SECOND ORDER VECTOR TAYLOR SERIES BASED ROBUST SPEECH RECOGNITION

被引：0
|
作者：
Bu, Suliang [1 ]
Qian, Yanmin [1 ]
Sim, Khe Chai [2 ]
You, Yongbin [1 ]
Yu, Kai [1 ]
机构：
[1] Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, MOE, Microsoft Key Lab Intelligent Comp & Intelligent, Shanghai 200030, Peoples R China
[2] Natl Univ Singapore, Dept Comp Sci, Singapore 117548, Singapore
来源：
2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2014年
关键词：
robust speech recognition; model based compensation; Vector Taylor Series; APPROXIMATION;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Vector Taylor Series (VTS) model based compensation approach has been successfully applied to various robust speech recognition tasks. In this paper, a novel method to derive the formula to calculate the static and dynamic statistics based on second-order VTS (sVTS) is presented, which provides a new insight on the VTS approximation. Lengthy derivation could therefore be avoided when high order VTS is used and the proposed approach is more compact and easier to implement compared to previous high order VTS approaches. Experiments on Aurora 4 showed that the proposed sVTS based model compensation approach obtained 16.7% relative WER reduction over traditional first-order VTS (fVTS) approach.
引用
收藏
页数：5
相关论文
共 50 条
  • [1] ON NOISE ESTIMATION FOR ROBUST SPEECH RECOGNITION USING VECTOR TAYLOR SERIES
    Zhao, Yong
    Juang, Biing-Hwang
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4290 - 4293
  • [2] Multi-environment model adaptation based on vector Taylor series for robust speech recognition
    Lue, Yong
    Wu, Haiyang
    Zhou, Lin
    Wu, Zhenyang
    [J]. PATTERN RECOGNITION, 2010, 43 (09) : 3093 - 3099
  • [3] A new algorithm using improved Vector Taylor Series for robust speech recognition
    Li, YY
    Li, B
    Wang, CY
    Tang, CJ
    [J]. 2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS, INTELLIGENT SYSTEMS AND SIGNAL PROCESSING, VOLS 1 AND 2, PROCEEDINGS, 2003, : 1146 - 1150
  • [4] Vector Taylor Series Expansion with Auditory Masking for Noise Robust Speech Recognition
    Das, Biswajit
    Panda, Ashish
    [J]. 2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
  • [5] Robust Speech Recognition Using Improved Vector Taylor Series Algorithm for Embedded Systems
    Lue, Yong
    Wu, Haiyang
    Wu, Zhenyang
    [J]. IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2010, 56 (02) : 764 - 769
  • [6] Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition
    Loweimi, Erfan
    Barker, Jon
    Hain, Thomas
    [J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3798 - 3802
  • [7] Speech recognition in noisy environments using first-order vector Taylor series
    Kim, DY
    Un, CK
    Kim, NS
    [J]. SPEECH COMMUNICATION, 1998, 24 (01) : 39 - 49
  • [8] NOISE ADAPTIVE TRAINING USING A VECTOR TAYLOR SERIES APPROACH FOR NOISE ROBUST AUTOMATIC SPEECH RECOGNITION
    Kalinli, Ozlem
    Seltzer, Michael L.
    Acero, Alex
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 3825 - 3828
  • [9] NOISE ADAPTIVE FRONT-END NORMALIZATION BASED ON VECTOR TAYLOR SERIES FOR DEEP NEURAL NETWORKS IN ROBUST SPEECH RECOGNITION
    Bo Li
    Chai, Khe Sim
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7408 - 7412
  • [10] A vector Taylor series approach for environment-independent speech recognition
    Moreno, PJ
    Raj, B
    Stern, RM
    [J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 733 - 736
12345