Structure-Aware Piano Accompaniment via Style Planning and Dataset-Aligned Pattern Retrieval
This addresses the challenge of creating structured and stylistically consistent piano accompaniments for musicians and composers, representing an incremental improvement through a hybrid method combining planning and retrieval.
The paper tackles the problem of generating symbolic piano accompaniments by decoupling high-level style planning from note-level realization, using a transformer to predict per-measure style plans and a retriever to select and reharmonize human-performed patterns, resulting in diverse long-form accompaniments with strong style realization.
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.