Melody Infilling with User-Provided Structural Context
This work addresses the issue of overly smooth and structurally incoherent music generation in melody infilling for users in music composition and AI-assisted creativity, representing an incremental improvement by incorporating structural context into existing methods.
The paper tackles the problem of generating music passages that fill gaps between given past and future contexts, proposing a Transformer-based model with structure-aware conditioning that effectively uses user-provided structural information to produce higher-quality pop melodies compared to existing structure-agnostic models.
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.