Distinctive Phonetic Feature (dpf) Based Phone Segmentation Using 2-stage Multilayer Neural Networks

Segmentation of speech into its corresponding phones has become very important issue in many speech processing areas such as speech recognition, speech analysis, speech synthesis, and speech database. In this paper, for accurate segmentation in speech recognition applications, we introduce Distinctive Phonetic Feature (DPF) based feature extraction using a two-stage MLN (Multi-Layer Neural Network) system consists of an MLNLF-DPF in the first stage and an MLNDyn in the second stage. The MLNLF-DPF maps continuous acoustic features, Local Feature (LF), onto discrete DPF patterns, while the MLNDyn constraints DPF context or dynamics in an utterance. The experiments are carried out using Japanese triphthong data. The proposed DPF based feature extractor provides good segmentation and high recognition rate with a reduced mixture-set of HMMs (Hidden Markov Models) by resolving co-articulation effect.