StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations

arXiv:2404.14946v1 Announce Type: cross
Abstract: While acoustic expressiveness has long been studied in expressive text-to-speech (ETTS), the inherent expressiveness in text lacks sufficient attention, especially for ETTS of artistic works. In this paper, we introduce StoryTTS, a highly ETTS dataset that contains rich expressiveness both in acoustic and textual perspective, from the recording of a Mandarin storytelling show. A systematic and comprehensive labeling framework is proposed for textual expressiveness. We analyze and define speech-related textual expressiveness in StoryTTS to include …

abstract annotations arxiv attention cs.cl cs.sd dataset eess.as paper speech text text-to-speech textual type