{"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/unsupervised-deep-clustering-for-source","title":"Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information","arxiv_id":"1811.01531","date":"2018-11-05","proceeding":null,"authors":["Efthymios Tzinis","Shrikant Venkataramani","Paris Smaragdis"],"abstract":"We present a monophonic source separation system that is trained by only\nobserving mixtures with no ground truth separation information. We use a deep\nclustering approach which trains on multi-channel mixtures and learns to\nproject spectrogram bins to source clusters that correlate with various spatial\nfeatures. We show that using such a training process we can obtain separation\nperformance that is as good as making use of ground truth separation\ninformation. Once trained, this system is capable of performing sound\nseparation on monophonic inputs, despite having learned how to do so using\nmulti-channel recordings.","url_abs":"http://arxiv.org/abs/1811.01531v2","url_pdf":"http://arxiv.org/pdf/1811.01531v2.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":"unsupervised-deep-clustering-for-source","repo_url":"https://github.com/etzinis/unsupervised_spatial_dc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"multi-speaker-source-separation","task_name":"Multi-Speaker Source Separation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.01531"}},"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/etzinis/unsupervised_spatial_dc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":6,"ran":1,"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":"971fc60507ed355e","entry":"normalize_tensor_wav","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/data_loaders/wham.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/data_loaders/wham.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"971fc60507ed355e"}},{"code_sha256_prefix":"75bf976559cf2c0d","entry":"create_dataset_name","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/data_generator/dataset_storage.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/data_generator/dataset_storage.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":"75bf976559cf2c0d"}},{"code_sha256_prefix":"e774931e287d45ad","entry":"efficient_frobenius","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/dnn/losses/affinity_approximation.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/dnn/losses/affinity_approximation.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":"e774931e287d45ad"}},{"code_sha256_prefix":"c9cfa0aebd00cf8b","entry":"frobenius_naive","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/dnn/losses/affinity_approximation.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/dnn/losses/affinity_approximation.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":"c9cfa0aebd00cf8b"}},{"code_sha256_prefix":"8efe3077c248ddec","entry":"get_mixture_name_and_data_to_save","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/data_generator/dataset_storage.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/data_generator/dataset_storage.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":"8efe3077c248ddec"}},{"code_sha256_prefix":"9b4f013af48f8852","entry":"paris_naive","repo":"etzinis/unsupervised_spatial_dc","repo_kind":"official","path":"spatial_two_mics/dnn/losses/affinity_approximation.py","file_url":"https://github.com/etzinis/unsupervised_spatial_dc/blob/HEAD/spatial_two_mics/dnn/losses/affinity_approximation.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":"9b4f013af48f8852"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}