{"ID":2866061,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21214","arxiv_id":"2509.21214","title":"MeanSE: Efficient Generative Speech Enhancement with Mean Flows","abstract":"Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, leading to high computational load and poor 1-NFE performance. In this paper, we propose MeanSE, an efficient generative speech enhancement model using mean flows, which models the average velocity field to achieve high-quality 1-NFE enhancement. Experimental results demonstrate that our proposed MeanSE significantly outperforms the flow matching baseline with a single NFE, exhibiting extremely better out-of-domain generalization capabilities.","short_abstract":"Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, leading to high computa...","url_abs":"https://arxiv.org/abs/2509.21214","url_pdf":"https://arxiv.org/pdf/2509.21214v1","authors":"[\"Jiahe Wang\",\"Hongyu Wang\",\"Wei Wang\",\"Lei Yang\",\"Chenda Li\",\"Wangyou Zhang\",\"Lufen Tan\",\"Yanmin Qian\"]","published":"2025-09-25T14:23:23Z","proceeding":"eess.AS","tasks":"[\"eess.AS\"]","methods":"[]","has_code":false}