• DocumentCode
    1086298
  • Title

    The DRAGON system--An overview

  • Author

    Baker, James K.

  • Author_Institution
    IBM Thomas J. Watson Research Center, Yorktown Heights, N.Y.
  • Volume
    23
  • Issue
    1
  • fYear
    1975
  • fDate
    2/1/1975 12:00:00 AM
  • Firstpage
    24
  • Lastpage
    29
  • Abstract
    This paper briefly describes the major features of the DRAGON speech understanding system. DRAGON makes systematic use of a general abstract model to represent each of the knowledge sources necessary for automatic recognition of continuous speech. The model--that of a probabilistic function of a Markov process--is very flexible and leads to features which allow DRAGON to function despite high error rates from individual knowledge sources. Repeated use of a simple abstract model produces a system which is simple in structure, but powerful in capabilities.
  • Keywords
    Acoustic measurements; Automatic speech recognition; Data mining; Error analysis; Markov processes; Power system modeling; Power system reliability; Random variables; Speech recognition; Vocabulary;
  • fLanguage
    English
  • Journal_Title
    Acoustics, Speech and Signal Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0096-3518
  • Type

    jour

  • DOI
    10.1109/TASSP.1975.1162650
  • Filename
    1162650