A cascaded audio-prompting and ICL-based online RL method improves naturalness and expressivity in conversational TTS with reduced data needs.
Dataset: We used in-house voice actor data for prompt can- didates, with coarse-grained voice styles provided by the vendor
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning
A cascaded audio-prompting and ICL-based online RL method improves naturalness and expressivity in conversational TTS with reduced data needs.