Improving Music Performance Assessment with Contrastive Learning

TL;DR

This paper explores the use of contrastive learning to enhance automatic music performance assessment systems, achieving performance comparable or superior to state-of-the-art methods by improving latent space clustering.

Contribution

It introduces a weighted contrastive loss tailored for regression in MPA and demonstrates its effectiveness in improving assessment accuracy.

Findings

Contrastive learning improves MPA regression performance.

The proposed method surpasses state-of-the-art results.

Better class clustering in latent space enhances assessment reliability.

Abstract

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This study investigates contrastive learning as a potential method to improve existing MPA systems. Contrastive learning is a widely used technique in representation learning to learn a structured latent space capable of separately clustering multiple classes. It has been shown to produce state of the art results for image-based classification problems. We introduce a weighted contrastive loss suitable for regression tasks applied to a convolutional neural network and show that contrastive loss results in performance gains in regression tasks for MPA. Our results show that contrastive-based methods are able to match and exceed SoTA performance for MPA regression tasks by creating better class clusters within the latent space of the neural networks.