• DocumentCode
    3098925
  • Title

    An Effective Method to Decrease the Dimension of Input Vector of BPNN on ASR System

  • Author

    Huang, Wan-chen

  • Author_Institution
    Wu-Feng Inst. of Technol., Chiayi
  • fYear
    2007
  • fDate
    5-8 Nov. 2007
  • Firstpage
    2499
  • Lastpage
    2502
  • Abstract
    This paper uses BP neural network for modeling and recognition in the ASR (automatic speech recognition system) to get a high performance. But it still has some disadvantages, one of which is that it needs to construct a high dimension of input vector, so it will waste a lot of memory storage and spend much time in computing. In this paper we present a new method to combine HMM and BPNN to decrease the dimension of input vector and still keep a high recognition rate while recognizing.
  • Keywords
    backpropagation; hidden Markov models; neural nets; speech recognition; automatic speech recognition system; backpropagation neural network; hidden Markov models; memory storage; Automatic speech recognition; Hidden Markov models; Industrial Electronics Society; Mechanical engineering; Neural networks; Notice of Violation; Probability distribution; Real time systems; Speech recognition; Vectors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Industrial Electronics Society, 2007. IECON 2007. 33rd Annual Conference of the IEEE
  • Conference_Location
    Taipei
  • ISSN
    1553-572X
  • Print_ISBN
    1-4244-0783-4
  • Type

    conf

  • DOI
    10.1109/IECON.2007.4460202
  • Filename
    4460202