{"ID":3084767,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T01:45:54.587002255Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05575","arxiv_id":"2606.05575","title":"SB-RF: Schrödinger Bridge Rectified Flow for One-Step Robust Speech Enhancement","abstract":"Generative models have shown impressive results in speech enhancement but often suffer from multi-step inference. We propose SB-RF, a one-step generative framework integrating Rectified Flow (RF) with Schrödinger Bridge (SB) theory. SB-RF constructs a conditional bridge between clean and noisy speech distributions via entropy-regularized optimal transport. By aligning SB trajectories with the optimal transport geodesic through the velocity-matching objective of RF, SB-RF enables high-quality enhancement with one-step generation. Experiments demonstrate that SB-RF achieves leading performance among generative methods on the VoiceBank-DEMAND benchmark. Furthermore, to fully assess performance in challenging real-world scenarios, we evaluate SB-RF on a simulated low signal-to-noise ratio test set using an expanded training dataset. Under these conditions, SB-RF exhibits strong and competitive robustness with high efficiency, validating its potential for real-world applications.","short_abstract":"Generative models have shown impressive results in speech enhancement but often suffer from multi-step inference. We propose SB-RF, a one-step generative framework integrating Rectified Flow (RF) with Schrödinger Bridge (SB) theory. SB-RF constructs a conditional bridge between clean and noisy speech distributions via...","url_abs":"https://arxiv.org/abs/2606.05575","url_pdf":"https://arxiv.org/pdf/2606.05575v1","authors":"[\"Caixia Lu\",\"Xueyang Lv\",\"Penglong Hu\",\"Jiaming Xu\"]","published":"2026-06-04T01:50:12Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}