DDPO-VC applies diffusion denoising policy optimization with dual-teacher rewards to improve speaker de-identification while preserving cognitive utility on dementia speech benchmarks.
Emo-stargan: A semi-supervised any-to-many non-parallel emotion- preserving voice conversion,
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
-
DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization
DDPO-VC applies diffusion denoising policy optimization with dual-teacher rewards to improve speaker de-identification while preserving cognitive utility on dementia speech benchmarks.