{"id":"https://openalex.org/W2896538040","doi":"https://doi.org/10.1109/icassp.2019.8683892","title":"Fully Supervised Speaker Diarization","display_name":"Fully Supervised Speaker Diarization","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2896538040","doi":"https://doi.org/10.1109/icassp.2019.8683892","mag":"2896538040"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5047876033","display_name":"Aonan Zhang","orcid":"https://orcid.org/0000-0002-6310-4769"},"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":"Aonan Zhang","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"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":"Quan Wang","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041599050","display_name":"Zhenyao Zhu","orcid":null},"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":"Zhenyao Zhu","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110662445","display_name":"John Paisley","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Paisley","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329463","display_name":"Chong Wang","orcid":"https://orcid.org/0000-0003-0022-0217"},"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":"Chong Wang","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047876033"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":25.4063,"has_fulltext":false,"cited_by_count":237,"citation_normalized_percentile":{"value":0.99633719,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6301","last_page":"6305"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.885589599609375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960144281387329},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7859712839126587},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.7759726047515869},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7100926041603088},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6536756753921509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6454794406890869},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6308637261390686},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5880433320999146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573067665100098},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4545804560184479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38294562697410583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3062317967414856},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2865496873855591},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10766032338142395}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.885589599609375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960144281387329},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7859712839126587},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.7759726047515869},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7100926041603088},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6536756753921509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6454794406890869},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6308637261390686},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5880433320999146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573067665100098},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4545804560184479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38294562697410583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3062317967414856},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2865496873855591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10766032338142395}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W336125708","https://openalex.org/W1037395734","https://openalex.org/W1494198834","https://openalex.org/W1500943299","https://openalex.org/W1591607137","https://openalex.org/W1606894530","https://openalex.org/W1665214252","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2093499222","https://openalex.org/W2114925438","https://openalex.org/W2125642021","https://openalex.org/W2150769028","https://openalex.org/W2154241802","https://openalex.org/W2157331557","https://openalex.org/W2208598356","https://openalex.org/W2340687287","https://openalex.org/W2524400072","https://openalex.org/W2553510336","https://openalex.org/W2615915281","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2746574320","https://openalex.org/W2749214709","https://openalex.org/W2750259098","https://openalex.org/W2769236969","https://openalex.org/W2777460248","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2869261065","https://openalex.org/W2870677466","https://openalex.org/W2889144942","https://openalex.org/W2894809337","https://openalex.org/W2926514197","https://openalex.org/W2928608015","https://openalex.org/W2928921291","https://openalex.org/W2931030156","https://openalex.org/W2950628382","https://openalex.org/W2962788625","https://openalex.org/W2963432880","https://openalex.org/W2963470929","https://openalex.org/W2973062255","https://openalex.org/W2992261503","https://openalex.org/W3019618160","https://openalex.org/W3039147984","https://openalex.org/W3140816754","https://openalex.org/W4214556932","https://openalex.org/W4294589828","https://openalex.org/W6601947329","https://openalex.org/W6636312512","https://openalex.org/W6637242042","https://openalex.org/W6684363390","https://openalex.org/W6743140259","https://openalex.org/W6743299418","https://openalex.org/W6748447238","https://openalex.org/W6752888775","https://openalex.org/W6755462816"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W2896538040","https://openalex.org/W1521049138","https://openalex.org/W2950628382"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,33,54,87],"fully":[6,70],"supervised":[7,71],"speaker":[8,29,81],"diarization":[9,89],"approach,":[10],"named":[11],"unbounded":[12],"interleaved-state":[13],"recurrent":[14],"neural":[15],"networks":[16],"(UIS-RNN).":[17],"Given":[18],"extracted":[19],"speaker-discriminative":[20],"embeddings":[21],"(a.k.a.":[22],"d-vectors)":[23],"from":[24,77],"input":[25],"utterances,":[26],"each":[27],"individual":[28],"is":[30,50,69,73,98],"modeled":[31],"by":[32],"parameter-sharing":[34],"RNN,":[35],"while":[36,115],"the":[37,45,101],"RNN":[38,49],"states":[39],"for":[40],"different":[41],"speakers":[42],"interleave":[43],"in":[44,111],"time":[46],"domain.":[47],"This":[48],"naturally":[51],"integrated":[52],"with":[53],"distance-dependent":[55],"Chinese":[56],"restaurant":[57],"process":[58],"(ddCRP)":[59],"to":[60,75],"accommodate":[61],"an":[62,112],"unknown":[63],"number":[64],"of":[65],"speakers.":[66],"Our":[67],"system":[68],"and":[72],"able":[74],"learn":[76],"examples":[78],"where":[79],"time-stamped":[80],"labels":[82],"are":[83],"annotated.":[84],"We":[85],"achieved":[86],"7.6%":[88],"error":[90],"rate":[91],"on":[92,120],"NIST":[93],"SRE":[94],"2000":[95],"CALLHOME,":[96],"which":[97],"better":[99],"than":[100],"state-of-the-art":[102,117],"method":[103,109],"using":[104],"spectral":[105],"clustering.":[106,122],"Moreover,":[107],"our":[108],"decodes":[110],"online":[113],"fashion":[114],"most":[116],"systems":[118],"rely":[119],"offline":[121]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":54},{"year":2020,"cited_by_count":61},{"year":2019,"cited_by_count":27}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}