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.
Sound demixing challenge 2023 music demixing track technical report: Tfc-tdf-unet v3
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Articulation-manner knowledge vectors improve target speech extraction on cinematic audio source separation (CASS) data versus knowledge-free baselines, especially for short buried speech segments.
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.
-
A Knowledge-Driven Approach to Target Speech Extraction in the Presence of Background Sound Effects for Cinematic Audio Source Separation (CASS)
Articulation-manner knowledge vectors improve target speech extraction on cinematic audio source separation (CASS) data versus knowledge-free baselines, especially for short buried speech segments.