• DocumentCode
    1921922
  • Title

    Description of Training Procedure for AlfaNum Continuous Speech Recognition System

  • Author

    Jakovljevic, Niksha ; Pekar, Darko

  • Author_Institution
    Fac. of Eng., Novi Sad Univ.
  • Volume
    2
  • fYear
    2005
  • fDate
    21-24 Nov. 2005
  • Firstpage
    1646
  • Lastpage
    1649
  • Abstract
    This paper presents training procedure for our continuous speech recognition system in Serbian, based on hidden Markov models. In this paper, we focus on solutions of the problem of insufficient training data, and improvements obtained by maximum likelihood train algorithm
  • Keywords
    hidden Markov models; maximum likelihood estimation; natural languages; speech recognition; AlfaNum continuous speech recognition system; Serbian language; hidden Markov models; maximum likelihood train algorithm; Automatic speech recognition; Context modeling; Hidden Markov models; Robustness; Spatial databases; Speech recognition; State estimation; Telephony; Testing; Training data; Automatic speech recognition; hidden Markov models; maximum likelihood train algorithm and tying procedure;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer as a Tool, 2005. EUROCON 2005.The International Conference on
  • Conference_Location
    Belgrade
  • Print_ISBN
    1-4244-0049-X
  • Type

    conf

  • DOI
    10.1109/EURCON.2005.1630286
  • Filename
    1630286
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1921922