arXiv Open Access 2025

Segment-Factorized Full-Song Generation on Symbolic Piano Music

Ping-Yi Chen Chih-Pin Tan Yi-Hsuan Yang

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.SD cs.AI cs.LG cs.MM eess.AS

Penulis (3)

Ping-Yi Chen

Chih-Pin Tan

Yi-Hsuan Yang

Format Sitasi

APA MLA BibTeX

Chen, P., Tan, C., Yang, Y. (2025). Segment-Factorized Full-Song Generation on Symbolic Piano Music. https://arxiv.org/abs/2510.05881

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