{"id":"https://openalex.org/W4401387004","doi":"https://doi.org/10.1109/taslp.2024.3439993","title":"End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors","display_name":"End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401387004","doi":"https://doi.org/10.1109/taslp.2024.3439993"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3439993","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3439993","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":"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2024.3439993","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016218474","display_name":"M. Rybicka","orcid":"https://orcid.org/0000-0002-2413-077X"},"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":true,"raw_author_name":"Magdalena Rybicka","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"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":"Jes\u00fas Villalba","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040324682","display_name":"Thomas Thebaud","orcid":"https://orcid.org/0000-0001-8953-7872"},"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":"Thomas Thebaud","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"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":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035943967","display_name":"Konrad Kowalczyk","orcid":"https://orcid.org/0000-0002-7834-6920"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]},{"id":"https://openalex.org/I686019","display_name":"AGH University of Krakow","ror":"https://ror.org/00bas1c41","country_code":"PL","type":"education","lineage":["https://openalex.org/I686019"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Konrad Kowalczyk","raw_affiliation_strings":["AGH University of Krakow, Krakow, Poland"],"affiliations":[{"raw_affiliation_string":"AGH University of Krakow, Krakow, Poland","institution_ids":["https://openalex.org/I686019","https://openalex.org/I126596746"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5016218474"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.3523,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8379265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"3960","last_page":"3973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9979000091552734,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7496250867843628},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6582698822021484},{"id":"https://openalex.org/keywords/nonlinear-autoregressive-exogenous-model","display_name":"Nonlinear autoregressive exogenous model","score":0.5300003886222839},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4620605707168579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4598684012889862},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4256387948989868},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4078623652458191},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.324171245098114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2815730571746826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21079710125923157},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.0967196524143219}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7496250867843628},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6582698822021484},{"id":"https://openalex.org/C42536954","wikidata":"https://www.wikidata.org/wiki/Q7049462","display_name":"Nonlinear autoregressive exogenous model","level":3,"score":0.5300003886222839},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4620605707168579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4598684012889862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4256387948989868},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4078623652458191},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.324171245098114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2815730571746826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21079710125923157},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0967196524143219}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3439993","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3439993","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":"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"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3439993","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3439993","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":"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":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G4321397363","display_name":null,"funder_award_id":"TEAM/2017-3/23","funder_id":"https://openalex.org/F4320321042","funder_display_name":"Fundacja na rzecz Nauki Polskiej"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321042","display_name":"Fundacja na