Metraipolis › archive › dc_2f8bb5efbd29

Iterative Audio Separation with Mixture Consistency via MIMO Model Extension — arXiv:2609.07226

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.07226
License (as archived): CC0-1.0
Archived: 2026-10-16T13:59:08.744Z
SHA-256 of the archived text: 8b12d896e9d4e812d6033c9ed91ba8ae319b1d1ee694204287a6d24023f4c158
Stable URL of this page: https://metraipolis.com/documento/dc_2f8bb5efbd29

How to cite

Iterative Audio Separation with Mixture Consistency via MIMO Model Extension — arXiv:2609.07226 — arXiv (en), https://arxiv.org/abs/2609.07226 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f8bb5efbd29 (Metraipolis archive dc_2f8bb5efbd29, sha256 8b12d896e9d4e812d6033c9ed91ba8ae319b1d1ee694204287a6d24023f4c158)

BibTeX

@misc{dc2f8bb5efbd29,
  title = {Iterative Audio Separation with Mixture Consistency via MIMO Model Extension — arXiv:2609.07226},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07226},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f8bb5efbd29; sha256 8b12d896e9d4e812d6033c9ed91ba8ae319b1d1ee694204287a6d24023f4c158},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07226. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes a general framework for stable and effective iterative audio separation with mixture consistency by extending source separation models to a multi-input multi-output (MIMO) configuration. In the field of audio separation, mixture consistency is an essential property for many applications that require accurate phase and timbral information of target sources. While iterative approaches such as diffusion models achieve perceptually superior results in speech enhancement or user-guided target source separation tasks, most existing methods focus on single-step separation with a single-input single-output (SISO) or single-input multi-output (SIMO) configuration through architectural improvements, since mixture-consistent audio separation is generally regarded as a regression problem that admits a unique solution. By extending these architectures to a MIMO configuration, we introduce iterative prediction without compromising the architectural advantages or the characteristics of mixture consistency. We conduct a comprehensive ablation study of combining the framework with discriminators and extending it to a generative model. Experimental results demonstrate significant performance improvements when applying the proposed framework to state-of-the-art separation models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.07226 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T13:39:43.210Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).