• DocumentCode
    989909
  • Title

    Fast channel adaptation for continuous density HMMs using maximum likelihood spectral transform

  • Author

    Kim, D. ; Yook, D.

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Korea Univ., Seoul, South Korea
  • Volume
    40
  • Issue
    10
  • fYear
    2004
  • fDate
    5/13/2004 12:00:00 AM
  • Firstpage
    632
  • Lastpage
    634
  • Abstract
    A transform-based adaptation algorithm for robust speech recognition in unknown environments is proposed. In the cepstral domain, it is difficult to handle environmental noise. The proposed approach deals with such noise in the linear spectral domain, so that a small number of parameters can be used for fast adaptation.
  • Keywords
    hidden Markov models; maximum likelihood estimation; spectral analysis; speech recognition; transforms; cepstral domain; channel adaptation; continuous density HMM; environmental noise; linear spectral domain; maximum likelihood spectral transform; robust speech recognition;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:20040395
  • Filename
    1300308
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=989909