{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/diffusion-based-generative-speech-source","title":"Diffusion-based Generative Speech Source Separation","arxiv_id":"2210.17327","date":"2022-10-31","proceeding":null,"authors":["Robin Scheibler","Youna Ji","Soo-Whan Chung","Jaeuk Byun","Soyeon Choe","Min-Seok Choi"],"abstract":"We propose DiffSep, a new single channel source separation method based on score-matching of a stochastic differential equation (SDE). We craft a tailored continuous time diffusion-mixing process starting from the separated sources and converging to a Gaussian distribution centered on their mixture. This formulation lets us apply the machinery of score-based generative modelling. First, we train a neural network to approximate the score function of the marginal probabilities or the diffusion-mixing process. Then, we use it to solve the reverse time SDE that progressively separates the sources starting from their mixture. We propose a modified training strategy to handle model mismatch and source permutation ambiguity. Experiments on the WSJ0 2mix dataset demonstrate the potential of the method. Furthermore, the method is also suitable for speech enhancement and shows performance competitive with prior work on the VoiceBank-DEMAND dataset.","url_abs":"https://arxiv.org/abs/2210.17327v2","url_pdf":"https://arxiv.org/pdf/2210.17327v2.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":"diffusion-based-generative-speech-source","repo_url":"https://github.com/fakufaku/diffusion-separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.17327","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.17327"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fakufaku/diffusion-separation","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3d8559d06e3b030c","entry":"scale_output","repo":"fakufaku/diffusion-separation","repo_kind":"listed","path":"separate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/separate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d8559d06e3b030c"}},{"code_sha256_prefix":"fa078ec7d64f76db","entry":"str_or_int","repo":"fakufaku/diffusion-separation","repo_kind":"listed","path":"separate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/separate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa078ec7d64f76db"}},{"code_sha256_prefix":"3f0ed50b8555a67e","entry":"summarize","repo":"fakufaku/diffusion-separation","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f0ed50b8555a67e"}},{"code_sha256_prefix":"0186314b1cbf6dc5","entry":"summarize","repo":"fakufaku/diffusion-separation","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/fakufaku/diffusion-separation/blob/HEAD/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0186314b1cbf6dc5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}