Presents the LibriQuote dataset of expressive audiobook speech and shows that fine-tuning or training TTS models on it improves expressivity and intelligibility.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Computational Narrative Understanding for Expressive Text-to-Speech
Presents the LibriQuote dataset of expressive audiobook speech and shows that fine-tuning or training TTS models on it improves expressivity and intelligibility.