• DocumentCode
    2660226
  • Title

    The Kohonen net for speaker dependent isolated word recognition

  • Author

    Kepuska, Veton Z. ; Gowdy, John N.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA
  • fYear
    1988
  • fDate
    0-0 1988
  • Firstpage
    388
  • Abstract
    Summary form only given, as follows. The authors evaluate the effectiveness of a neural-network model for use in a speech-recognition system. Performance of the model depends on many factors, including dimensionality of the network, number of neural units, type of neural units, and lateral feedback. They explore the effect of these parameters, as well as suitability and robustness of such a network for the task of speaker-dependent isolated-word discrimination. The model is tested using the Texas Instruments speech database.<>
  • Keywords
    neural nets; speech recognition; Kohonen net; dimensionality; intelligent speech recognition; neural-network model; speaker dependent isolated word recognition; Instruments; Neural networks; Neurofeedback; Robustness; Speech recognition;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    System Theory, 1988., Proceedings of the Twentieth Southeastern Symposium on
  • Conference_Location
    Charlotte, NC, USA
  • ISSN
    0094-2898
  • Print_ISBN
    0-8186-0847-1
  • Type

    conf

  • DOI
    10.1109/SSST.1988.17081
  • Filename
    17081