A new feature normalization scheme based on eigenspace for noisy speech recognition

被引：0
|
作者：
Lee, Y [1 ]
Ko, H [1 ]
机构：
[1] Korea Univ, Dept Elect & Comp Engn, Seoul 136701, South Korea
来源：
STRING PROCESSING AND INFORMATION RETRIEVAL, PROCEEDINGS | 2004年 / 3246卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We propose a new feature normalization scheme based on eigenspace, for achieving robust speech recognition. In particular, we employ the Mean and Variance Normalization (MVN) in eigenspace using unique and independent eigenspaces to cepstra, delta and delta-delta cepstra respectively. We also normalize training data in eigenspace and get the model from the normalized training data. In addition, a feature space rotation procedure is introduced to reduce the mismatch of training and test data distribution in noisy condition. As a result, we obtain a substantial recognition improvement over the basic eigenspace normalization.
引用
收藏
页码：76 / 78
页数：3
相关论文
共 50 条
  • [41] Speaker normalization for template based speech recognition
    Demange, Sebastien
    Van Compernolle, Dirk
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 560 - 563
  • [42] SPEECH FEATURE DENOISING AND DEREVERBERATION VIA DEEP AUTOENCODERS FOR NOISY REVERBERANT SPEECH RECOGNITION
    Feng, Xue
    Zhang, Yaodong
    Glass, James
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [43] Phonological feature based variable frame rate scheme for improved speech recognition
    Sangwan, Abhijeet
    Hansen, John H. L.
    [J]. 2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 582 - 586
  • [44] A Feature Extraction Scheme Based on Enhanced Wavelet Coefficients for Speech Emotion Recognition
    Shahnaz, C.
    Sultana, S.
    [J]. 2014 IEEE 57TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2014, : 1093 - 1096
  • [45] Distribution-Based Feature Normalization for Robust Speech Recognition Leveraging Context and Dynamics Cues
    Kao, Yu -Chen
    Chen, Berlin
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2957 - 2961
  • [46] Subband Feature Statistics Normalization Techniques Based on a Discrete Wavelet Transform for Robust Speech Recognition
    Hung, Jeih-weih
    Fan, Hao-Teng
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2009, 16 (09) : 806 - 809
  • [47] A segment-based Co adaptation scheme for PMC-based noisy Mandarin speech recognition
    Hong, WT
    Chen, SH
    [J]. ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 433 - 436
  • [48] FUNDAMENTAL FREQUENCY FEATURE NORMALIZATION AND DATA AUGMENTATION FOR CHILD SPEECH RECOGNITION
    Yeung, Gary
    Fan, Ruchao
    Alwan, Abeer
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 6993 - 6997
  • [49] Phoneme class based feature adaptation for mismatch acoustic modeling and recognition of distant noisy speech
    Uluskan S.
    Sangwan A.
    Hansen J.H.L.
    [J]. International Journal of Speech Technology, 2017, 20 (4) : 799 - 811
  • [50] Feature Normalization Using Structured Full Transforms for Robust Speech Recognition
    Xiao, Xiong
    Li, Jinyu
    Chng, Eng Siong
    Li, Haizhou
    [J]. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 700 - +
12345