The authors release NonverbalTTS, a 17-hour open dataset with nonverbal vocalization and emotion annotations, and show that fine-tuning an open TTS model on it yields performance comparable to CosyVoice2.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech
The authors release NonverbalTTS, a 17-hour open dataset with nonverbal vocalization and emotion annotations, and show that fine-tuning an open TTS model on it yields performance comparable to CosyVoice2.