DAFMSVC swaps source SSL features for similar target features and adds dual cross-attention plus flow matching to improve one-shot singing voice conversion.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
DAFMSVC swaps source SSL features for similar target features and adds dual cross-attention plus flow matching to improve one-shot singing voice conversion.