And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?

TL;DR

This paper presents a metric learning-based music version identification system that combines melodic, harmonic, rhythmic, and lyrical features, achieving state-of-the-art results and suggesting near-optimal performance potential.

Contribution

It introduces a simple yet effective model leveraging four musical dimensions for version identification, with lyrics as a key discriminative feature.

Findings

Achieved state-of-the-art performance on two datasets.

Demonstrated the complementarity of multiple musical features.

Proposed that combining these features can reach optimal performance.

Abstract

Version identification (VI) has seen substantial progress over the past few years. On the one hand, the introduction of the metric learning paradigm has favored the emergence of scalable yet accurate VI systems. On the other hand, using features focusing on specific aspects of musical pieces, such as melody, harmony, or lyrics, yielded interpretable and promising performances. In this work, we build upon these recent advances and propose a metric learning-based system systematically leveraging four dimensions commonly admitted to convey musical similarity between versions: melodic line, harmonic structure, rhythmic patterns, and lyrics. We describe our deliberately simple model architecture, and we show in particular that an approximated representation of the lyrics is an efficient proxy to discriminate between versions and non-versions. We then describe how these features complement each other and yield new state-of-the-art performances on two publicly available datasets. We finally suggest that a VI system using a combination of melodic, harmonic, rhythmic and lyrics features could theoretically reach the optimal performances obtainable on these datasets.