{"ID":2859328,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.05881","arxiv_id":"2510.05881","title":"Segment-Factorized Full-Song Generation on Symbolic Piano Music","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.","short_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...","url_abs":"https://arxiv.org/abs/2510.05881","url_pdf":"https://arxiv.org/pdf/2510.05881v1","authors":"[\"Ping-Yi Chen\",\"Chih-Pin Tan\",\"Yi-Hsuan Yang\"]","published":"2025-10-07T12:54:44Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\",\"cs.LG\",\"cs.MM\",\"eess.AS\"]","methods":"[]","has_code":false}