Structure-Aware Piano Accompaniment via Style Planning and Dataset-Aligned Pattern Retrieval

TL;DR

This paper presents a novel structure-aware system for symbolic piano accompaniment that combines high-level style planning with dataset-aligned pattern retrieval, enabling diverse and stylistically consistent accompaniments.

Contribution

It introduces a decoupled approach using a transformer for style planning and a retrieval system for pattern selection, enhancing flexibility and style fidelity in piano accompaniment generation.

Findings

Transformer-guided retrieval produces diverse accompaniments.

The system achieves strong style realization and structural coherence.

Experimental results validate the effectiveness of the approach.

Abstract

We introduce a structure-aware approach for symbolic piano accompaniment that decouples high-level planning from note-level realization. A lightweight transformer predicts an interpretable, per-measure style plan conditioned on section/phrase structure and functional harmony, and a retriever then selects and reharmonizes human-performed piano patterns from a corpus. We formulate retrieval as pattern matching under an explicit energy with terms for harmonic feasibility, structural-role compatibility, voice-leading continuity, style preferences, and repetition control. Given a structured lead sheet and optional keyword prompts, the system generates piano-accompaniment MIDI. In our experiments, transformer style-planner-guided retrieval produces diverse long-form accompaniments with strong style realization. We further analyze planner ablations and quantify inter-style isolation. Experimental results demonstrate the effectiveness of our inference-time approach for piano accompaniment generation.