Diff-VS is an efficient audio-aware diffusion U-Net for vocal separation that matches discriminative baselines on objective metrics while achieving state-of-the-art perceptual quality via proxy measures.
With band-splitting and a sparse com- pression network, SCNet [3] achieves competitive perfor- mance with faster inference, fewer parameters, and a single model for all four stems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation
Diff-VS is an efficient audio-aware diffusion U-Net for vocal separation that matches discriminative baselines on objective metrics while achieving state-of-the-art perceptual quality via proxy measures.