FLOMSS: Generative Music Source Separation by Flow Matching
Shuyang Cui, Zhi Zhong, Keisuke Toyama, Koichi Saito, Qiyu Wu, Yukara Ikemiya and 7 more
Collected · snapshot shipped with the site build, not a live feed
Abstract · as written by the authors
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/
This is the original abstract from arXiv. It has not been summarised, translated or rewritten.
Terms in plain language
AutomaticMade by matching the words of the title and abstract against a fixed list of definitions. It does not read the paper and does not change the abstract above.
- embedding
- a list of numbers that captures the meaning of a piece of text, an image or other data, so that similar items get similar lists.
- benchmark
- a fixed set of tasks or questions used to compare models on the same test.