EngravingGNN: A Hybrid Graph Neural Network for End-to-End Piano Score Engraving
This addresses the mostly unexplored problem of creating human-readable musical scores for piano music, which is incremental as it builds on existing subtask methods with a unified approach.
The paper tackled the problem of automatic music engraving for piano scores by formalizing it as interdependent subtasks and proposing a unified graph neural network framework, achieving good accuracy across all subtasks on diverse piano corpora compared to specialized systems.
This paper focuses on automatic music engraving, i.e., the creation of a humanly-readable musical score from musical content. This step is fundamental for all applications that include a human player, but it remains a mostly unexplored topic in symbolic music processing. In this work, we formalize the problem as a collection of interdependent subtasks, and propose a unified graph neural network (GNN) framework that targets the case of piano music and quantized symbolic input. Our method employs a multi-task GNN to jointly predict voice connections, staff assignments, pitch spelling, key signature, stem direction, octave shifts, and clef signs. A dedicated postprocessing pipeline generates print-ready MusicXML/MEI outputs. Comprehensive evaluation on two diverse piano corpora (J-Pop and DCML Romantic) demonstrates that our unified model achieves good accuracy across all subtasks, compared to existing systems that only specialize in specific subtasks. These results indicate that a shared GNN encoder with lightweight task-specific decoders in a multi-task setting offers a scalable and effective solution for automatic music engraving.