{"id":"https://openalex.org/W3008880747","doi":"https://doi.org/10.1109/taslp.2021.3099291","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","display_name":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3008880747","doi":"https://doi.org/10.1109/taslp.2021.3099291","mag":"3008880747"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3099291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3099291","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.08933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047639590"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":7.77489439,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98329179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"2840","last_page":"2849"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7242637276649475},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6975072622299194},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6941010355949402},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.639348030090332},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6170419454574585},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5981778502464294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5603778958320618},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.558330774307251},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4671482443809509},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4541144371032715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4192020893096924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37724733352661133},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16830968856811523},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08815038204193115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7242637276649475},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6975072622299194},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6941010355949402},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.639348030090332},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6170419454574585},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5981778502464294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5603778958320618},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.558330774307251},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4671482443809509},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4541144371032715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4192020893096924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37724733352661133},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16830968856811523},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08815038204193115},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2021.3099291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3099291","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2002.08933","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08933","pdf_url":"https://arxiv.org/pdf/2002.08933","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":"","raw_type":"text"},{"id":"mag:3008880747","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.08933.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.2002.08933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.08933","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.08933","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.08933","pdf_url":"https://arxiv.org/pdf/2002.08933","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1523691755","https://openalex.org/W1569447338","https://openalex.org/W1677182931","https://openalex.org/W1987906574","https://openalex.org/W2003167205","https://openalex.org/W2004407417","https://openalex.org/W2009974515","https://openalex.org/W2095705004","https://openalex.org/W2108255727","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2134383396","https://openalex.org/W2144763279","https://openalex.org/W2168793898","https://openalex.org/W2221409856","https://openalex.org/W2337770506","https://openalex.org/W2460742184","https://openalex.org/W2516890051","https://openalex.org/W2558649592","https://openalex.org/W2559280146","https://openalex.org/W2669032454","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2766953637","https://openalex.org/W2771585046","https://openalex.org/W2772138577","https://openalex.org/W2800022361","https://openalex.org/W2800664709","https://openalex.org/W2801839390","https://openalex.org/W2884797218","https://openalex.org/W2884941392","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2918296821","https://openalex.org/W2936302822","https://openalex.org/W2938646939","https://openalex.org/W2939771864","https://openalex.org/W2949382160","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962715207","https://openalex.org/W2962753171","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963840672","https://openalex.org/W2963921132","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2971458685","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W2980986990","https://openalex.org/W2996969697","https://openalex.org/W3004940340","https://openalex.org/W3008003372","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015390914","https://openalex.org/W3015794161","https://openalex.org/W3027008958","https://openalex.org/W3035268204","https://openalex.org/W3098166093","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6631302301","https://openalex.org/W6633847657","https://openalex.org/W6676302446","https://openalex.org/W6684458083","https://openalex.org/W6696085341","https://openalex.org/W6730692885","https://openalex.org/W6740674931","https://openalex.org/W6745136726","https://openalex.org/W6753550916","https://openalex.org/W6755462816","https://openalex.org/W6758474948","https://openalex.org/W6766320909","https://openalex.org/W6774995033","https://openalex.org/W6777776875","https://openalex.org/W6780226713","https://openalex.org/W6948320247"],"related_works":["https://openalex.org/W2952218014","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2460742184","https://openalex.org/W3185109982","https://openalex.org/W3015199127","https://openalex.org/W1494198834","https://openalex.org/W2962935966","https://openalex.org/W3035268204","https://openalex.org/W2972460025","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W1552314771","https://openalex.org/W2972541922","https://openalex.org/W2891405874","https://openalex.org/W2735663686","https://openalex.org/W3016232124","https://openalex.org/W2996969697","https://openalex.org/W2963403868","https://openalex.org/W2558649592"],"abstract_inverted_index":{"We":[0,102],"introduce":[1],"Wavesplit,":[2],"an":[3],"end-to-end":[4],"source":[5,19,24,48],"separation":[6,71],"system.":[7],"From":[8],"a":[9,15,45,68,105,132],"single":[10,133],"mixture,":[11],"the":[12,27,40,54,82,109],"model":[13,31],"infers":[14,44],"representation":[16],"for":[17],"each":[18,23],"and":[20,98,127],"then":[21],"estimates":[22],"signal":[25],"given":[26],"inferred":[28],"representations.":[29],"The":[30],"is":[32,118],"trained":[33],"to":[34,77,121],"jointly":[35],"perform":[36],"both":[37],"tasks":[38],"from":[39,131],"raw":[41],"waveform.":[42],"Wavesplit":[43,80,117],"set":[46,104],"of":[47,58,72,87],"representations":[49,66],"via":[50],"clustering,":[51],"which":[52],"addresses":[53],"fundamental":[55],"permutation":[56],"problem":[57],"separation.":[59],"For":[60],"speech":[61],"separation,":[62],"our":[63],"sequence-wide":[64],"speaker":[65],"provide":[67],"more":[69],"robust":[70],"long,":[73],"challenging":[74],"recordings":[75],"compared":[76],"prior":[78],"work.":[79],"redefines":[81],"state-of-the-art":[83],"on":[84,108],"clean":[85],"mixtures":[86],"2":[88],"or":[89],"3":[90],"speakers":[91],"(WSJ0-2/3mix),":[92],"as":[93,95],"well":[94],"in":[96],"noisy":[97],"reverberated":[99],"settings":[100],"(WHAM/WHAMR).":[101],"also":[103,119],"new":[106],"benchmark":[107],"recent":[110],"LibriMix":[111],"dataset.":[112],"Finally,":[113],"we":[114],"show":[115],"that":[116],"applicable":[120],"other":[122],"domains,":[123],"by":[124],"separating":[125],"fetal":[126],"maternal":[128],"heart":[129],"rates":[130],"abdominal":[134],"electrocardiogram.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":19}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}