EXTENDED VTS FOR NOISE-ROBUST SPEECH RECOGNITION

被引：3
|
作者：
van Dalen, R. C. [1 ]
Gales, M. J. F. [1 ]
机构：
[1] Univ Cambridge, Dept Engn, Cambridge CB2 1PZ, England
来源：
2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年
关键词：
Speech recognition; acoustic noise; robustness;
D O I：
10.1109/ICASSP.2009.4960462
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Model compensation is a standard way of improving speech recogniers' robustness to noise. Currently popular schemes are based on vector Taylor series (VTS) compensation. They often use the continuous time approximation to compensate dynamic parameters. In this paper, the accuracy of dynamic parameter compensation is improved by representing the dynamic features as a linear transformation of a window of static features. A modified version of VTS compensation is applied to the distribution of the window of static features and, importantly, their correlations. These compensated distributions are then transformed to standard static and dynamic distributions. The proposed scheme outperformed the standard VTS scheme by about 10% relative.
引用
收藏
页码：3829 / 3832
页数：4
相关论文
共 50 条
  • [1] Extended VTS for Noise-Robust Speech Recognition
    van Dalen, Rogier C.
    Gales, Mark J. F.
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (04): : 733 - 743
  • [2] Dual-channel VTS feature compensation for noise-robust speech recognition on mobile devices
    Lopez-Espejo, Ivan
    Peinado, Antonio M.
    Gomez, Angel M.
    Gonzalez, Jose A.
    IET SIGNAL PROCESSING, 2017, 11 (01) : 17 - 25
  • [3] Sequential noise estimation for noise-robust speech recognition based on 1st-order VTS approximation
    Ding, GH
    Wang, X
    Cao, Y
    Ding, F
    Tang, YZ
    2005 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2005, : 363 - 368
  • [4] Noise-Robust speech recognition of Conversational Telephone Speech
    Chen, Gang
    Tolba, Hesham
    O'Shaughnessy, Douglas
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1101 - 1104
  • [5] An overview of noise-robust automatic speech recognition
    Li, Jinyu
    Deng, Li
    Gong, Yifan
    Haeb-Umbach, Reinhold
    IEEE Transactions on Audio, Speech and Language Processing, 2014, 22 (04): : 745 - 777
  • [6] An Overview of Noise-Robust Automatic Speech Recognition
    Li, Jinyu
    Deng, Li
    Gong, Yifan
    Haeb-Umbach, Reinhold
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (04) : 745 - 777
  • [7] Covariance Modelling for Noise-Robust Speech Recognition
    van Dalen, R. C.
    Gales, M. J. F.
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 2000 - 2003
  • [8] Frame decorrelation for noise-robust speech recognition
    Jung, HY
    Kim, DY
    Un, CK
    ELECTRONICS LETTERS, 1996, 32 (13) : 1163 - 1164
  • [9] Frame decorrelation for noise-robust speech recognition
    Korea Advanced Inst of Science and, Technology, Taejon, Korea, Republic of
    Electron Lett, 13 (1163-1164):
  • [10] NOISE-ROBUST WHISPERED SPEECH RECOGNITION USING A NON-AUDIBLE-MURMUR MICROPHONE WITH VTS COMPENSATION
    Yang, Chen-Yu
    Brown, Georgina
    Lu, Liang
    Yamagishi, Junichi
    King, Simon
    2012 8TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, 2012, : 220 - 223
12345