D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation From Lead sheet

TL;DR

D3PIA is a novel discrete diffusion model that generates piano accompaniments from lead sheets, effectively capturing local musical context and outperforming existing methods in fidelity and coherence.

Contribution

This paper introduces D3PIA, a discrete diffusion model with Neighborhood Attention for improved local context modeling in piano accompaniment generation from lead sheets.

Findings

D3PIA better preserves chord conditions than baselines.

D3PIA produces more musically coherent accompaniments.

Objective and subjective evaluations favor D3PIA over existing models.

Abstract

Generating piano accompaniments in the symbolic music domain is a challenging task that requires producing a complete piece of piano music from given melody and chord constraints, such as those provided by a lead sheet. In this paper, we propose a discrete diffusion-based piano accompaniment generation model, D3PIA, leveraging local alignment between lead sheet and accompaniment in piano-roll representation. D3PIA incorporates Neighborhood Attention (NA) to both encode the lead sheet and condition it for predicting note states in the piano accompaniment. This design enhances local contextual modeling by efficiently attending to nearby melody and chord conditions. We evaluate our model using the POP909 dataset, a widely used benchmark for piano accompaniment generation. Objective evaluation results demonstrate that D3PIA preserves chord conditions more faithfully compared to continuous diffusion-based and Transformer-based baselines. Furthermore, a subjective listening test indicates that D3PIA generates more musically coherent accompaniments than the comparison models.