Speaker-dependent recognition of isolated Chinese words based on neural networks

Abstract

This paper describes a speaker-dependent, isolated Chinese word recognition system based on neural networks. An improved neural network is applied to the recognition of speaker-dependent isolated Chinese words. The improved neural network is composed of several BP (back-propagation) networks. The isolated Chinese word sets are partitioned into a group of subsets based on a priori phonological knowledge. One of the BP networks identifies the subset to which the input word belongs; the others recognize the words in the subset. The improved neural network has the following advantages over a single BP network: training time is reduced; higher recognition accuracy is obtained with less training samples; new words can be easily added by adding new subsets.<>