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
  • [31] Robust i-vector based Adaptation of DNN Acoustic Model for Speech Recognition
    Garimella
    Mandal, Arindam
    Strom, Nikko
    Hoffmeister, Bjorn
    Matsoukas, Spyros
    Parthasarathi, Hari Krishnan
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2877 - 2881
  • [32] CASA Based Speech Separation for Robust Speech Recognition
    Han Runqiang
    Zhao Pei
    Gao Qin
    Zhang Zhiping
    Wu Hao
    Wu Xihong
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 77 - 80
  • [33] A Vector Space Approach to Environment Modeling for Robust Speech Recognition
    Tsao, Yu
    Lee, Chin-Hui
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 785 - 788
  • [34] Robust recognition of cellular telephone speech by adaptive vector quantization
    Sonmez, MK
    Rajasekaran, R
    Baras, JS
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 503 - 506
  • [35] Vector Taylor series based model adaptation using noisy speech trained hidden Markov models
    Chung, Yongjoo
    PATTERN RECOGNITION LETTERS, 2016, 75 : 36 - 40
  • [36] GENERAL ROBUST DESIGN BY SEMI-SECOND-ORDER TAYLOR EXPANSION
    Du, Xiaoping
    IMECE2008: PROCEEDINGS OF THE ASME INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, VOL 4: DESIGN AND MANUFACTURING, 2009, : 87 - 92
  • [37] Identification of Dynamic Loads Based on Second-Order Taylor-Series Expansion Method
    Li, Xiaowang
    Deng, Zhongmin
    SHOCK AND VIBRATION, 2016, 2016
  • [38] Offline Signature Verification Based on Partial Sum of Second-Order Taylor Series Expansion
    Shekar, B. H.
    Pilar, Bharathi
    Kumar, D. S. Sunil
    DATA ANALYTICS AND LEARNING, 2019, 43 : 359 - 367
  • [39] Vector Taylor Series based Joint Uncertainty Decoding
    Xu, Haitian
    Rigazio, Luca
    Kryze, David
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1125 - +
  • [40] Third-order moments of filtered speech signals for robust speech recognition
    Indrebo, KM
    Povinelli, RJ
    Johnson, MT
    NONLINEAR ANALYSES AND ALGORITHMS FOR SPEECH PROCESSING, 2005, 3817 : 277 - 283
12345