Duration Modeling For Turkish Text-to-Speech Synthesis System

Abstract

Naturalness of synthetic speech depends on appropriate modeling of prosodic aspects. Mostly, three prosody components are modeled: segmental duration, pitch contour and intensity. In this study, we present our work on modeling segmental duration in Turkish by using machine-learning algorithms. The models predict phone durations based on attributes such as phone identity, neighboring phone identities, lexical stress, position of syllable in word, part-of-speech information, word length in number of syllables and position of word in utterance. Obtained models predict segment durations better than mean duration approximations.

Resources

Details