Contrastive Learning of Musical Representations

TL;DR

This paper introduces CLMR, a self-supervised contrastive learning framework for music representations that works on raw audio data, requiring no labels, and demonstrates strong transferability and data efficiency in music classification tasks.

Contribution

The paper presents CLMR, a novel contrastive learning approach for music that leverages new audio augmentations and achieves state-of-the-art results without labeled data.

Findings

Outperforms supervised models on MagnaTagATune

Achieves comparable results on Million Song dataset

Enables effective learning with only 1% labeled data

Abstract

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.