Papers › Contrastive Learning of Musical Representations

Contrastive Learning of Musical Representations

17 Mar 2021arXiv:2103.09410archive 2025-07-28

Janne Spijkervet, John Ashley Burgoyne

While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large chain of audio data augmentations to form a simple framework for self-supervised, contrastive learning of musical representations: CLMR. This approach works on raw time-domain music data and requires no labels to learn useful representations. We evaluate CLMR in the downstream task of music classification on the MagnaTagATune and Million Song datasets and present an ablation study to test which of our music-related innovations over SimCLR are most effective. A linear classifier trained on the proposed representations achieves a higher average precision than supervised models on the MagnaTagATune dataset, and performs comparably on the Million Song dataset. Moreover, we show that CLMR's representations are transferable using out-of-domain datasets, indicating that our method has strong generalisability in music classification. Lastly, we show that the proposed method allows data-efficient learning on smaller labeled datasets: we achieve an average precision of 33.1% despite using only 259 labeled songs in the MagnaTagATune dataset (1% of the full dataset) during linear evaluation. To foster reproducibility and future research on self-supervised learning in music, we publicly release the pre-trained models and the source code of all experiments of this paper.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

spijkervet/CLMR officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive Learning Linear evaluation Music Auto-Tagging Music Classification Self-Supervised Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Music Auto-Tagging	MagnaTagATune	CLMR	PR-AUC	35.4	#3 of 3	Archive leaderboard	report
Music Auto-Tagging	MagnaTagATune	CLMR	ROC AUC	88.5	#3 of 3	Archive leaderboard	report
Music Auto-Tagging	Million Song Dataset	CLMR	PR-AUC	25.0	#1 of 2	Archive leaderboard	report
Music Auto-Tagging	Million Song Dataset	CLMR (ours)	ROC-AUC	85.7	#2 of 2	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block ColorJitter Contrastive Learning Convolution Dense Connections Feedforward Network Global Average Pooling Kaiming Initialization Max Pooling NT-Xent ReLU Residual Block Residual Connection SimCLR

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections