Score Transformer: Generating Musical Score from Note-level Representation

TL;DR

This paper introduces a Transformer-based method for converting note-level musical representations into detailed visual scores, effectively capturing musical notation elements and outperforming existing approaches.

Contribution

The paper proposes a novel score token representation and a Transformer model to transcribe note-level music into comprehensive visual notation, addressing a gap in automated music score generation.

Findings

Significantly outperforms existing methods on 12 musical aspects

Effective notation-level token representation improves results

Proposed method accurately captures musical symbols and attributes

Abstract

In this paper, we explore the tokenized representation of musical scores using the Transformer model to automatically generate musical scores. Thus far, sequence models have yielded fruitful results with note-level (MIDI-equivalent) symbolic representations of music. Although the note-level representations can comprise sufficient information to reproduce music aurally, they cannot contain adequate information to represent music visually in terms of notation. Musical scores contain various musical symbols (e.g., clef, key signature, and notes) and attributes (e.g., stem direction, beam, and tie) that enable us to visually comprehend musical content. However, automated estimation of these elements has yet to be comprehensively addressed. In this paper, we first design score token representation corresponding to the various musical elements. We then train the Transformer model to transcribe note-level representation into appropriate music notation. Evaluations of popular piano scores show that the proposed method significantly outperforms existing methods on all 12 musical aspects that were investigated. We also explore an effective notation-level token representation to work with the model and determine that our proposed representation produces the steadiest results.