{"ID":6023496,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-10T09:52:53.206514518Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06088","arxiv_id":"2607.06088","title":"Flow Matching-Based Speech Source Separation with Best-of-N Biometric Sampling","abstract":"Single-channel speech separation remains challenging for real-world deployment due to source permutation ambiguity, sampling variability of generative models, and the difficulty of processing long recordings with chunk-wise inference. We address these issues with a conditional flow-matching-based method that produces an ordered two-source output conditioned on the mixture. A frozen speaker encoder defines the source order during training and is reused at inference for biometric best-of-$N$ candidate selection and chunk-level channel alignment. We evaluate separation quality on Libri2Mix benchmark using SI-SDR, PESQ, and ESTOI, and measure downstream impact using cpWER for automatic speech recognition and EER for speaker verification. The results show that the proposed Transformer U-Net variant is competitive with strong baselines in objective separation metrics and achieves the lowest downstream automatic speech recognition and speaker verification error rates in all evaluated settings.","short_abstract":"Single-channel speech separation remains challenging for real-world deployment due to source permutation ambiguity, sampling variability of generative models, and the difficulty of processing long recordings with chunk-wise inference. We address these issues with a conditional flow-matching-based method that produces a...","url_abs":"https://arxiv.org/abs/2607.06088","url_pdf":"https://arxiv.org/pdf/2607.06088v1","authors":"[\"Anastasia Zorkina\",\"Alexandr Anikin\",\"Nikita Khmelev\",\"Anastasiya Korenevskaya\",\"Sergey Novoselov\",\"Vladimir Volokhov\",\"Maxim Korenevsky\",\"Yuriy Matveev\"]","published":"2026-07-07T10:00:23Z","proceeding":"cs.SD","tasks":"[\"cs.SD\"]","methods":"[\"Transformer\"]","has_code":false}