Large-Scale Weakly-Supervised Content Embeddings for Music Recommendation and Tagging

We explore content-based representation learning strategies tailored for large-scale, uncurated music collections that afford only weak supervision through unstructured natural language metadata and colisten statistics. At the core is a hybrid training scheme that uses classification and metric learning losses to incorporate both metadata-derived text labels and aggregate co-listen supervisory signals into a single convolutional model. The resulting joint text and audio content embedding defines a similarity metric and supports prediction of semantic text labels using a vocabulary of unprecedented granularity, which we refine using a novel word-sense disambiguation procedure. As input to simple classifier architectures, our representation achieves state-of-the-art performance on two music tagging benchmarks.

Paper

Full text

PDF

Large-Scale Weakly-Supervised Content Embeddings for Music Recommendation and Tagging

Semantic Scholar · Computer Science · 2020

Abstract

We explore content-based representation learning strategies tailored for large-scale, uncurated music collections that afford only weak supervision through unstructured natural language metadata and colisten statistics. At the core is a hybrid training scheme that uses classification and metric learning losses to incorporate both metadata-derived text labels and aggregate co-listen supervisory signals into a single convolutional model. The resulting joint text and audio content embedding defines a similarity metric and supports prediction of semantic text labels using a vocabulary of unprecedented granularity, which we refine using a novel word-sense disambiguation procedure. As input to simple classifier architectures, our representation achieves state-of-the-art performance on two music tagging benchmarks.

Similar papers

© 2026 NYSGPT2525 LLC