A new phonetic model for continuous speech recognition systems

Abstract

The main goal of this work is to describe a new model for a large vocabulary continuous speech recognition system using a phonetic-phonological approach. This work proposes a statistical phonetic structure, applied at the phonetic-phonological level, to improve the speech recognition performance in systems with phonetic-phonological modeling. It is shown that the general likelihood scores are increased, indicating better recognition performance. This is due to the fact that the statistical phonetic structure leads to enhancement of some frequent phonetic combinations from the language itself. Such a structure should be considered as an additional knowledge base, containing information about the real language phonetic structure. Also this new phonetic-phonological approach should be strongly recommended for use in spontaneous speech recognition systems.