• DocumentCode
    1909511
  • Title

    A dynamic neural network for syllable recognition

  • Author

    Zhong, Lin ; Shi, Yuanyuan ; Liu, Runsheng

  • Author_Institution
    Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
  • Volume
    5
  • fYear
    1999
  • fDate
    1999
  • Firstpage
    2997
  • Abstract
    A dynamic neural network architecture based on the time-delay neural network and the convolutional neural network is originated. The dynamic network achieves much better performance than those of MLP and TDNN when dealing with syllable recognition. Such performance is also comparable to that of the more popular HMM method
  • Keywords
    convolution; delays; multilayer perceptrons; neural net architecture; speech recognition; MLP; TDNN; convolutional neural network; dynamic neural network architecture; syllable recognition; time-delay neural network; Cellular neural networks; Hidden Markov models; Lamination; Neural networks; Neurons; Speech recognition; Vocabulary;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 1999. IJCNN '99. International Joint Conference on
  • Conference_Location
    Washington, DC
  • ISSN
    1098-7576
  • Print_ISBN
    0-7803-5529-6
  • Type

    conf

  • DOI
    10.1109/IJCNN.1999.836002
  • Filename
    836002
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1909511