Channel-weighting method for speech recognition using wavelet decompositions

Jyh Shing Shyuu, Jhing Fa Wang, Chung-Hsien Wu

研究成果: Paper

2 引文 (Scopus)

摘要

A decomposition of signal into a set of frequency channels of equal bandwidth on a logarithmic scale, i.e., an analysis of the signal using constant Q filters, using wavelet and multiresolution analysis is used in this paper to derive cepstrum features of different spatial frequency bands. Based on the decompositions, each channel is modeled as a Bayesian subnetwork and each subnetwork is weighted by a weighting algorithm. The distortions for speech recognition between a reference model and the input vectors are then computed by summing the weighted scores of all decomposed channels. The experimental results show that the recognition rate of this method is superior to those non-weighting methods.

原文English
頁面519-523
頁數5
出版狀態Published - 1994 十二月 1
事件Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems - Taipei, Taiwan
持續時間: 1994 十二月 51994 十二月 8

Other

OtherProceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems
城市Taipei, Taiwan
期間94-12-0594-12-08

指紋

Multiresolution analysis
Wavelet decomposition
Wavelet analysis
Speech recognition
Frequency bands
Bandwidth

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

引用此文

Shyuu, J. S., Wang, J. F., & Wu, C-H. (1994). Channel-weighting method for speech recognition using wavelet decompositions. 519-523. 論文發表於 Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, .
Shyuu, Jyh Shing ; Wang, Jhing Fa ; Wu, Chung-Hsien. / Channel-weighting method for speech recognition using wavelet decompositions. 論文發表於 Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, .5 p.
@conference{15a2ccd107514f369c5cb504ac1b2823,
title = "Channel-weighting method for speech recognition using wavelet decompositions",
abstract = "A decomposition of signal into a set of frequency channels of equal bandwidth on a logarithmic scale, i.e., an analysis of the signal using constant Q filters, using wavelet and multiresolution analysis is used in this paper to derive cepstrum features of different spatial frequency bands. Based on the decompositions, each channel is modeled as a Bayesian subnetwork and each subnetwork is weighted by a weighting algorithm. The distortions for speech recognition between a reference model and the input vectors are then computed by summing the weighted scores of all decomposed channels. The experimental results show that the recognition rate of this method is superior to those non-weighting methods.",
author = "Shyuu, {Jyh Shing} and Wang, {Jhing Fa} and Chung-Hsien Wu",
year = "1994",
month = "12",
day = "1",
language = "English",
pages = "519--523",
note = "Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems ; Conference date: 05-12-1994 Through 08-12-1994",

}

Shyuu, JS, Wang, JF & Wu, C-H 1994, 'Channel-weighting method for speech recognition using wavelet decompositions', 論文發表於 Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, 94-12-05 - 94-12-08 頁 519-523.

Channel-weighting method for speech recognition using wavelet decompositions. / Shyuu, Jyh Shing; Wang, Jhing Fa; Wu, Chung-Hsien.

1994. 519-523 論文發表於 Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, .

研究成果: Paper

TY - CONF

T1 - Channel-weighting method for speech recognition using wavelet decompositions

AU - Shyuu, Jyh Shing

AU - Wang, Jhing Fa

AU - Wu, Chung-Hsien

PY - 1994/12/1

Y1 - 1994/12/1

N2 - A decomposition of signal into a set of frequency channels of equal bandwidth on a logarithmic scale, i.e., an analysis of the signal using constant Q filters, using wavelet and multiresolution analysis is used in this paper to derive cepstrum features of different spatial frequency bands. Based on the decompositions, each channel is modeled as a Bayesian subnetwork and each subnetwork is weighted by a weighting algorithm. The distortions for speech recognition between a reference model and the input vectors are then computed by summing the weighted scores of all decomposed channels. The experimental results show that the recognition rate of this method is superior to those non-weighting methods.

AB - A decomposition of signal into a set of frequency channels of equal bandwidth on a logarithmic scale, i.e., an analysis of the signal using constant Q filters, using wavelet and multiresolution analysis is used in this paper to derive cepstrum features of different spatial frequency bands. Based on the decompositions, each channel is modeled as a Bayesian subnetwork and each subnetwork is weighted by a weighting algorithm. The distortions for speech recognition between a reference model and the input vectors are then computed by summing the weighted scores of all decomposed channels. The experimental results show that the recognition rate of this method is superior to those non-weighting methods.

UR - http://www.scopus.com/inward/record.url?scp=0028740144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028740144&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028740144

SP - 519

EP - 523

ER -

Shyuu JS, Wang JF, Wu C-H. Channel-weighting method for speech recognition using wavelet decompositions. 1994. 論文發表於 Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems, Taipei, Taiwan, .