{"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/many-speakers-single-channel-speech","title":"Many-Speakers Single Channel Speech Separation with Optimal Permutation Training","arxiv_id":"2104.08955","date":"2021-04-18","proceeding":null,"authors":["Shaked Dovrat","Eliya Nachmani","Lior Wolf"],"abstract":"Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which rely on the Permutation Invariant Loss (PIT). In this work, we present a permutation invariant training that employs the Hungarian algorithm in order to train with an $O(C^3)$ time complexity, where $C$ is the number of speakers, in comparison to $O(C!)$ of PIT based methods. Furthermore, we present a modified architecture that can handle the increased number of speakers. Our approach separates up to $20$ speakers and improves the previous results for large $C$ by a wide margin.","url_abs":"https://arxiv.org/abs/2104.08955v4","url_pdf":"https://arxiv.org/pdf/2104.08955v4.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":"many-speakers-single-channel-speech","repo_url":"https://github.com/shakeddovrat/librimix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-libri10mix","task":"Speech Separation","dataset":"Libri10Mix","model":"Hungarian PIT","rank_in_archive_order":3,"of":3,"metrics":{"SI-SDRi":"7.78"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-libri15mix","task":"Speech Separation","dataset":"Libri15Mix","model":"Hungarian PIT","rank_in_archive_order":1,"of":1,"metrics":{"SI-SDRi":"5.66"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-libri20mix","task":"Speech Separation","dataset":"Libri20Mix","model":"Hungarian PIT","rank_in_archive_order":2,"of":2,"metrics":{"SI-SDRi":"4.26"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-libri5mix","task":"Speech Separation","dataset":"Libri5Mix","model":"Hungarian PIT","rank_in_archive_order":4,"of":4,"metrics":{"SI-SDRi":"12.72"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-5mix","task":"Speech Separation","dataset":"WSJ0-5mix","model":"Hungarian PIT","rank_in_archive_order":2,"of":6,"metrics":{"SI-SDRi":"13.22"},"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":"shakeddovrat/librimix","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":"274a3c82ce0639dbe18976e23c84abfb24fa705544ec1fd948c9052bad9e8fc0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}