Pianoroll-Event: A Novel Score Representation for Symbolic Music

TL;DR

Symbolic music encoding struggles to balance spatial structure with encoding efficiency. The authors introduce Pianoroll-Event, a unified representation that transforms pianoroll frames into four event types—Frame, Gap, Pattern, and Musical Structure—preserving temporal dependencies while reducing sequence length and vocabulary size. They demonstrate encoding efficiency gains of $1.36\times$ to $7.16\times$ over representative methods and show state-of-the-art generation quality across multiple autoregressive architectures in both objective metrics and human evaluations. This approach provides a scalable, structure-aware encoding that improves both compression and musicality, with broad implications for scalable symbolic-music modeling and generation.

Abstract

Symbolic music representation is a fundamental challenge in computational musicology. While grid-based representations effectively preserve pitch-time spatial correspondence, their inherent data sparsity leads to low encoding efficiency. Discrete-event representations achieve compact encoding but fail to adequately capture structural invariance and spatial locality. To address these complementary limitations, we propose Pianoroll-Event, a novel encoding scheme that describes pianoroll representations through events, combining structural properties with encoding efficiency while maintaining temporal dependencies and local spatial patterns. Specifically, we design four complementary event types: Frame Events for temporal boundaries, Gap Events for sparse regions, Pattern Events for note patterns, and Musical Structure Events for musical metadata. Pianoroll-Event strikes an effective balance between sequence length and vocabulary size, improving encoding efficiency by 1.36\times to 7.16\times over representative discrete sequence methods. Experiments across multiple autoregressive architectures show models using our representation consistently outperform baselines in both quantitative and human evaluations.

Figures (1)

• Figure 1: The process of converting pianoroll representation into pianoroll-events. Through frame segmentation, partitioning, and compression operations, the pianoroll is transformed into a sequence of pianoroll-events containing diverse event types.