{"id":"https://openalex.org/W4283717211","doi":"https://doi.org/10.21437/interspeech.2022-944","title":"Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization","display_name":"Interrelate Training and Searching: A Unified Online Clustering Framework for Speaker Diarization","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283717211","doi":"https://doi.org/10.21437/interspeech.2022-944"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-944","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-944","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100405119","display_name":"Yifan Chen","orcid":"https://orcid.org/0000-0001-5494-4435"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Chen","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026759570","display_name":"Yifan Guo","orcid":"https://orcid.org/0000-0002-9700-5005"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences, China","Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036226253","display_name":"Qingxuan Li","orcid":"https://orcid.org/0000-0001-5163-7958"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxuan Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of Chinese Academy of Sciences, China","Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, China,","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100405119"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66418875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1456","last_page":"1460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9897000193595886,"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":0.9743000268936157,"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":0.8495991230010986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666572332382202},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7213795185089111},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6824575662612915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5210561156272888},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43734800815582275},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4292137026786804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40998855233192444}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8495991230010986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666572332382202},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7213795185089111},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6824575662612915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5210561156272888},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43734800815582275},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4292137026786804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40998855233192444},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-944","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-944","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320336292","display_name":"Institute of Acoustics, Chinese Academy of Sciences","ror":"https://ror.org/00v8rqv75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1524333225","https://openalex.org/W1998871699","https://openalex.org/W2016973429","https://openalex.org/W2046056978","https://openalex.org/W2081074144","https://openalex.org/W2130556178","https://openalex.org/W2150769028","https://openalex.org/W2165874743","https://openalex.org/W2598634450","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2969985801","https://openalex.org/W2972680151","https://openalex.org/W2972891548","https://openalex.org/W2989790778","https://openalex.org/W3008357631","https://openalex.org/W3015598461","https://openalex.org/W3016031604","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3097022478","https://openalex.org/W3099206234","https://openalex.org/W3103152812","https://openalex.org/W3128434617","https://openalex.org/W3160044950","https://openalex.org/W3178462146","https://openalex.org/W4206908380","https://openalex.org/W4245490569","https://openalex.org/W4287235989"],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W2143693287","https://openalex.org/W3193772784","https://openalex.org/W1967070677","https://openalex.org/W2914064142","https://openalex.org/W2736005052","https://openalex.org/W2931508530","https://openalex.org/W2103611452","https://openalex.org/W3205635414"],"abstract_inverted_index":{"For":[0],"online":[1,35,43,136,146],"speaker":[2,36],"diarization,":[3],"samples":[4,13],"arrive":[5],"incrementally,":[6],"and":[7,54,69],"the":[8,12,21,25,57,77,81,95,103,115,118,121,141,159,162,165],"overall":[9],"distribution":[10],"of":[11,24,60,84,114,124,164],"is":[14,28,170],"invisible.Moreover,":[15],"in":[16,127,135],"most":[17],"existing":[18],"clustering-based":[19],"methods,":[20],"training":[22,67,82],"objective":[23],"embedding":[26,52,85,96],"extractor":[27],"not":[29,90],"designed":[30],"specially":[31],"for":[32,94,102],"clustering.To":[33],"improve":[34],"diarization":[37],"performance,":[38],"we":[39],"propose":[40],"a":[41],"unified":[42],"clustering":[44,55,73,78,104,133,147,169],"framework,":[45],"which":[46,87,110],"provides":[47],"an":[48],"interactive":[49],"manner":[50],"between":[51],"extractors":[53],"algorithms.Specifically,":[56],"framework":[58],"consists":[59],"two":[61],"highly":[62],"coupled":[63],"parts:":[64],"clustering-guided":[65],"recurrent":[66],"(CGRT)":[68],"truncated":[70],"beam":[71],"searching":[72],"(TBSC).The":[74],"CGRT":[75],"introduces":[76],"algorithm":[79],"into":[80],"process":[83,105],"extractors,":[86],"could":[88],"provide":[89],"only":[91],"cluster-aware":[92],"information":[93,113],"extractor,":[97],"but":[98],"also":[99],"crucial":[100],"parameters":[101],"afterward.And":[106],"with":[107,138,152],"these":[108],"parameters,":[109],"contain":[111],"preliminary":[112],"metric":[116],"space,":[117],"TBSC":[119],"penalizes":[120],"probability":[122],"score":[123],"each":[125],"cluster,":[126],"order":[128],"to":[129],"output":[130],"more":[131],"accurate":[132],"results":[134],"fashion":[137],"low":[139],"latency.With":[140],"above":[142],"innovations,":[143],"our":[144],"proposed":[145],"system":[148],"achieves":[149],"14.48%":[150],"DER":[151,163],"collar":[153],"0.25":[154],"at":[155],"2.5s":[156],"latency":[157],"on":[158],"AISHELL-4,":[160],"while":[161],"offline":[166],"agglomerative":[167],"hierarchical":[168],"14.57%.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}