• DocumentCode
    842837
  • Title

    Efficient Viterbi scoring architecture for HMM-based speech recognition systems

  • Author

    Cho, Y.S. ; Kim, Jin Young ; Lee, Hwang Soo

  • Author_Institution
    Dept. of Inf. & Commun. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
  • Volume
    28
  • Issue
    25
  • fYear
    1992
  • Firstpage
    2338
  • Lastpage
    2340
  • Abstract
    A new dedicated architecture for Viterbi scoring in hidden Markov model (HMM)-based real-time isolated word recognition systems is proposed. Because, in HMMs, most states are connected to only three or fewer preceding states, the state transition matrix is a banded upper triangular matrix. Using this property of the HMM, the authors design an efficient Viterbi scoring architecture.
  • Keywords
    hidden Markov models; parallel architectures; pipeline processing; speech analysis and processing; speech recognition; HMM-based speech recognition; Viterbi scoring architecture; banded upper triangular matrix; dedicated architecture; hidden Markov model; real-time isolated word recognition; state transition matrix;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19921507
  • Filename
    191864
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=842837