{"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/speech-enhancement-and-dereverberation-with","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","arxiv_id":"2208.05830","date":"2022-08-11","proceeding":"IEEE/ACM Transactions on Audio, Speech, and Language Processing 2023 6","authors":["Julius Richter","Simon Welker","Jean-Marie Lemercier","Bunlong Lay","Timo Gerkmann"],"abstract":"In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve into an extensive theoretical examination of its implications. Opposed to usual conditional generation tasks, we do not start the reverse process from pure Gaussian noise but from a mixture of noisy speech and Gaussian noise. This matches our forward process which moves from clean speech to noisy speech by including a drift term. We show that this procedure enables using only 30 diffusion steps to generate high-quality clean speech estimates. By adapting the network architecture, we are able to significantly improve the speech enhancement performance, indicating that the network, rather than the formalism, was the main limitation of our original approach. In an extensive cross-dataset evaluation, we show that the improved method can compete with recent discriminative models and achieves better generalization when evaluating on a different corpus than used for training. We complement the results with an instrumental evaluation using real-world noisy recordings and a listening experiment, in which our proposed method is rated best. Examining different sampler configurations for solving the reverse process allows us to balance the performance and computational speed of the proposed method. Moreover, we show that the proposed method is also suitable for dereverberation and thus not limited to additive background noise removal. Code and audio examples are available online, see https://github.com/sp-uhh/sgmse","url_abs":"https://arxiv.org/abs/2208.05830v2","url_pdf":"https://arxiv.org/pdf/2208.05830v2.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":"speech-enhancement-and-dereverberation-with","repo_url":"https://github.com/sp-uhh/sgmse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-dereverberation","task_name":"Speech Dereverberation"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[{"slug":"reverb-wsj0","name":"Reverb-WSJ0","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-dereverberation-on-ears-reverb","task":"Speech Dereverberation","dataset":"EARS-Reverb","model":"SGMSE+","rank_in_archive_order":1,"of":1,"metrics":{"ESTOI":"0.85","MOS Reverb":"4.73","PESQ-WB":"3.03","SI-SDR":"5.79","SIGMOS":"3.49"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-ears-wham","task":"Speech Enhancement","dataset":"EARS-WHAM","model":"SGMSE+","rank_in_archive_order":2,"of":6,"metrics":{"DNSMOS":"3.88","ESTOI":"0.73","PESQ-WB":"2.50","POLQA":"3.40","SI-SDR":"16.78","SIGMOS":"3.41"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"SGMSE+ (Diffusion Model)","rank_in_archive_order":38,"of":42,"metrics":{"PESQ (wb)":"2.93"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.05830","atlas_url":"https://app.syntology.ai/?focus=2208.05830","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2208.05830"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2208.05830\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2208.05830"},"call":"get_concepts_for_paper(arxiv_id=\"2208.05830\")"}],"by_repo":[{"repo":"sp-uhh/sgmse","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2406.06185"],"harvested_for_calls":[{"arxiv_id":"2406.06185","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2406.06185"},"call":"get_harvested_code_for_paper(arxiv_id=\"2406.06185\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"abca56213f2298ba323c512be446cdafa9ca86a2e4ca1f5743597bf09fa7d16a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}