Phoneme sequence pattern recognition using fuzzy neural network

Abstract

In this paper, a 2-D phoneme sequence pattern recognition using the fuzzy neural network is presented. The self-organizing map and the learning vector quantization are used to organize the phoneme feature vectors of short and long phonemes segmented from speech samples to obtain the phoneme maps. The 2-D phoneme response sequences of the speech samples are formed on the phoneme maps by the Viterbi search algorithm. These 2-D phoneme response sequence curves are used as inputs to the fuzzy neural network for training and recognition of 0-9 digit-voice utterances. Simulation results are given.