SURF uses teacher-student remixing within a flow-matching framework to achieve unsupervised source separation and reports new state-of-the-art results on audio and image benchmarks.
Foley Sound Synthesis at the DCASE 2023 Challenge
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative citing papers
OTAD replaces FAD's frozen embedding cost and Gaussian coupling with a learned Riemannian adapter and Sinkhorn OT, reporting higher MOS Spearman correlation on DCASE 2023 and per-sample diagnostics with AUROC at least 0.86.
MAP-Elites with CPPNs, DSP graphs, and a deep classifier produces diverse synthetic sounds across durations and musical/non-musical contexts.
citing papers explorer
-
SURF: Separation via Unsupervised Remixing Flow
SURF uses teacher-student remixing within a flow-matching framework to achieve unsupervised source separation and reports new state-of-the-art results on audio and image benchmarks.
-
Optimal Transport Audio Distance with Learned Riemannian Ground Metrics
OTAD replaces FAD's frozen embedding cost and Gaussian coupling with a learned Riemannian adapter and Sinkhorn OT, reporting higher MOS Spearman correlation on DCASE 2023 and per-sample diagnostics with AUROC at least 0.86.
-
Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration
MAP-Elites with CPPNs, DSP graphs, and a deep classifier produces diverse synthetic sounds across durations and musical/non-musical contexts.