• DocumentCode
    1399742
  • Title

    Improvements in HMM-based isolated word recognition system

  • Author

    Peinado, A.M. ; Lopez, J.M. ; Sanchez, V.E. ; Segura, J.C. ; Ayuso, A. J Rubio

  • Author_Institution
    Dept. de Electro. y Tecnologia de Computadores, Granada Univ., Spain
  • Volume
    138
  • Issue
    3
  • fYear
    1991
  • fDate
    6/1/1991 12:00:00 AM
  • Firstpage
    201
  • Lastpage
    206
  • Abstract
    A speaker-independent isolated word recognition system for voice-activated robots is introduced. Since such an application requires a fast and accurate recognition system, discrete hidden Markov models and vector quantisation techniques have been used. Different initialisations for VQ and HMM training are tested to obtain improvements over the other systems. The final models can be evaluated using a temporal normalisation of the HMM scores. A threshold-based rejector can also be established using this temporal normalisation.<>
  • Keywords
    Markov processes; data compression; encoding; speech recognition; HMM scores; HMM-based isolated word recognition system; discrete hidden Markov models; speaker-independent system; temporal normalisation; threshold-based rejector; training algorithms; vector quantisation; voice-activated robots;
  • fLanguage
    English
  • Journal_Title
    Communications, Speech and Vision, IEE Proceedings I
  • Publisher
    iet
  • ISSN
    0956-3776
  • Type

    jour

  • Filename
    87866