{"id":"https://openalex.org/W3016021376","doi":"https://doi.org/10.1109/icassp40776.2020.9054176","title":"Speaker Diarization with Session-Level Speaker Embedding Refinement Using Graph Neural Networks","display_name":"Speaker Diarization with Session-Level Speaker Embedding Refinement Using Graph Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016021376","doi":"https://doi.org/10.1109/icassp40776.2020.9054176","mag":"3016021376"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5063578134","display_name":"Jixuan Wang","orcid":"https://orcid.org/0000-0003-1986-6747"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jixuan Wang","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020436837","display_name":"Ranjani Ramamurthy","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ranjani Ramamurthy","raw_affiliation_strings":["Microsoft, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056256317","display_name":"Frank Rudzicz","orcid":"https://orcid.org/0000-0002-1139-3423"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Frank Rudzicz","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012113499","display_name":"Michael Brudno","orcid":"https://orcid.org/0000-0001-7947-2243"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Brudno","raw_affiliation_strings":["University of Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063578134"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":2.3861,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90751436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"104","issue":null,"first_page":"7109","last_page":"7113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9975000023841858,"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":0.859611988067627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7496993541717529},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6915392279624939},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6419205665588379},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5959755778312683},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5495676398277283},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5396161079406738},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5375513434410095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48865655064582825},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44215306639671326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43928760290145874},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16296231746673584}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.859611988067627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7496993541717529},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6915392279624939},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6419205665588379},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5959755778312683},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5495676398277283},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5396161079406738},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5375513434410095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48865655064582825},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44215306639671326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43928760290145874},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16296231746673584},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1529533208","https://openalex.org/W1606894530","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2046056978","https://openalex.org/W2118550318","https://openalex.org/W2132914434","https://openalex.org/W2150593711","https://openalex.org/W2150769028","https://openalex.org/W2165232124","https://openalex.org/W2547446130","https://openalex.org/W2554952599","https://openalex.org/W2606780347","https://openalex.org/W2620757702","https://openalex.org/W2638067502","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2918342466","https://openalex.org/W2962788625","https://openalex.org/W2963224980","https://openalex.org/W2963285578","https://openalex.org/W2963386851","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2963745998","https://openalex.org/W2963757395","https://openalex.org/W2964015378","https://openalex.org/W2972949456","https://openalex.org/W2999547272","https://openalex.org/W4210257598","https://openalex.org/W4250042253","https://openalex.org/W4288419263","https://openalex.org/W4295700283","https://openalex.org/W4322614756","https://openalex.org/W6685562342","https://openalex.org/W6726873649","https://openalex.org/W6729100687","https://openalex.org/W6730084236","https://openalex.org/W6736685754","https://openalex.org/W6748856961","https://openalex.org/W6760045743","https://openalex.org/W6807384801"],"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/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Deep":[0],"speaker":[1,13,18,62,70,84,159],"embedding":[2,19,96],"models":[3],"have":[4],"been":[5],"commonly":[6],"used":[7],"as":[8],"a":[9,26,43,66,88,94,104,118],"building":[10],"block":[11],"for":[12,38,60,114],"diarization":[14,63],"systems;":[15],"however,":[16],"the":[17,31,52,61,74,100,123,126,131,135,147,153,157,162,177,181],"model":[20,90,111],"is":[21,112,141],"usually":[22],"trained":[23,113],"according":[24],"to":[25,68],"global":[27],"loss":[28],"defined":[29],"on":[30,144,166,180],"training":[32],"data,":[33,172],"which":[34,99],"could":[35],"be":[36],"suboptimal":[37],"distinguishing":[39],"speakers":[40,102],"locally":[41,72],"in":[42,98,117],"specific":[44],"meeting":[45,171],"session.":[46,82],"In":[47],"this":[48],"work":[49],"we":[50],"present":[51],"first":[53],"use":[54],"of":[55,146,156],"graph":[56],"neural":[57],"networks":[58],"(GNNs)":[59],"problem,":[64],"utilizing":[65],"GNN":[67],"refine":[69],"embeddings":[71,85,133,160,164],"using":[73],"structural":[75],"information":[76],"between":[77,125],"speech":[78],"segments":[79],"inside":[80],"each":[81],"The":[83,110],"extracted":[86],"by":[87,121,130],"pre-trained":[89],"are":[91,107],"remapped":[92],"into":[93],"new":[95],"space,":[97],"different":[101],"within":[103],"single":[105],"session":[106],"better":[108],"separated.":[109],"linkage":[115],"prediction":[116],"supervised":[119],"manner":[120],"minimizing":[122],"difference":[124],"affinity":[127],"matrix":[128],"constructed":[129],"refined":[132,148,158],"and":[134,169,173],"ground-truth":[136],"adjacency":[137],"matrix.":[138],"Spectral":[139],"clustering":[140,154],"then":[142],"applied":[143],"top":[145],"embeddings.":[149],"We":[150],"show":[151],"that":[152],"performance":[155],"outperforms":[161],"original":[163],"significantly":[165],"both":[167],"simulated":[168],"real":[170],"our":[174],"system":[175],"achieves":[176],"state-of-the-art":[178],"result":[179],"NIST":[182],"SRE":[183],"2000":[184],"CALLHOME":[185],"database.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}