{"id":"https://openalex.org/W3196857193","doi":"https://doi.org/10.21437/interspeech.2021-1004","title":"Advances in Integration of End-to-End Neural and Clustering-Based Diarization for Real Conversational Speech","display_name":"Advances in Integration of End-to-End Neural and Clustering-Based Diarization for Real Conversational Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196857193","doi":"https://doi.org/10.21437/interspeech.2021-1004","mag":"3196857193"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1004","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069398831"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5059,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.95417294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3565","last_page":"3569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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":0.9965000152587891,"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":0.979200005531311,"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/T12031","display_name":"Speech and dialogue systems","score":0.97079998254776,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8816285133361816},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8378239870071411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878532409667969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6088200807571411},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5565537214279175},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5167297720909119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47058171033859253},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3811532258987427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35841840505599976}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8816285133361816},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8378239870071411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878532409667969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6088200807571411},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5565537214279175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5167297720909119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47058171033859253},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3811532258987427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35841840505599976}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1004","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Recently,":[0],"we":[1,82],"proposed":[2,26,146],"a":[3],"novel":[4],"speaker":[5],"diarization":[6,20,35,106],"method":[7,27,63,100,147],"called":[8],"End-to-End-Neural-Diarization-vector":[9],"clustering":[10,92],"(EEND-vector":[11],"clustering)":[12],"that":[13,98],"integrates":[14],"clustering-based":[15,59],"and":[16,37,45,94,125,142,148],"end-to-end":[17],"neural":[18],"network-based":[19],"approaches":[21],"into":[22],"one":[23],"framework.":[24],"The":[25],"combines":[28],"advantages":[29],"of":[30,39,48,55,129,144],"both":[31],"frameworks,":[32],"i.e.":[33],"high":[34],"performance":[36],"handling":[38,47],"overlapped":[40,123],"speech":[41,120,124],"based":[42,57],"on":[43,58,69,113],"EEND,":[44],"robust":[46,90],"long":[49],"recordings":[50],"with":[51],"an":[52,126],"arbitrary":[53,127],"number":[54,128],"speakers":[56],"approaches.":[60],"However,":[61],"the":[62,99,134,145],"was":[64],"only":[65],"evaluated":[66],"so":[67],"far":[68],"simulated":[70],"2-speaker":[71],"meeting-like":[72],"data.":[73],"This":[74],"paper":[75,138],"is":[76],"to":[77,84],"(1)":[78],"report":[79],"recent":[80],"advances":[81],"made":[83],"this":[85,137],"framework,":[86],"including":[87,122],"newly":[88],"introduced":[89],"constrained":[91],"algorithms,":[93],"(2)":[95],"experimentally":[96],"show":[97],"can":[101],"now":[102],"significantly":[103],"outperform":[104],"competitive":[105],"methods":[107],"such":[108],"as":[109],"Encoder-Decoder":[110],"Attractor":[111],"(EDA)-EEND,":[112],"CALLHOME":[114],"data":[115,121],"which":[116],"comprises":[117],"real":[118],"conversational":[119],"speakers.":[130],"By":[131],"further":[132,152],"analyzing":[133],"experimental":[135],"results,":[136],"also":[139],"discusses":[140],"pros":[141],"cons":[143],"reveals":[149],"potential":[150],"for":[151],"improvement.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}