{"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/the-cone-of-silence-speech-separation-by","title":"The Cone of Silence: Speech Separation by Localization","arxiv_id":"2010.06007","date":"2020-10-12","proceeding":"NeurIPS 2020 12","authors":["Teerapat Jenrungrot","Vivek Jayaram","Steve Seitz","Ira Kemelmacher-Shlizerman"],"abstract":"Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core of our method is a deep network, in the waveform domain, which isolates sources within an angular region $\\theta \\pm w/2$, given an angle of interest $\\theta$ and angular window size $w$. By exponentially decreasing $w$, we can perform a binary search to localize and separate all sources in logarithmic time. Our algorithm allows for an arbitrary number of potentially moving speakers at test time, including more speakers than seen during training. Experiments demonstrate state-of-the-art performance for both source separation and source localization, particularly in high levels of background noise.","url_abs":"https://arxiv.org/abs/2010.06007v1","url_pdf":"https://arxiv.org/pdf/2010.06007v1.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":"the-cone-of-silence-speech-separation-by","repo_url":"https://github.com/vivjay30/Cone-of-Silence","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.06007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06007"}},"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/vivjay30/Cone-of-Silence","reach":null}],"summary":{"ran":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"bdd7e1ced98c7e9c","entry":"CoSNetwork","repo":"vivjay30/Cone-of-Silence","repo_kind":"official","path":"cos/training/network.py","file_url":"https://github.com/vivjay30/Cone-of-Silence/blob/HEAD/cos/training/network.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdd7e1ced98c7e9c"}},{"code_sha256_prefix":"484cd671c584e223","entry":"center_trim","repo":"vivjay30/Cone-of-Silence","repo_kind":"official","path":"cos/training/network.py","file_url":"https://github.com/vivjay30/Cone-of-Silence/blob/HEAD/cos/training/network.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"484cd671c584e223"}},{"code_sha256_prefix":"36a315697716ef97","entry":"rescale_conv","repo":"vivjay30/Cone-of-Silence","repo_kind":"official","path":"cos/training/network.py","file_url":"https://github.com/vivjay30/Cone-of-Silence/blob/HEAD/cos/training/network.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":"36a315697716ef97"}},{"code_sha256_prefix":"6010024b9098c40f","entry":"rescale_module","repo":"vivjay30/Cone-of-Silence","repo_kind":"official","path":"cos/training/network.py","file_url":"https://github.com/vivjay30/Cone-of-Silence/blob/HEAD/cos/training/network.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":"6010024b9098c40f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}