Welcome to Journal of Beijing Institute of Technology
Volume 15Issue 2
.
Turn off MathJax
Article Contents
ZHAO Jun-hui, XIE Xiang, KUANG Jing-ming. Data-Driven Temporal Filtering on Teager Energy Time Trajectory for Robust Speech Recognition[J]. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2006, 15(2): 195-200.
Citation: ZHAO Jun-hui, XIE Xiang, KUANG Jing-ming. Data-Driven Temporal Filtering on Teager Energy Time Trajectory for Robust Speech Recognition[J].JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2006, 15(2): 195-200.

Data-Driven Temporal Filtering on Teager Energy Time Trajectory for Robust Speech Recognition

Funds:Sponsored bythe Basic Research Foundation of Beijing Institute of Technology (BIT-UBF-200301F03);BIT &Ericsson Cooperation Project
  • Received Date:2004-11-10
  • Data-driven temporal filtering technique is integrated into the time trajectory of Teager energy operation (TEO) based feature parameter for improving the robustness of speech recognition system against noise. Three kinds of data-driven temporal filters are investigated for the motivation of alleviating the harmful effects that the environmental factors have on the speech. The filters include: principle component analysis (PCA) based filters, linear discriminant analysis (LDA) based filters and minimum classification error (MCE) based filters. Detailed comparative analysis among these temporal filtering approaches applied in Teager energy domain is presented. It is shown that while all of them can improve the recognition performance of the original TEO based feature parameter in adverse environment, MCE based temporal filtering can provide the lowest error rate as SNR decreases than any other algorithms.
  • loading
  • [1]
    Hermansky H, Morgan N. RASTA processing of speech[J]. IEEE Transactions on Speech and Audio Process ing, 1994, 2(4): 578-589.
    [2]
    T eager H M, Teager S M. Evidence for nonlinear speechproductio n mechanisms in the vocal tract [R]. Bo nas,France: NATO Adv anced Study Institute on Speech Pro duct ion and Speech Mo delling, 1989.
    [3]
    Maragos P, Kaiser J F, Quatieri T F. Energ y separationin signal modulations w ith application to speech analysis[J]. IEEE Transactions on Speech and Audio Process ing, 1993, 41(2): 3024-3051.
    [4]
    Hung J, Wang H, Lee L S. Compar ative analysis for da ta driven temporal filters obtained via pr incipal componentanalysis[Z]. EUROSPEECH, Aalborg Demark, 2001.
    [5]
    Avendano C, Vuuren S, Hermansky H. Data based filterdesign for RASTA like channel no rmalization in ASR[Z]. ICSLP, Philadephia, Pennsylvania, 1996.
    [6]
    Hung J, Lee L S. Data driven tempor al filters for r obustfeatures in speech recog nition obtained via minimum clas sification erro r (MCE) [Z]. ICASSP, Orlando, Flo rida,2002.
    [7]
    Slaney M. An efficient implementation of the patterson holdswort h auditory filter bank [R]. Apple T ech RepNo. 35, 1993.
    [8]
    Avendano C, Hermansky H. On the pr operties of tempo ral processing for speech in adverse env ironments [Z]. Proc of IEEE Wor kshop on Applications of Signal Pro cessing to Audio and Acoustics, Mohonk, NY, 1997.
    [9]
    Haeb Umbach R, Ney H. Linear discr iminant analysisfor improving larg e vocabulary continuous speech r ecogni tion[Z]. ICASSP, San Francisco, 1992.
    [10]
    Juang B, Chou W, Lee C. Minimum classification errorrate methods for speech r ecognition[J]. IEEE Transac tions on Speech and Audio Processing, 1997, 5(3): 257-265.
    [11]
    Young S. The HTK book[M]. Cambr idge: CambridgeResear ch Lab, 2001.
    [12]
    Varg a A. The NOI SEX-92 study on the effect of addi tive noise on automatic speech r ecognition[R]. [s. l.]: [s. n.], 1992.
  • 加载中

Catalog

    通讯作者:陈斌, bchen63@163.com
    • 1.

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (165) PDF downloads(0) Cited by()
    Proportional views
    Related

    /

      Return
      Return
        Baidu
        map