{"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/voice-separation-with-an-unknown-number-of","title":"Voice Separation with an Unknown Number of Multiple Speakers","arxiv_id":"2003.01531","date":"2020-02-29","proceeding":"ICML 2020 1","authors":["Eliya Nachmani","Yossi Adi","Lior Wolf"],"abstract":"We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.","url_abs":"https://arxiv.org/abs/2003.01531v4","url_pdf":"https://arxiv.org/pdf/2003.01531v4.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":"voice-separation-with-an-unknown-number-of","repo_url":"https://github.com/facebookresearch/svoice","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"voice-separation-with-an-unknown-number-of","repo_url":"https://github.com/Mack189/gdprnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"voice-separation-with-an-unknown-number-of","repo_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"voice-separation-with-an-unknown-number-of","repo_url":"https://github.com/enk100/speaker_separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"prelu","method_name":"PReLU"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"upit","method_name":"uPIT"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"VSUNOS","rank_in_archive_order":12,"of":18,"metrics":{"SI-SDRi":"12.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"Gated DualPathRNN","rank_in_archive_order":25,"of":40,"metrics":{"SI-SDRi":"20.12"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-3mix","task":"Speech Separation","dataset":"WSJ0-3mix","model":"Gated DualPathRNN","rank_in_archive_order":9,"of":9,"metrics":{"SI-SDRi":"16.85"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-4mix","task":"Speech Separation","dataset":"WSJ0-4mix","model":"Gated DualPathRNN","rank_in_archive_order":2,"of":5,"metrics":{"SI-SDRi":"12.88"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-5mix","task":"Speech Separation","dataset":"WSJ0-5mix","model":"Gated DualPathRNN","rank_in_archive_order":5,"of":6,"metrics":{"SI-SDRi":"10.56"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.01531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01531"}},"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/enk100/speaker_separation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mack189/gdprnn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/muhammad-ahmed-ghani/svoice_demo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/svoice","reach":null}],"summary":{"ran":6,"ran_violates":1,"ran_honours":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":12,"ran":9,"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":9,"samples":[{"code_sha256_prefix":"173650e5ae028b2f","entry":"ByPass","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"173650e5ae028b2f"}},{"code_sha256_prefix":"3b1d338215096fe7","entry":"DPMulCat","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3b1d338215096fe7"}},{"code_sha256_prefix":"5f72b86aea22a846","entry":"Decoder","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5f72b86aea22a846"}},{"code_sha256_prefix":"820a2cedf7915ddd","entry":"Encoder","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"820a2cedf7915ddd"}},{"code_sha256_prefix":"92748185c4ff9d16","entry":"MulCatBlock","repo":"facebookresearch/svoice","repo_kind":"official","path":"svoice/models/swave.py","file_url":"https://github.com/facebookresearch/svoice/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"92748185c4ff9d16"}},{"code_sha256_prefix":"facca3bf4fbfc471","entry":"Separator","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"facca3bf4fbfc471"}},{"code_sha256_prefix":"891e417fc38edeb0","entry":"cal_SISNR","repo":"Mack189/gdprnn","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/Mack189/gdprnn/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"891e417fc38edeb0"}},{"code_sha256_prefix":"ca6c3339d98f2a2c","entry":"cal_SISNRi","repo":"Mack189/gdprnn","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/Mack189/gdprnn/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca6c3339d98f2a2c"}},{"code_sha256_prefix":"ccacfa5207d7243d","entry":"capture_init","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ccacfa5207d7243d"}},{"code_sha256_prefix":"9c926905c0e7a1c7","entry":"overlap_and_add","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9c926905c0e7a1c7"}},{"code_sha256_prefix":"8967a79d23072fba","entry":"SWave","repo":"muhammad-ahmed-ghani/svoice_demo","repo_kind":"listed","path":"svoice/models/swave.py","file_url":"https://github.com/muhammad-ahmed-ghani/svoice_demo/blob/HEAD/svoice/models/swave.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8967a79d23072fba"}},{"code_sha256_prefix":"ecdad0e168981f5d","entry":"capture_init","repo":"Mack189/gdprnn","repo_kind":"listed","path":"src/models/swave.py","file_url":"https://github.com/Mack189/gdprnn/blob/HEAD/src/models/swave.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ecdad0e168981f5d"}},{"code_sha256_prefix":"1e3f6a2103e513ce","entry":"pad_list","repo":"Mack189/gdprnn","repo_kind":"listed","path":"preprocess.py","file_url":"https://github.com/Mack189/gdprnn/blob/HEAD/preprocess.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e3f6a2103e513ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}