{"id":"https://openalex.org/W4375869289","doi":"https://doi.org/10.1109/icassp49357.2023.10096276","title":"Absolute Decision Corrupts Absolutely: Conservative Online Speaker Diarisation","display_name":"Absolute Decision Corrupts Absolutely: Conservative Online Speaker Diarisation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869289","doi":"https://doi.org/10.1109/icassp49357.2023.10096276"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5067505925","display_name":"Youngki Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youngki Kwon","raw_affiliation_strings":["NAVER Cloud Corporation,South Korea","NAVER Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070613375","display_name":"Hee-Soo Heo","orcid":"https://orcid.org/0000-0003-1567-123X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hee-Soo Heo","raw_affiliation_strings":["NAVER Cloud Corporation,South Korea","NAVER Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong-Jin Lee","raw_affiliation_strings":["NAVER Cloud Corporation,South Korea","NAVER Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022133103","display_name":"You Jin Kim","orcid":"https://orcid.org/0000-0002-4952-5532"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"You Jin Kim","raw_affiliation_strings":["NAVER Cloud Corporation,South Korea","NAVER Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091834525","display_name":"Jee-weon Jung","orcid":"https://orcid.org/0000-0003-0505-2988"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-Weon Jung","raw_affiliation_strings":["NAVER Cloud Corporation,South Korea","NAVER Cloud Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Cloud Corporation,South Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Cloud Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067505925"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77913296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9968000054359436,"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/centroid","display_name":"Centroid","score":0.8736050724983215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506284713745117},{"id":"https://openalex.org/keywords/silhouette","display_name":"Silhouette","score":0.7395526766777039},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6364104747772217},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5914801359176636},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5759493112564087},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5138199925422668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.491522878408432},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4606791138648987},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4111621379852295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36987948417663574},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3684534430503845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11133888363838196},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10152754187583923}],"concepts":[{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.8736050724983215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506284713745117},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.7395526766777039},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6364104747772217},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5914801359176636},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5759493112564087},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5138199925422668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.491522878408432},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4606791138648987},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4111621379852295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36987948417663574},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3684534430503845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11133888363838196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10152754187583923},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1987971958","https://openalex.org/W2081074144","https://openalex.org/W2174668315","https://openalex.org/W2405137844","https://openalex.org/W2963470929","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3015308613","https://openalex.org/W3015783745","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3095212884","https://openalex.org/W3162770427","https://openalex.org/W3163505255","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3196595845","https://openalex.org/W3197331597","https://openalex.org/W3197762688","https://openalex.org/W3201972179","https://openalex.org/W3204593031","https://openalex.org/W3212886388","https://openalex.org/W4221165661","https://openalex.org/W4237168004","https://openalex.org/W4283069218","https://openalex.org/W4297841423","https://openalex.org/W4297841591","https://openalex.org/W6633847657","https://openalex.org/W6770434673","https://openalex.org/W6786127183","https://openalex.org/W6801554186"],"related_works":["https://openalex.org/W2019992318","https://openalex.org/W92081101","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Our":[0],"focus":[1],"lies":[2],"in":[3,23,31,81,136,162],"developing":[4],"an":[5,36,79],"online":[6,18],"speaker":[7,19],"diarisation":[8],"framework":[9,65],"which":[10],"demonstrates":[11,148],"robust":[12],"performance":[13,150],"across":[14],"diverse":[15],"domains.":[16],"In":[17],"diarisation,":[20],"outputs":[21],"generated":[22,121],"real-time":[24],"are":[25,96],"irreversible,":[26],"and":[27,92,107,154,164],"a":[28,128],"few":[29],"misjudgements":[30],"the":[32,49,68,75,82,103],"early":[33],"phase":[34],"of":[35,51,55,70,105],"input":[37],"session":[38],"can":[39,119],"lead":[40],"to":[41,101,133],"catastrophic":[42],"results.":[43],"We":[44,86],"hypothesise":[45],"that":[46,78,114],"cautiously":[47],"increasing":[48],"number":[50,69,104],"estimated":[52],"speakers":[53,71,106],"is":[54,141,159],"paramount":[56],"importance":[57],"among":[58],"many":[59],"other":[60],"factors.":[61],"Thus,":[62],"our":[63],"proposed":[64],"includes":[66],"decreasing":[67],"by":[72],"one":[73,117,123],"when":[74],"system":[76,140,147],"judges":[77],"increase":[80],"past":[83],"was":[84],"faulty.":[85],"also":[87,160],"adopt":[88],"dual":[89],"buffers,":[90],"checkpoints":[91,95],"centroids,":[93],"where":[94,157],"combined":[97],"with":[98],"silhouette":[99],"coefficients":[100],"estimate":[102],"centroids":[108],"represent":[109],"speakers.":[110],"Again,":[111],"we":[112,126],"believe":[113],"more":[115],"than":[116],"centroid":[118],"be":[120],"from":[122],"speaker.":[124],"Thus":[125],"design":[127],"clustering-based":[129],"label":[130],"matching":[131],"technique":[132],"assign":[134],"labels":[135],"realtime.":[137],"The":[138,146],"resulting":[139],"lightweight":[142],"yet":[143],"surprisingly":[144],"effective.":[145],"state-of-the-art":[149],"on":[151],"DIHARD":[152],"II":[153],"III":[155],"datasets,":[156],"it":[158],"competitive":[161],"AMI":[163],"VoxConverse":[165],"test":[166],"sets.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
