| title | FLOMSS: Generative Music Source Separation by Flow Matching |
|---|---|
| authors | Shuyang Cui, Zhi Zhong, Keisuke Toyama, Koichi Saito, Qiyu Wu, Yukara Ikemiya, Junghyun Koo, Kin Wai Cheuk, Woosung Choi, Giorgio Fabbro, Wei-Hsiang Liao, Shusuke Takahashi, Yuki Mitsufuji |
| date | 2026-10-14 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.17821 |
| upvotes | 12 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Music source separation (MSS) has been conventionally addressed by discriminative methods. Recently, flow matching has emerged as a strong generative paradigm for modeling complex data distributions, with successful applications across diverse domains. These advances motivate us to systematically investigate flow matching for MSS in a four-source (Vocals, Bass, Drums, Other) setting in full-band stereo. Specifically, we investigate prediction targets, flow paths, single-source versus multi-source modeling, and mixture consistency constraints. Beyond the signal-level metrics commonly used for MSS, such as signal-to-distortion ratio, we further evaluate MSS methods using embedding-based metrics, as well as a listening test, providing a comprehensive benchmark. On MUSDB18-HQ, our proposed model exhibits competitive performance in both objective and subjective tests, highlighting the potential of flow matching for generative MSS. Demo: https://ik4sumii.github.io/FLOMSS/ |
cite
@misc{cui2026flomss,
title={FLOMSS: Generative Music Source Separation by Flow Matching},
author={Shuyang Cui and Zhi Zhong and Keisuke Toyama and Koichi Saito and Qiyu Wu and Yukara Ikemiya and Junghyun Koo and Kin Wai Cheuk and Woosung Choi and Giorgio Fabbro and Wei-Hsiang Liao and Shusuke Takahashi and Yuki Mitsufuji},
year={2026},
eprint={2610.17821},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.17821}
}