Back to Search Start Over

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

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

Authors :
Liu, Sen
Guo, Yiwei
Chen, Xie
Yu, Kai
Source :
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 11521-11525
Publication Year :
2024

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 five distinct dimensions through linguistics, rhetoric, etc. Then we employ large language models and prompt them with a few manual annotation examples for batch annotation. The resulting corpus contains 61 hours of consecutive and highly prosodic speech equipped with accurate text transcriptions and rich textual expressiveness annotations. Therefore, StoryTTS can aid future ETTS research to fully mine the abundant intrinsic textual and acoustic features. Experiments are conducted to validate that TTS models can generate speech with improved expressiveness when integrating with the annotated textual labels in StoryTTS.<br />Comment: Accepted by ICASSP 2024

Details

Database :
arXiv
Journal :
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, pp. 11521-11525
Publication Type :
Report
Accession number :
edsarx.2404.14946
Document Type :
Working Paper