Neural learning for articulatory speech synthesis under different statistical characteristics of acoustic input patterns

Abstract

Input data representation is highly decisive in neural learning in terms of convergence. In this paper, within an analytical and statistical framework, the effect of the distribution characteristics of the input pattern vectors on the performance of the back-propagation (BP) algorithm is established for a function approximation problem, where parameters of an articulatory speech synthesizer are estimated from acoustic input data. The aim is to determine the optimum statistical characteristics of the acoustic input patterns in order to improve neural learning. Improvement is obtained through a modification of the statistical characteristics of the input data, which reduces effectively the occurrence of node saturation in the hidden layer.