{"ID":2886693,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02071","arxiv_id":"2508.02071","title":"Unsupervised Multi-channel Speech Dereverberation via Diffusion","abstract":"We consider the problem of multi-channel single-speaker blind dereverberation, where multi-channel mixtures are used to recover the clean anechoic speech. To solve this problem, we propose USD-DPS, {U}nsupervised {S}peech {D}ereverberation via {D}iffusion {P}osterior {S}ampling. USD-DPS uses an unconditional clean speech diffusion model as a strong prior to solve the problem by posterior sampling. At each diffusion sampling step, we estimate all microphone channels' room impulse responses (RIRs), which are further used to enforce a multi-channel mixture consistency constraint for diffusion guidance. For multi-channel RIR estimation, we estimate reference-channel RIR by optimizing RIR parameters of a sub-band RIR signal model, with the Adam optimizer. We estimate non-reference channels' RIRs analytically using forward convolutive prediction (FCP). We found that this combination provides a good balance between sampling efficiency and RIR prior modeling, which shows superior performance among unsupervised dereverberation approaches. An audio demo page is provided in https://usddps.github.io/USDDPS_demo/.","short_abstract":"We consider the problem of multi-channel single-speaker blind dereverberation, where multi-channel mixtures are used to recover the clean anechoic speech. To solve this problem, we propose USD-DPS, {U}nsupervised {S}peech {D}ereverberation via {D}iffusion {P}osterior {S}ampling. USD-DPS uses an unconditional clean spee...","url_abs":"https://arxiv.org/abs/2508.02071","url_pdf":"https://arxiv.org/pdf/2508.02071v1","authors":"[\"Yulun Wu\",\"Zhongweiyang Xu\",\"Jianchong Chen\",\"Zhong-Qiu Wang\",\"Romit Roy Choudhury\"]","published":"2025-08-04T05:22:38Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[\"Diffusion Model\"]","has_code":false}