Self-Supervised Multi-View Learning for Disentangled Music Audio Representations

TL;DR

This work proposes a novel self-supervised multi-view learning framework for audio designed to incentivize separation between private and shared representation spaces and demonstrates the effectiveness of this method on audio disentanglement.

Abstract

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view redundancy to create pretext tasks. However, these approaches often produce entangled representations and lose view-specific information. We propose a novel self-supervised multi-view learning framework for audio designed to incentivize separation between private and shared representation spaces. A case study on audio disentanglement in a controlled setting demonstrates the effectiveness of our method.

Figures (2)

• Figure 1: Mutual information between latent dimensions ($z_k$) within each latent and the generative factors.
• Figure :