Melody Infilling with User-Provided Structural Context

TL;DR

This paper introduces a Transformer-based music score infilling model that incorporates user-provided structural information to generate higher-quality, style-consistent melodies by considering musical form and structure.

Contribution

It presents a novel structure-aware conditioning method with an attention-selecting module to improve music infilling by leveraging structural context.

Findings

Outperforms existing models in style and quality

Effectively utilizes structural information for better coherence

Generates melodies in pop style with higher subjective ratings

Abstract

This paper proposes a novel Transformer-based model for music score infilling, to generate a music passage that fills in the gap between given past and future contexts. While existing infilling approaches can generate a passage that connects smoothly locally with the given contexts, they do not take into account the musical form or structure of the music and may therefore generate overly smooth results. To address this issue, we propose a structure-aware conditioning approach that employs a novel attention-selecting module to supply user-provided structure-related information to the Transformer for infilling. With both objective and subjective evaluations, we show that the proposed model can harness the structural information effectively and generate melodies in the style of pop of higher quality than the two existing structure-agnostic infilling models.