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

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. In this correspondence, we address this problem by using the predictive minimum description length (PMDL) principle to select the optimal network size in modeling speech signals.Index Terms-Neural networks structure optimization, predictive minimum description length (PMDL), speech modeling.