A rectified-flow voice conversion model with speaker feature fusion achieves zero-shot conversion in one sampling step with quality close to 30-step diffusion baselines.
ReFlow-VC can use the RK45 ODE solver for sampling, generating speech samples with optimal audio quality
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization
A rectified-flow voice conversion model with speaker feature fusion achieves zero-shot conversion in one sampling step with quality close to 30-step diffusion baselines.