Segment-Factorized Full-Song Generation on Symbolic Piano Music
This addresses the challenge of AI-assisted music creation for composers and musicians, offering an interactive tool for co-creation, though it is incremental in its approach.
The paper tackles the problem of generating full symbolic piano songs by proposing a segmented model that accepts user-defined structures and optional seed segments, achieving higher quality and efficiency compared to prior work.
We propose the Segmented Full-Song Model (SFS) for symbolic full-song generation. The model accepts a user-provided song structure and an optional short seed segment that anchors the main idea around which the song is developed. By factorizing a song into segments and generating each one through selective attention to related segments, the model achieves higher quality and efficiency compared to prior work. To demonstrate its suitability for human-AI interaction, we further wrap SFS into a web application that enables users to iteratively co-create music on a piano roll with customizable structures and flexible ordering.