Google Research

Large-Scale Weakly-Supervised Content Embeddingsfor Music Recommendation and Tagging

ICASSP 2020 (2020)


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 co-listen 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.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work