• DocumentCode
    2695426
  • Title

    Phoneme recognition with a time-delay neural network

  • Author

    Shaw, Arnab ; Mitchell, Richard A.

  • fYear
    1990
  • fDate
    17-21 June 1990
  • Firstpage
    191
  • Abstract
    A time-delay neural network architecture is used for speaker-dependent recognition of the long vowel sounds a, e, and i. The following areas are investigated: increasing the amount of data supplied to the network, allowing longer and variable-length utterances, and using English rather than Japanese speech. With this architecture, 100% recognition has been obtained for a population of six speakers
  • Keywords
    neural nets; parallel architectures; speech recognition; English; Japanese speech; long vowel sounds; phoneme recognition; speaker-dependent recognition; time-delay neural network; variable-length utterances;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1990., 1990 IJCNN International Joint Conference on
  • Conference_Location
    San Diego, CA, USA
  • Type

    conf

  • DOI
    10.1109/IJCNN.1990.137715
  • Filename
    5726674
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2695426