{"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/adversarial-semi-supervised-audio-source","title":"Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction","arxiv_id":"1711.00048","date":"2017-10-31","proceeding":null,"authors":["Daniel Stoller","Sebastian Ewert","Simon Dixon"],"abstract":"The state of the art in music source separation employs neural networks\ntrained in a supervised fashion on multi-track databases to estimate the\nsources from a given mixture. With only few datasets available, often extensive\ndata augmentation is used to combat overfitting. Mixing random tracks, however,\ncan even reduce separation performance as instruments in real music are\nstrongly correlated. The key concept in our approach is that source estimates\nof an optimal separator should be indistinguishable from real source signals.\nBased on this idea, we drive the separator towards outputs deemed as realistic\nby discriminator networks that are trained to tell apart real from separator\nsamples. This way, we can also use unpaired source and mixture recordings\nwithout the drawbacks of creating unrealistic music mixtures. Our framework is\nwidely applicable as it does not assume a specific network architecture or\nnumber of sources. To our knowledge, this is the first adoption of adversarial\ntraining for music source separation. In a prototype experiment for singing\nvoice separation, separation performance increases with our approach compared\nto purely supervised training.","url_abs":"http://arxiv.org/abs/1711.00048v2","url_pdf":"http://arxiv.org/pdf/1711.00048v2.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":"adversarial-semi-supervised-audio-source","repo_url":"https://github.com/f90/AdversarialAudioSeparation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adversarial-semi-supervised-audio-source","repo_url":"https://github.com/NullspaceSF/AAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adversarial-semi-supervised-audio-source","repo_url":"https://github.com/NullspaceSF/DSSGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"music-source-separation","task_name":"Music Source Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.00048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.00048"}},"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/NullspaceSF/AAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NullspaceSF/DSSGAN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/f90/AdversarialAudioSeparation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1},"listed":{"samples":4,"ran":0,"repositories":2}},"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":"f2da58f9ec583bb7","entry":"create_critic","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Models/WGAN_Critic.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Models/WGAN_Critic.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":"f2da58f9ec583bb7"}},{"code_sha256_prefix":"d26c3a2e8e28a862","entry":"create_critic","repo":"NullspaceSF/DSSGAN","repo_kind":"listed","path":"Models/WGAN_Critic.py","file_url":"https://github.com/NullspaceSF/DSSGAN/blob/HEAD/Models/WGAN_Critic.py","link_basis":"harvester_set","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":"d26c3a2e8e28a862"}},{"code_sha256_prefix":"469716a01b7bf92f","entry":"crop","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Input/Input.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Input/Input.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":"469716a01b7bf92f"}},{"code_sha256_prefix":"8b5c1e48a63915a6","entry":"crop","repo":"NullspaceSF/AAS","repo_kind":"listed","path":"Utils.py","file_url":"https://github.com/NullspaceSF/AAS/blob/HEAD/Utils.py","link_basis":"harvester_set","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":"8b5c1e48a63915a6"}},{"code_sha256_prefix":"404b97b66e233e0d","entry":"getNumParams","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Utils.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Utils.py","link_basis":"harvester_set","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":"404b97b66e233e0d"}},{"code_sha256_prefix":"e119d722ad3969f8","entry":"getTrainableVariables","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Utils.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Utils.py","link_basis":"harvester_set","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":"e119d722ad3969f8"}},{"code_sha256_prefix":"d50210d9769f40fc","entry":"get_mp3_metadata","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Metadata.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Metadata.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":"d50210d9769f40fc"}},{"code_sha256_prefix":"74f62f7a310f111b","entry":"get_multitrack_input","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Input/Input.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Input/Input.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":"74f62f7a310f111b"}},{"code_sha256_prefix":"225ae974caab90cb","entry":"get_multitrack_input","repo":"NullspaceSF/AAS","repo_kind":"listed","path":"Input/Input.py","file_url":"https://github.com/NullspaceSF/AAS/blob/HEAD/Input/Input.py","link_basis":"harvester_set","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":"225ae974caab90cb"}},{"code_sha256_prefix":"80d5222f4f8e9ebf","entry":"get_multitrack_placeholders","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Input/Input.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Input/Input.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":"80d5222f4f8e9ebf"}},{"code_sha256_prefix":"460fd7a1f5e670de","entry":"get_multitrack_placeholders","repo":"NullspaceSF/AAS","repo_kind":"listed","path":"Input/Input.py","file_url":"https://github.com/NullspaceSF/AAS/blob/HEAD/Input/Input.py","link_basis":"harvester_set","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":"460fd7a1f5e670de"}},{"code_sha256_prefix":"5361990013803dce","entry":"seconds_to_min_sec","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Metadata.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Metadata.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":"5361990013803dce"}},{"code_sha256_prefix":"1835f4a216642e4b","entry":"timestamp_to_seconds","repo":"f90/AdversarialAudioSeparation","repo_kind":"official","path":"Metadata.py","file_url":"https://github.com/f90/AdversarialAudioSeparation/blob/HEAD/Metadata.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":"1835f4a216642e4b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}