rzecz Nauki Polskiej","ror":"https://ror.org/048zd9m77"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2038101708","https://openalex.org/W2089946642","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2972449503","https://openalex.org/W2972680151","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3010196324","https://openalex.org/W3015780472","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3112157188","https://openalex.org/W3147414526","https://openalex.org/W3147778289","https://openalex.org/W3157070662","https://openalex.org/W3162899666","https://openalex.org/W3163903701","https://openalex.org/W3196857193","https://openalex.org/W3198482860","https://openalex.org/W4220731890","https://openalex.org/W4221165661","https://openalex.org/W4224291204","https://openalex.org/W4225661121","https://openalex.org/W4296069292","https://openalex.org/W4297841708","https://openalex.org/W4372259977","https://openalex.org/W4372349651","https://openalex.org/W4385245566","https://openalex.org/W4385822749","https://openalex.org/W6688816777","https://openalex.org/W6774558098","https://openalex.org/W6774835902"],"related_works":["https://openalex.org/W2606910468","https://openalex.org/W3116827148","https://openalex.org/W3120843198","https://openalex.org/W2154965898","https://openalex.org/W2036704594","https://openalex.org/W4226315710","https://openalex.org/W3083782034","https://openalex.org/W4287185323","https://openalex.org/W2117809914","https://openalex.org/W2995801509"],"abstract_inverted_index":{"Despite":[0],"many":[1],"recent":[2,199],"developments":[3],"in":[4,23,63,92,168,196],"speaker":[5,53],"diarization,":[6],"it":[7],"remains":[8],"a":[9,82,111,164,176,225],"challenge":[10],"and":[11,21,33,79,157,181,202,227,241,245,251,271],"an":[12,118,158],"active":[13],"area":[14],"of":[15,40,90,97,114,143,153,179,214,224,230],"research":[16],"to":[17,105,117,187,206,263,273],"make":[18],"diarization":[19,54],"robust":[20],"effective":[22],"real-life":[24,246],"scenarios.":[25],"Well-established":[26],"clustering-based":[27],"methods":[28],"are":[29,38,57],"showing":[30],"good":[31],"performance":[32],"qualities.":[34],"However,":[35,167],"such":[36,73],"systems":[37,56,260],"built":[39],"several":[41],"independent,":[42],"separately":[43],"optimized":[44],"modules,":[45],"which":[46,218],"may":[47],"cause":[48],"non-optimum":[49],"performance.":[50],"End-to-end":[51],"neural":[52],"(EEND)":[55],"considered":[58],"the":[59,93,126,131,141,154,182,207,215,239,249,258,268,279],"next":[60],"stepping":[61],"stone":[62],"pursuing":[64],"high-performance":[65],"diarization.":[66],"Nevertheless,":[67],"this":[68,144,192],"approach":[69,201],"also":[70],"suffers":[71],"limitations,":[72],"as":[74,151],"dealing":[75],"with":[76,81,99,107,133],"long":[77],"recordings":[78,108,189,221,247,277],"scenarios":[80],"large":[83],"(more":[84],"than":[85],"four)":[86],"or":[87],"unknown":[88,228],"number":[89,113,178,229],"speakers":[91,115],"recording.":[94],"The":[95],"appearance":[96],"EEND":[98,132],"encoder-decoder-based":[100],"attractors":[101],"(EEND-EDA)":[102],"enabled":[103],"us":[104],"deal":[106],"that":[109],"contain":[110],"flexible":[112],"thanks":[116],"LSTM-based":[119],"EDA":[120],"module.":[121],"A":[122],"competitive":[123],"alternative":[124],"over":[125,278],"referenced":[127],"EEND-EDA":[128],"baseline":[129,280],"is":[130],"non-autoregressive":[134],"attractor":[135,155,159],"(EEND-NAA)":[136],"estimation,":[137],"proposed":[138,259],"recently":[139],"by":[140],"authors":[142],"article.":[145],"NAA":[146,216],"back-end":[147],"incorporates":[148],"k-means":[149],"clustering":[150],"part":[152],"estimation":[156],"refinement":[160],"module":[161],"based":[162],"on":[163,172],"Transformer":[165],"decoder.":[166],"our":[169,198],"previous":[170],"work":[171],"EEND-NAA,":[173],"we":[174,194],"assumed":[175],"known":[177],"speakers,":[180],"experimental":[183,256],"evaluation":[184],"was":[185],"limited":[186],"2-speaker":[188],"only.":[190],"In":[191,255],"article,":[193],"describe":[195],"detail":[197],"EEND-NAA":[200,208],"propose":[203],"further":[204],"improvements":[205],"architecture,":[209],"introducing":[210],"three":[211],"novel":[212],"variants":[213],"back-end,":[217],"can":[219],"handle":[220],"containing":[222],"speech":[223],"variable":[226],"speakers.":[231],"Conducted":[232],"experiments":[233],"include":[234],"simulated":[235,269],"mixtures":[236],"generated":[237],"using":[238],"Switchboard":[240],"NIST":[242],"SRE":[243],"datasets":[244],"from":[248],"CALLHOME":[250],"DIHARD":[252],"II":[253],"datasets.":[254],"evaluation,":[257],"achieve":[261],"up":[262,272],"51%":[264],"relative":[265],"improvement":[266],"for":[267,275],"scenario":[270],"15%":[274],"real":[276],"EEND-EDA.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}