Skip to content
conftrace_
2025 ICML ICML 2025

Supervised Contrastive Learning from Weakly-Labeled Audio Segments for Musical Version Matching

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Joan Serrà, R. Oguz Araz, Dmitry Bogdanov, Yuki Mitsufuji

Topics

Machine Learning > Learning Types > Contrastive Learning Machine Learning > Learning Types > Weakly Supervised Learning Deep Learning > Learning Types > Contrastive Learning

Keywords

state-of-the-art performance contrastive loss segment-level matching musical version detection pairwise distance reductions weakly-labeled segments
Download PDF