• DocumentCode
    1342930
  • Title

    Modeling of speech signals using an optimal neural network structure based on the PMDL principle

  • Author

    Gao, Xiao Ming ; Ovaska, Seppo J. ; Lehtokangas, Mikko ; Saarinen, Jukka

  • Author_Institution
    Inst. of Intelligent Power Electron., Helsinki Univ. of Technol., Espoo, Finland
  • Volume
    6
  • Issue
    2
  • fYear
    1998
  • fDate
    3/1/1998 12:00:00 AM
  • Firstpage
    177
  • Lastpage
    180
  • Abstract
    Although neural networks have already found many successful applications in speech signal processing, it is difficult to compare their performance with that of the traditional methods objectively. We address this problem by using the predictive minimum description length (PMDL) principle to select the optimal network size in modeling speech signals
  • Keywords
    feedforward neural nets; optimisation; prediction theory; speech processing; PMDL principle; feedforward neural network; optimal network size; optimal neural network structure; performance; predictive minimum description length; speech signal processing; speech signals modeling; Information theory; Network topology; Neural networks; Predictive models; Signal processing; Signal processing algorithms; Speech processing; Speech recognition; Testing; Time series analysis;
  • fLanguage
    English
  • Journal_Title
    Speech and Audio Processing, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    1063-6676
  • Type

    jour

  • DOI
    10.1109/89.661476
  • Filename
    661476