{"id":"https://openalex.org/W4220731890","doi":"https://doi.org/10.1109/taslp.2022.3162080","title":"Encoder-Decoder Based Attractors for End-to-End Neural Diarization","display_name":"Encoder-Decoder Based Attractors for End-to-End Neural Diarization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4220731890","doi":"https://doi.org/10.1109/taslp.2022.3162080"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3162080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3162080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09741374.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09741374.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3166-4956","affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi, Ltd., Tokyo, Japan","LINE Corporation, Shinjuku-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6523-8146","affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"LINE Corporation, Shinjuku-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101012633","display_name":"Yawen Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yawen Xue","raw_affiliation_strings":["Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Kokubunji-shi, Tokyo, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-7449-5726","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2156,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.97477083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1493","last_page":"1507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.7176669836044312},{"id":"https://openalex.org/keywords/attractor","display_name":"Attractor","score":0.7008883953094482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5436635613441467},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5071229934692383},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5052681565284729},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4835657775402069},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46840259432792664},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.450560986995697},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4120481312274933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.284629225730896},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.20415928959846497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16900339722633362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7176669836044312},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.7008883953094482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5436635613441467},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5071229934692383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5052681565284729},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4835657775402069},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46840259432792664},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.450560986995697},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4120481312274933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.284629225730896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.20415928959846497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16900339722633362},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3162080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3162080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09741374.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:2106.10654","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.10654","pdf_url":"https://arxiv.org/pdf/2106.10654","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"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3162080","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3162080","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09741374.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220731890.pdf","grobid_xml":"https://content.openalex.org/works/W4220731890.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2083751884","https://openalex.org/W2093499222","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2638067502","https://openalex.org/W2735663686","https://openalex.org/W2746574320","https://openalex.org/W2801839390","https://openalex.org/W2870589900","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2891054259","https://openalex.org/W2891247151","https://openalex.org/W2896538040","https://openalex.org/W2900212944","https://openalex.org/W2902864383","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962935966","https://openalex.org/W2963470929","https://openalex.org/W2970568180","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W2972767900","https://openalex.org/W2972949456","https://openalex.org/W2989790778","https://openalex.org/W2997419692","https://openalex.org/W3007946293","https://openalex.org/W3008357631","https://openalex.org/W3008849579","https://openalex.org/W3010196324","https://openalex.org/W3015544392","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3033627755","https://openalex.org/W3095212884","https://openalex.org/W3099330747","https://openalex.org/W3105031100","https://openalex.org/W3124972797","https://openalex.org/W3140898556","https://openalex.org/W3144086690","https://openalex.org/W3145204487","https://openalex.org/W3147778289","https://openalex.org/W3160044950","https://openalex.org/W3161590371","https://openalex.org/W3162347631","https://openalex.org/W3162770427","https://openalex.org/W3163019736","https://openalex.org/W3178462146","https://openalex.org/W3185109982","https://openalex.org/W3196595845","https://openalex.org/W3197762688","https://openalex.org/W3197916665","https://openalex.org/W3212886388","https://openalex.org/W4225661121","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6755477022","https://openalex.org/W6774558098","https://openalex.org/W6779069803","https://openalex.org/W6779469704","https://openalex.org/W6790297703"],"related_works":["https://openalex.org/W2960434112","https://openalex.org/W3049714198","https://openalex.org/W2036805113","https://openalex.org/W2592279130","https://openalex.org/W4389272081","https://openalex.org/W135211875","https://openalex.org/W2049158118","https://openalex.org/W1499880030","https://openalex.org/W2123827981","https://openalex.org/W4205994410"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"an":[3,10,83,156,179],"end-to-end":[4],"neural":[5],"diarization":[6,173],"(EEND)":[7],"method":[8,81,133,159,168],"for":[9],"unknown":[11],"number":[12,49,98,142],"of":[13,31,50,78,99,112,143,178],"speakers.":[14,51],"In":[15],"contrast":[16],"to":[17,22,63,160],"the":[18,76,97,113,140,150,171,176,202],"conventional":[19,203],"cascaded":[20,189,204],"approach":[21],"speaker":[23,32,120,137],"diarization,":[24],"EEND":[25,36],"methods":[26],"are":[27,68,106],"better":[28],"in":[29,41,123],"terms":[30],"overlap":[33],"handling.":[34],"However,":[35],"still":[37,147],"has":[38],"a":[39,47,79,91,167],"disadvantage":[40],"that":[42,169,199],"it":[43],"cannot":[44],"deal":[45,135],"with":[46,128,136,175],"flexible":[48],"To":[52],"remedy":[53],"this":[54,132,162],"problem,":[55],"we":[56,153,165],"introduce":[57],"encoder-decoder-based":[58],"attractor":[59,87],"calculation":[60],"module":[61],"(EDA)":[62],"EEND.":[64],"Once":[65],"frame-wise":[66],"embeddings":[67,118],"obtained,":[69],"EDA":[70],"sequentially":[71],"generates":[72],"speaker-wise":[73],"attractors":[74,100,114],"on":[75,193],"basis":[77],"sequence-to-sequence":[80],"using":[82],"LSTM":[84],"encoder-decoder.":[85],"The":[86,117],"generation":[88],"continues":[89],"until":[90],"stopping":[92],"condition":[93],"is":[94,146],"satisfied;":[95],"thus,":[96,131],"can":[101,134],"be":[102],"flexible.":[103],"Diarization":[104],"results":[105,174,177],"then":[107],"estimated":[108,172],"as":[109],"dot":[110,125],"products":[111],"and":[115,195],"embeddings.":[116],"from":[119],"overlaps":[121],"result":[122],"larger":[124],"product":[126],"values":[127],"multiple":[129],"attractors;":[130],"overlaps.":[138],"Because":[139],"maximum":[141],"output":[144],"speakers":[145],"limited":[148],"by":[149],"training":[151],"set,":[152],"also":[154],"propose":[155,166],"iterative":[157],"inference":[158],"remove":[161],"restriction.":[163],"Further,":[164],"aligns":[170],"external":[180],"speech":[181],"activity":[182],"detector,":[183],"which":[184],"enables":[185],"fair":[186],"comparison":[187],"against":[188],"approaches.":[190],"Extensive":[191],"evaluations":[192],"simulated":[194],"real":[196],"datasets":[197],"show":[198],"EEND-EDA":[200],"outperforms":[201],"approach.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}