{"id":"https://openalex.org/W4389459167","doi":"https://doi.org/10.1109/access.2023.3340307","title":"Self-Conditioning via Intermediate Predictions for End-to-End Neural Speaker Diarization","display_name":"Self-Conditioning via Intermediate Predictions for End-to-End Neural Speaker Diarization","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389459167","doi":"https://doi.org/10.1109/access.2023.3340307"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3340307","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3340307","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10347201.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10347201.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["LY Corporation, Tokyo, Japan","Waseda University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6523-8146","affiliations":[{"raw_affiliation_string":"LY Corporation, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7316-2073","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044818016"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1685,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58656817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":null,"first_page":"140069","last_page":"140076"},"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":0.9991999864578247,"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":0.9991000294685364,"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":0.7658137083053589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619627118110657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5937392711639404},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5832812190055847},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5307020545005798},{"id":"https://openalex.org/keywords/attractor","display_name":"Attractor","score":0.5102660655975342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47529304027557373},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46939602494239807},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4605068564414978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43809932470321655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3318607211112976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10574173927307129},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.062391817569732666}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7658137083053589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619627118110657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5937392711639404},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5832812190055847},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5307020545005798},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.5102660655975342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47529304027557373},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46939602494239807},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4605068564414978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43809932470321655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3318607211112976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10574173927307129},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.062391817569732666},{"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/access.2023.3340307","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3340307","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10347201.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5045f58aebab432b90ee4f2d3f2c7364","is_oa":true,"landing_page_url":"https://doaj.org/article/5045f58aebab432b90ee4f2d3f2c7364","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 140069-140076 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3340307","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3340307","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10347201.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389459167.pdf","grobid_xml":"https://content.openalex.org/works/W4389459167.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1485783873","https://openalex.org/W1591607137","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2081074144","https://openalex.org/W2144158639","https://openalex.org/W2159591770","https://openalex.org/W2170579896","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2638067502","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3020336359","https://openalex.org/W3033627755","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3103334733","https://openalex.org/W3160044950","https://openalex.org/W3162249256","https://openalex.org/W3196595845","https://openalex.org/W3196857193","https://openalex.org/W3197140813","https://openalex.org/W3197916665","https://openalex.org/W3206573929","https://openalex.org/W3209984917","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4225661121","https://openalex.org/W4297841362","https://openalex.org/W4372347449","https://openalex.org/W4372349651","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6762100871","https://openalex.org/W6779069803"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W1992908141","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,28,38,99,137,175],"speaker":[4,34,52,84,96],"diarization":[5,23,35,154,187],"model":[6],"that":[7,148],"incorporates":[8],"label":[9,59],"dependency":[10,60],"via":[11],"intermediate":[12,95,162],"predictions.":[13,163],"The":[14,140],"proposed":[15,55,150,167],"method":[16,30,56],"is":[17],"categorized":[18],"as":[19,98],"an":[20,75,123],"end-to-end":[21],"neural":[22,41],"(EEND),":[24],"which":[25,69,131],"has":[26,70],"been":[27,71],"promising":[29],"for":[31],"solving":[32],"the":[33,54,58,62,66,81,91,103,117,143,149,153,166],"problem":[36],"with":[37,142,178,185],"multi-label":[39],"classification":[40],"network.":[42],"While":[43],"most":[44],"EEND-based":[45],"models":[46,63],"assume":[47],"conditional":[48],"independence":[49],"between":[50],"frame-level":[51],"labels,":[53],"introduces":[57],"to":[61,74,181],"by":[64,89],"exploiting":[65],"self-conditioning":[67,82,106,151],"mechanism,":[68,83],"originally":[72],"applied":[73],"automatic":[76],"speech":[77],"recognition":[78],"model.":[79],"With":[80],"labels":[85,97],"are":[86],"iteratively":[87],"refined":[88],"taking":[90],"whole":[92],"sequence":[93],"of":[94,105],"reference.":[100],"We":[101],"demonstrate":[102],"effectiveness":[104],"in":[107,136],"both":[108],"Transformer-based":[109],"and":[110,156,173],"attractor-based":[111,118],"EEND":[112,119],"models.":[113,188],"To":[114],"efficiently":[115],"train":[116],"model,":[120],"we":[121],"propose":[122],"improved":[124],"attractor":[125,169],"computation":[126],"module":[127],"named":[128],"non-autoregressive":[129,138,168],"attractor,":[130],"produces":[132],"speaker-wise":[133],"attractors":[134],"simultaneously":[135],"manner.":[139],"experiments":[141],"CALLHOME":[144],"two-speaker":[145],"dataset":[146],"show":[147],"boosts":[152],"performance":[155,183],"progressively":[157],"reduces":[158],"errors":[159],"through":[160],"successive":[161],"In":[164],"addition,":[165],"improves":[170],"training":[171],"efficiency":[172],"provides":[174],"synergetic":[176],"boost":[177],"self-conditioning,":[179],"leading":[180],"superior":[182],"compared":[184],"existing":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}