{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/robust-one-step-speech-enhancement-via-1","title":"Robust One-step Speech Enhancement via Consistency Distillation","arxiv_id":"2507.05688","date":"2025-07-08","proceeding":null,"authors":["Liang Xu","Longfei Felix Yan","W. Bastiaan Kleijn"],"abstract":"Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by distilling a one-step consistency model from a multi-step diffusion-based teacher model. However, distilled consistency models are inherently biased towards the sampling trajectory of the teacher model, making them less robust to noise and prone to inheriting inaccuracies from the teacher model. To address this limitation, we propose ROSE-CD: Robust One-step Speech Enhancement via Consistency Distillation, a novel approach for distilling a one-step consistency model. Specifically, we introduce a randomized learning trajectory to improve the model's robustness to noise. Furthermore, we jointly optimize the one-step model with two time-domain auxiliary losses, enabling it to recover from teacher-induced errors and surpass the teacher model in overall performance. This is the first pure one-step consistency distillation model for diffusion-based speech enhancement, achieving 54 times faster inference speed and superior performance compared to its 30-step teacher model. Experiments on the VoiceBank-DEMAND dataset demonstrate that the proposed model achieves state-of-the-art performance in terms of speech quality. Moreover, its generalization ability is validated on both an out-of-domain dataset and real-world noisy recordings.","url_abs":"https://arxiv.org/abs/2507.05688v1","url_pdf":"https://arxiv.org/pdf/2507.05688v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-one-step-speech-enhancement-via-1","repo_url":"https://github.com/LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[{"method_slug":"cm","method_name":"Consistency Models"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"ROSE-CD(PESQ)","rank_in_archive_order":1,"of":42,"metrics":{"CBAK":"3.37","COVL":"4.30","CSIG":"4.63","ESTOI":"0.83","PESQ (wb)":"3.99","Para. (M)":"65","SI-SDR":"0.40","SSNR":"0.927","STOI":"92.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"ROSE-CD","rank_in_archive_order":13,"of":42,"metrics":{"CBAK":"3.33","COVL":"4.04","CSIG":"4.523","ESTOI":"0.87","PESQ (wb)":"3.49","Para. (M)":"65","SI-SDR":"17.80","SSNR":"3.34","STOI":"94.73"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-voicebank-demand-2","task":"Speech Enhancement","dataset":"VoiceBank+DEMAND","model":"ROSE-CD","rank_in_archive_order":1,"of":2,"metrics":{"DNSMOS":"3.48","DNSMOS BAK":"4.34","DNSMOS OVRL":"3.70","DNSMOS SIG":"4.02","ESTOI":"0.87","PESQ":"3.49","SI-SDR":"17.80"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-voicebank-demand-2","task":"Speech Enhancement","dataset":"VoiceBank+DEMAND","model":"rose_cd(PESQ )","rank_in_archive_order":2,"of":2,"metrics":{"DNSMOS":"3.01","DNSMOS BAK":"4.29","DNSMOS OVRL":"3.28","DNSMOS SIG":"3.52","ESTOI":"0.83","PESQ":"3.99","PESQ (wb)":"3.99","SI-SDR":"0.40"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1439b3eecc82b807cc5bdf9f860257a990e9d362d5978ce5114affa31de55dc4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}