Music102: An $D_{12}$-equivariant transformer for chord progression accompaniment

TL;DR

Music102 is a novel $D_{12}$-equivariant transformer model that improves chord progression accompaniment by embedding musical symmetries into its architecture, leading to better performance on the POP909 dataset.

Contribution

The paper introduces a $D_{12}$-equivariant transformer that encodes musical symmetries, advancing neural models for symbolic music analysis and generation.

Findings

Music102 outperforms Music101 in accuracy metrics.

The model uses fewer parameters than previous approaches.

It demonstrates the effectiveness of equivariance in musical modeling.

Abstract

We present Music102, an advanced model aimed at enhancing chord progression accompaniment through a $D_{12}$-equivariant transformer. Inspired by group theory and symbolic music structures, Music102 leverages musical symmetry--such as transposition and reflection operations--integrating these properties into the transformer architecture. By encoding prior music knowledge, the model maintains equivariance across both melody and chord sequences. The POP909 dataset was employed to train and evaluate Music102, revealing significant improvements over the non-equivariant Music101 prototype Music101 in both weighted loss and exact accuracy metrics, despite using fewer parameters. This work showcases the adaptability of self-attention mechanisms and layer normalization to the discrete musical domain, addressing challenges in computational music analysis. With its stable and flexible neural framework, Music102 sets the stage for further exploration in equivariant music generation and computational composition tools, bridging mathematical theory with practical music performance.