• DocumentCode
    2910627
  • Title

    A hybrid neural system for phonematic transformation

  • Author

    Podolak, Igor T. ; Lee, Seong-Whan ; Bielecki, Andrzej ; Majkut, Elzbieta

  • Author_Institution
    Center for Artificial Vision Res., Korea Univ., Seoul, South Korea
  • Volume
    2
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    957
  • Abstract
    Text-to-phoneme conversion is a common problem in speech processing. This can be done using a rule-based system or a neural network. In this paper we propose a solution to this problem using a modular hybrid system that uses basic rules to subdivide the original problem into easier tasks which are then solved by dedicated neural networks. Such a solution can be more rapidly constructed, and is easily extendable. A voting committee concept is used to enhance generalization abilities of the system
  • Keywords
    generalisation (artificial intelligence); knowledge based systems; neural nets; speech processing; text analysis; generalization; neural network; rule-based system; speech processing; text-phoneme conversion; voting committee concept; Artificial neural networks; Computer science; Image converters; Knowledge based systems; Natural languages; Neural networks; Research initiatives; Speech processing; Speech synthesis; Voting;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2000. Proceedings. 15th International Conference on
  • Conference_Location
    Barcelona
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-0750-6
  • Type

    conf

  • DOI
    10.1109/ICPR.2000.906233
  • Filename
    906233