• DocumentCode
    3621776
  • Title

    Phone recognition using hidden Markov models

  • Author

    I. Ipsic;F. Mihelic;N. Pavesic

  • Author_Institution
    Fac. of Electr. & Comput. Eng., Ljubljana Univ., Yugoslavia
  • fYear
    1991
  • fDate
    6/13/1905 12:00:00 AM
  • Firstpage
    1177
  • Abstract
    A phone recognizer based on hidden Markov models is described. For each phone a three-state Markov model is evaluated using the Baum-Welch learning algorithm. Phone models are then connected in a parallel concatenation, representing the phone recognizer. For recognition of a sentence the Viterbi algorithm is used. The recognizer was tested on a database of 50 Slovene sentences spoken by a female speaker.
  • Keywords
    "Hidden Markov models","Speech recognition","Databases","Probability density function","Prototypes","Signal processing","Viterbi algorithm","System testing","Stochastic processes","Context modeling"
  • Publisher
    ieee
  • Conference_Titel
    Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean
  • Print_ISBN
    0-87942-655-1
  • Type

    conf

  • DOI
    10.1109/MELCON.1991.162051
  • Filename
    162051
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3621776