Preprint
Aug 2026
Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation
Generative modeling provides a flexible way to model mixture-conditioned source distributions, but iterative diffusion and flow matching models are costly for long music signals. This paper studies joint vocal-accompaniment separation through latent flow matching, where a pretrained variational autoencoder (VAE) maps m...
Li-Shi Zuo, Youzhi Tu, Lu Yi et al.
· 0 citations