Memory-enhanced MMSE-based channel error mitigation for distributed speech recognition

Cheng Lung Lee; Wen-Whei Chang

Memory-enhanced MMSE-based channel error mitigation for distributed speech recognition

Cheng Lung Lee^*, Wen-Whei Chang

^*Corresponding author for this work

Department of Electrical and Computer Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

A new approach to sequence minimum mean-squared error (SMMSE) decoding for vector quantization over channels with memory is presented. The decoder is based on the Gilbert channel model that allows the exploitation of intra-vector correlation of bit error sequences. We apply the memory-enhanced SMMSE decoding algorithm to channel error mitigation in distributed speech recognition. Experiments on Mandarin digit string recognition task indicate that with the aid of Gilbert channel characterization, the proposed scheme obtains better performance than the ETSI mitigation algorithm under GSM channel conditions.

Original language	English
Pages	3137-3140
Number of pages	4
State	Published - Sep 2005
Event	9th European Conference on Speech Communication and Technology - Lisbon, Portugal Duration: 4 Sep 2005 → 8 Sep 2005

Conference

Conference	9th European Conference on Speech Communication and Technology
Country/Territory	Portugal
City	Lisbon
Period	4/09/05 → 8/09/05

Cite this

@conference{0090df2a60f4446fa1e66d05a3ee7b27,

title = "Memory-enhanced MMSE-based channel error mitigation for distributed speech recognition",

abstract = "A new approach to sequence minimum mean-squared error (SMMSE) decoding for vector quantization over channels with memory is presented. The decoder is based on the Gilbert channel model that allows the exploitation of intra-vector correlation of bit error sequences. We apply the memory-enhanced SMMSE decoding algorithm to channel error mitigation in distributed speech recognition. Experiments on Mandarin digit string recognition task indicate that with the aid of Gilbert channel characterization, the proposed scheme obtains better performance than the ETSI mitigation algorithm under GSM channel conditions.",

author = "Lee, {Cheng Lung} and Wen-Whei Chang",

year = "2005",

month = sep,

language = "English",

pages = "3137--3140",

note = "9th European Conference on Speech Communication and Technology ; Conference date: 04-09-2005 Through 08-09-2005",

}

TY - CONF

T1 - Memory-enhanced MMSE-based channel error mitigation for distributed speech recognition

AU - Lee, Cheng Lung

AU - Chang, Wen-Whei

PY - 2005/9

Y1 - 2005/9

N2 - A new approach to sequence minimum mean-squared error (SMMSE) decoding for vector quantization over channels with memory is presented. The decoder is based on the Gilbert channel model that allows the exploitation of intra-vector correlation of bit error sequences. We apply the memory-enhanced SMMSE decoding algorithm to channel error mitigation in distributed speech recognition. Experiments on Mandarin digit string recognition task indicate that with the aid of Gilbert channel characterization, the proposed scheme obtains better performance than the ETSI mitigation algorithm under GSM channel conditions.

AB - A new approach to sequence minimum mean-squared error (SMMSE) decoding for vector quantization over channels with memory is presented. The decoder is based on the Gilbert channel model that allows the exploitation of intra-vector correlation of bit error sequences. We apply the memory-enhanced SMMSE decoding algorithm to channel error mitigation in distributed speech recognition. Experiments on Mandarin digit string recognition task indicate that with the aid of Gilbert channel characterization, the proposed scheme obtains better performance than the ETSI mitigation algorithm under GSM channel conditions.

UR - http://www.scopus.com/inward/record.url?scp=33745205064&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:33745205064

SP - 3137

EP - 3140

T2 - 9th European Conference on Speech Communication and Technology

Y2 - 4 September 2005 through 8 September 2005

ER -

Memory-enhanced MMSE-based channel error mitigation for distributed speech recognition

Abstract

Conference

Other files and links

Fingerprint

Cite this