (WT) and BWT, the application of BWT to speech signal processing in CI has a number of advantages, including: improvement in recognition rates for both consonants and vowels, reduction of the number of required channels, reduction of the average stimulation duration for words, and high noise tolerance. Consonant recognition results in 15 normal hearing subjects show that the BWT produces significantly better performance than the WT (t = -4.36276, p = 0.00065). The BWT has great potential to reduce the performance gap between CI listeners and people with a normal hearing capability in the future.

KW - Bionic wavelet transform

KW - Cochlear implants

KW - Neural networks

KW - Speech signal processing

UR - http://www.scopus.com/inward/record.url?scp=0036845116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036845116&partnerID=8YFLogxK

U2 - 10.1109/TBME.2002.804590

DO - 10.1109/TBME.2002.804590

M3 - Article

VL - 49

SP - 1299

EP - 1309

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 11

ER -