Segment-Factorized Full-Song Generation on Symbolic Piano Music
Sound
2025-10-08 v1 Artificial Intelligence
Machine Learning
Multimedia
Audio and Speech Processing
Abstract
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.
Cite
@article{arxiv.2510.05881,
title = {Segment-Factorized Full-Song Generation on Symbolic Piano Music},
author = {Ping-Yi Chen and Chih-Pin Tan and Yi-Hsuan Yang},
journal= {arXiv preprint arXiv:2510.05881},
year = {2025}
}
Comments
Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI for Music