• DocumentCode
    1243976
  • Title

    Application of Markov chains to speech recognition

  • Author

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

  • Author_Institution
    Sch. of Comput. & Math. Sci., Robert Gordon Inst. of Technol., Aberdeen, UK
  • Volume
    27
  • Issue
    25
  • fYear
    1991
  • Firstpage
    2360
  • Lastpage
    2361
  • Abstract
    The authors describe how discrete Markov chains may be applied to speech recognition. In this application, a spectral vector is modelled by a state of a Markov chain, and an utterance is viewed as a sequence of observed states. Experiment showed that a speech recogniser based on this Markov model not only outperforms the HMM recognisers tested for comparison but also offers a saving in computation time.
  • Keywords
    Markov processes; speech recognition; Markov chains; spectral vector; speech recognition;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19911462
  • Filename
    121359