Expressive speech style transformation: Voice quality and prosody modification using a harmonic plus noise model

Abstract

This paper proposes an approach to transform speech from a neutral style into other expressive styles using both prosody and voice quality (VoQ). The main aim is to validate the usefulness of VoQ in the enhancement of expressive synthetic speech. A Harmonic plus Noise Model (HNM) is used to modify speech following a set of rules extracted from an expressive speech corpus with five categories (neutral, happy, sensual, aggressive and sad). Finally, modified speech utterances were used to perform a perceptual test. These results indicate that listeners prefer prosody together with VoQ transformation instead of only prosody modification.