{"ID":2884303,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06840","arxiv_id":"2508.06840","title":"FlowSE: Flow Matching-based Speech Enhancement","abstract":"Diffusion probabilistic models have shown impressive performance for speech enhancement, but they typically require 25 to 60 function evaluations in the inference phase, resulting in heavy computational complexity. Recently, a fine-tuning method was proposed to correct the reverse process, which significantly lowered the number of function evaluations (NFE). Flow matching is a method to train continuous normalizing flows which model probability paths from known distributions to unknown distributions including those described by diffusion processes. In this paper, we propose a speech enhancement based on conditional flow matching. The proposed method achieved the performance comparable to those for the diffusion-based speech enhancement with the NFE of 60 when the NFE was 5, and showed similar performance with the diffusion model correcting the reverse process at the same NFE from 1 to 5 without additional fine tuning procedure. We also have shown that the corresponding diffusion model derived from the conditional probability path with a modified optimal transport conditional vector field demonstrated similar performances with the NFE of 5 without any fine-tuning procedure.","short_abstract":"Diffusion probabilistic models have shown impressive performance for speech enhancement, but they typically require 25 to 60 function evaluations in the inference phase, resulting in heavy computational complexity. Recently, a fine-tuning method was proposed to correct the reverse process, which significantly lowered t...","url_abs":"https://arxiv.org/abs/2508.06840","url_pdf":"https://arxiv.org/pdf/2508.06840v1","authors":"[\"Seonggyu Lee\",\"Sein Cheong\",\"Sangwook Han\",\"Jong Won Shin\"]","published":"2025-08-09T05:45:17Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"eess.SP\"]","methods":"[\"Diffusion Model\"]","has_code":false}