• DocumentCode
    970187
  • Title

    Fuzzy smoothing of HMM parameters using the Parzen window

  • Author

    Dai, Jiejian ; Tyler, J.E.M. ; MacKenzie, I.G.

  • Author_Institution
    Dept. of Comput. Sci., Nanjing Univ., China
  • Volume
    29
  • Issue
    22
  • fYear
    1993
  • Firstpage
    1911
  • Lastpage
    1913
  • Abstract
    Presents a parameter-smoothing technique for discrete hidden Markov models in speech recognition using fuzzy vector quantisation and the Parzen window. The technique is compared with existing smoothing techniques by experiments with speaker-independent isolated word recognition. The results suggest that this technique is more effective than the others in terms of improved recognition.
  • Keywords
    fuzzy logic; hidden Markov models; speech coding; speech recognition; vector quantisation; HMM parameters; Parzen window; discrete hidden Markov models; fuzzy vector quantisation; parameter-smoothing technique; speaker-independent isolated word recognition; speech coding; speech recognition;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19931272
  • Filename
    244577
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=970187