RAPID JOINT SPEAKER AND NOISE COMPENSATION FOR ROBUST SPEECH RECOGNITION

被引：0

作者：

Chin, K. K. ^{[1
]}

Xu, Haitian ^{[1
]}

Gales, Mark J. F. ^{[1
]}

Breslin, Catherine ^{[1
]}

Knill, Kate ^{[1
]}

机构：

[1] Toshiba Res Europe Ltd, Cambridge Res Lab, Cambridge, England

来源：

2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年

关键词：

Speaker adaptation; Noise compensation; Robust ASR; Rapid adaptation;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

For speech recognition, mismatches between training and testing for speaker and noise are normally handled separately. The work presented in this paper aims at jointly applying speaker adaptation and model-based noise compensation by embedding speaker adaptation as part of the noise mismatch function. The proposed method gives a faster and more optimum adaptation compared to compensating for these two factors separately. It is also more consistent with respect to the basic assumptions of speaker and noise adaptation. Experimental results show significant and consistent gains from the proposed method.

引用

页码：5500 / 5503

页数：4

共 50 条

[1] Speaker and Noise Factorization for Robust Speech Recognition
Wang, Yongqiang
Gales, Mark J. F.
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (07): : 2149 - 2158
[2] Efficient Speaker and Noise Normalization for Robust Speech Recognition
Joshi, Vikas
Bilgi, Raghavendra
Umesh, S.
Benitez, C.
Garcia, L.
12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 2612 - 2615
[3] Noise robust estimate of speech dynamics for speaker recognition
Openshaw, JP
Mason, JS
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 925 - 928
[4] Joint compensation of noise and channel in speech recognition
Zhao, Rui
Wang, Zuoying
Shengxue Xuebao/Acta Acustica, 2006, 31 (05): : 466 - 470
[5] Residual noise compensation for robust speech recognition in nonstationary noise
Yao, KS
Shi, BE
Fung, P
Cao, ZG
2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 1125 - 1128
[6] Eigen-MLLR Environment/Speaker Compensation for Robust Speech Recognition
Liao, Yuan-Fu
Fang, Hung-Hsiang
Hsu, Chi-Hui
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1249 - 1252
[7] Speaker normalized spectral subband parameters for noise robust speech recognition
Tsuge, Satoru
Fukada, Toshiaki
Singer, Harald
Paliwal, Kuldip K.
Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi), 1999, 20 (06): : 425 - 431
[8] Speaker normalized spectral subband parameters for noise robust speech recognition
Tsuge, S
Fukada, T
Singer, H
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 285 - 288
[9] Signal trajectory based noise compensation for robust speech recognition
Yan, Zhi-Jie
Zhou, Jian-Lai
Soong, Frank
Wang, Ren-Hua
CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 335 - +
[10] Feature domain compensation of nonstationary noise for robust speech recognition
Kim, NS
SPEECH COMMUNICATION, 2002, 37 (3-4) : 231 - 248

← 1 2 3 4 5 →