{"id":"https://openalex.org/W3096915137","doi":"https://doi.org/10.1109/icassp39728.2021.9413627","title":"Single Channel Voice Separation for Unknown Number of Speakers Under Reverberant and Noisy Settings","display_name":"Single Channel Voice Separation for Unknown Number of Speakers Under Reverberant and Noisy Settings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3096915137","doi":"https://doi.org/10.1109/icassp39728.2021.9413627","mag":"3096915137"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083811924","display_name":"Eliya Nachmani","orcid":"https://orcid.org/0000-0003-4220-5672"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eliya Nachmani","raw_affiliation_strings":["Facebook AI Research","Tel Aviv University","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5080213609"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.1539,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39185016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"2","issue":null,"first_page":"3730","last_page":"3734"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.8122092485427856},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6705789566040039},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6553687453269958},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5807282328605652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5711381435394287},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5442796349525452},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5349518060684204},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46823614835739136},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2852049469947815},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1330251395702362},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13229697942733765},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07504233717918396}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.8122092485427856},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6705789566040039},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6553687453269958},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5807282328605652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5711381435394287},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5442796349525452},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5349518060684204},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46823614835739136},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2852049469947815},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1330251395702362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13229697942733765},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07504233717918396},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02329","pdf_url":"https://arxiv.org/pdf/2011.02329","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3096915137","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.02329.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.02329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02329","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/9vxp-we79","is_oa":true,"landing_page_url":"https://doi.org/10.17023/9vxp-we79","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02329","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02329","pdf_url":"https://arxiv.org/pdf/2011.02329","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096915137.pdf","grobid_xml":"https://content.openalex.org/works/W3096915137.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2123649031","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2502139158","https://openalex.org/W2558649592","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2771132365","https://openalex.org/W2891054259","https://openalex.org/W2891405874","https://openalex.org/W2899647550","https://openalex.org/W2938410884","https://openalex.org/W2952218014","https://openalex.org/W2963317762","https://openalex.org/W2963452667","https://openalex.org/W2972541922","https://openalex.org/W2972597685","https://openalex.org/W2972767900","https://openalex.org/W2996969697","https://openalex.org/W3008880747","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015338123","https://openalex.org/W3032969657","https://openalex.org/W3035268204","https://openalex.org/W3105169251","https://openalex.org/W6737894438","https://openalex.org/W6751512325","https://openalex.org/W6756022608","https://openalex.org/W6768815455","https://openalex.org/W6769767169","https://openalex.org/W6774687970","https://openalex.org/W6774995033","https://openalex.org/W6779752190"],"related_works":["https://openalex.org/W3161301466","https://openalex.org/W3107686772","https://openalex.org/W3171025350","https://openalex.org/W3210792213","https://openalex.org/W2578331995","https://openalex.org/W2952482988","https://openalex.org/W3029444444","https://openalex.org/W1148238185","https://openalex.org/W3185109982","https://openalex.org/W3091954663","https://openalex.org/W3126427729","https://openalex.org/W2612083379","https://openalex.org/W3037383957","https://openalex.org/W2735663686","https://openalex.org/W3162863443","https://openalex.org/W149543587","https://openalex.org/W1517146827","https://openalex.org/W3027465796","https://openalex.org/W2401186072","https://openalex.org/W2941551274"],"abstract_inverted_index":{"We":[0,67],"present":[1,97],"a":[2,26,62,92,98],"unified":[3],"network":[4],"for":[5],"voice":[6],"separation":[7,21,31,45],"of":[8,12,19,53,65,104],"an":[9],"unknown":[10],"number":[11,52,64],"speakers.":[13,66],"The":[14,30,47],"proposed":[15,70,83],"approach":[16,84],"is":[17,32,58,85],"composed":[18],"several":[20],"heads":[22],"optimized":[23],"together":[24,39],"with":[25,40],"speaker":[27],"classification":[28,48],"branch.":[29],"carried":[33],"out":[34],"in":[35,60],"the":[36,51,69,82,88],"time":[37],"domain,":[38],"parameter":[41],"sharing":[42],"between":[43],"all":[44],"heads.":[46],"branch":[49],"estimates":[50],"speakers":[54,109],"while":[55],"each":[56],"head":[57],"specialized":[59],"separating":[61],"different":[63,108],"evaluate":[68],"model":[71,90],"under":[72],"both":[73],"clean":[74],"and":[75,101],"noisy":[76,100],"reverberant":[77,102],"settings.":[78],"Results":[79],"suggest":[80],"that":[81],"superior":[86],"to":[87,106],"baseline":[89],"by":[91],"significant":[93],"margin.":[94],"Additionally,":[95],"we":[96],"new":[99],"dataset":[103],"up":[105],"five":[107],"speaking":[110],"simultaneously.":[111]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}