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
fDate :
3/1/1998 12:00:00 AM
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;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
