Language independent automatic speech segmentation into phoneme-like units on the base of acoustic distinctive features

Abstract

There are special topics in cognitive infocommunications where the processing of continuous speech is necessary. These topics often require the segmentation of speech signal into phoneme sized units. This kind of segmentation is necessary, when the desired behavior depends on speech timing, like rhythm or the place of voiced sounds (emotion or mood detection, language learning, acoustic feature visualization). Segmentation systems based on the acoustic-phonetic knowledge of speech could be realized in a language independent way. In this paper we introduce a language independent solution, based on the segmentation of continuous speech into 9 broad phonetic classes. The classification and segmentation was prepared using Hidden Markov Models. Three databases were used to evaluate the segmentation systems: Hungarian MRBA, German KIEL and English TIMIT databases. 80% average recognition result was obtained.