MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning
arXiv:2610.27491v1 Announce Type: cross Abstract: Real-world audio typically contains concurrent sound events, yet standard self-supervised methods treat each clip as an isolated training unit without explicitly modeling mixture--constituent relationships. We propose Mixture-to-Constituent Latent A…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv stat.ML
MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation Learning