A FreeVC-style conditional VAE with mHuBERT-147 discrete units, mixed-style layer normalization, an augmentation similarity loss, and F0 cross-attention reports better emotion transfer and less source leakage than three baselines, at the cost of a higher word error rate.
All datasets are English and total duration is around 228 hours with more than 920 speakers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion
A FreeVC-style conditional VAE with mHuBERT-147 discrete units, mixed-style layer normalization, an augmentation similarity loss, and F0 cross-attention reports better emotion transfer and less source leakage than three baselines, at the cost of a higher word error rate.