MuseBarControl: Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss

TL;DR

This paper introduces MuseBarControl, a method that improves fine-grained bar-level control in symbolic music generation by using pre-training tasks and a counterfactual loss, resulting in more precise and quality-preserving outputs.

Contribution

It proposes a novel pre-training task and counterfactual loss to enable better bar-level control in symbolic music generation, overcoming limitations of traditional fine-tuning methods.

Findings

13.06% improvement in control accuracy

Enhanced control without sacrificing musical quality

Effective alignment of control signals with musical tokens

Abstract

Automatically generating symbolic music-music scores tailored to specific human needs-can be highly beneficial for musicians and enthusiasts. Recent studies have shown promising results using extensive datasets and advanced transformer architectures. However, these state-of-the-art models generally offer only basic control over aspects like tempo and style for the entire composition, lacking the ability to manage finer details, such as control at the level of individual bars. While fine-tuning a pre-trained symbolic music generation model might seem like a straightforward method for achieving this finer control, our research indicates challenges in this approach. The model often fails to respond adequately to new, fine-grained bar-level control signals. To address this, we propose two innovative solutions. First, we introduce a pre-training task designed to link control signals directly with corresponding musical tokens, which helps in achieving a more effective initialization for subsequent fine-tuning. Second, we implement a novel counterfactual loss that promotes better alignment between the generated music and the control prompts. Together, these techniques significantly enhance our ability to control music generation at the bar level, showing a 13.06\% improvement over conventional methods. Our subjective evaluations also confirm that this enhanced control does not compromise the musical quality of the original pre-trained generative model.