{"id":"https://openalex.org/W2104804886","doi":"https://doi.org/10.1109/tmm.2008.2007344","title":"Boosting-Based Multimodal Speaker Detection for Distributed Meeting Videos","display_name":"Boosting-Based Multimodal Speaker Detection for Distributed Meeting Videos","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2104804886","doi":"https://doi.org/10.1109/tmm.2008.2007344","mag":"2104804886"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2008.2007344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2008.2007344","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5103551927","display_name":"Cha Zhang","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":"Cha Zhang","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688994","display_name":"Peihao Yin","orcid":"https://orcid.org/0009-0001-1496-1107"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei Yin","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728762","display_name":"Yong Rui","orcid":"https://orcid.org/0000-0002-9142-5914"},"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"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yong Rui","raw_affiliation_strings":["Microsoft R and D (CRD) Group, Beijing, China","Microsoft Research Limited, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft R and D (CRD) Group, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"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":"Ross Cutler","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042310818","display_name":"Paul Viola","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":"Paul Viola","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102147563","display_name":"Xinding Sun","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":"Xinding Sun","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026272893","display_name":"Nelson Pinto","orcid":"https://orcid.org/0000-0002-8041-9199"},"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":"Nelson Pinto","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058849717","display_name":"Zhengyou Zhang","orcid":"https://orcid.org/0000-0002-6606-2525"},"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":"Zhengyou Zhang","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8907,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95551884,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":"8","first_page":"1541","last_page":"1552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":0.9969000220298767,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958000183105469,"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/boosting","display_name":"Boosting (machine learning)","score":0.9037315249443054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8891253471374512},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5794810056686401},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5044673681259155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49475210905075073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4622291028499603},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4530775249004364},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4424673318862915},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43999171257019043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34569114446640015},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19639506936073303},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0876035988330841}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.9037315249443054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8891253471374512},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5794810056686401},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5044673681259155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49475210905075073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4622291028499603},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4530775249004364},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4424673318862915},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43999171257019043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34569114446640015},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19639506936073303},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0876035988330841}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2008.2007344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2008.2007344","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W170371357","https://openalex.org/W1529401398","https://openalex.org/W1546961578","https://openalex.org/W1596560216","https://openalex.org/W1869980952","https://openalex.org/W1992825118","https://openalex.org/W2000466020","https://openalex.org/W2024046085","https://openalex.org/W2032210760","https://openalex.org/W2035090801","https://openalex.org/W2039668773","https://openalex.org/W2042045798","https://openalex.org/W2046845112","https://openalex.org/W2052470695","https://openalex.org/W2091377065","https://openalex.org/W2096343094","https://openalex.org/W2100152238","https://openalex.org/W2106488367","https://openalex.org/W2110412069","https://openalex.org/W2114863372","https://openalex.org/W2118725351","https://openalex.org/W2118847468","https://openalex.org/W2121486117","https://openalex.org/W2123993331","https://openalex.org/W2132920253","https://openalex.org/W2133447020","https://openalex.org/W2135502357","https://openalex.org/W2137611207","https://openalex.org/W2140235142","https://openalex.org/W2142511364","https://openalex.org/W2151928407","https://openalex.org/W2152239535","https://openalex.org/W2154636774","https://openalex.org/W2161969291","https://openalex.org/W2164899449","https://openalex.org/W3028832680","https://openalex.org/W3097096317","https://openalex.org/W3151111735","https://openalex.org/W4244952642","https://openalex.org/W6606956301","https://openalex.org/W6639402332","https://openalex.org/W6648736754","https://openalex.org/W6675974536","https://openalex.org/W6677831795","https://openalex.org/W6678139733","https://openalex.org/W6680075925","https://openalex.org/W6682920111","https://openalex.org/W6684193366","https://openalex.org/W6778281501"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2963610131","https://openalex.org/W1560125148"],"abstract_inverted_index":{"Identifying":[0],"the":[1,20,23,39,42,50,60,94,142,147,156,165,172],"active":[2],"speaker":[3,40,57,72,128,176],"in":[4,182],"a":[5,8,34,56,68,112,125],"video":[6,37],"of":[7,22,28,38,77,115,139,150,167],"distributed":[9,63],"meeting":[10,64],"can":[11],"be":[12],"very":[13,126],"helpful":[14],"for":[15,59],"remote":[16,43],"participants":[17],"to":[18,32,41,108],"understand":[19],"dynamics":[21],"meeting.":[24],"A":[25],"straightforward":[26],"application":[27],"such":[29],"analysis":[30],"is":[31,124,171,180],"stream":[33],"high":[35,132],"resolution":[36],"participants.":[44],"In":[45,134],"this":[46,170],"paper,":[47],"we":[48,52],"present":[49],"challenges":[51],"met":[53],"while":[54],"designing":[55],"detector":[58,129],"Microsoft":[61],"RoundTable":[62],"device,":[65],"and":[66,84,88,99,118,155,158],"propose":[67],"novel":[69],"boosting-based":[70],"multimodal":[71,175],"detection":[73,86,177],"(BMSD)":[74],"algorithm.":[75],"Instead":[76],"separately":[78],"performing":[79],"sound":[80],"source":[81],"localization":[82],"(SSL)":[83],"multiperson":[85],"(MPD)":[87],"subsequently":[89],"fusing":[90],"their":[91],"individual":[92],"results,":[93],"proposed":[95,143],"algorithm":[96,145,178],"fuses":[97],"audio":[98,117],"visual":[100,119],"information":[101],"at":[102],"feature":[103],"level":[104],"by":[105,153,162],"using":[106],"boosting":[107],"select":[109],"features":[110,120],"from":[111],"combined":[113],"pool":[114],"both":[116],"simultaneously.":[121],"The":[122],"result":[123],"accurate":[127],"with":[130],"extremely":[131],"efficiency.":[133],"experiments":[135],"that":[136,179],"includes":[137],"hundreds":[138],"real-world":[140],"meetings,":[141],"BMSD":[144],"reduces":[146],"error":[148],"rate":[149],"SSL-only":[151],"approach":[152,161],"24.6%,":[154],"SSL":[157],"MPD":[159],"fusion":[160],"20.9%.":[163],"To":[164],"best":[166],"our":[168],"knowledge,":[169],"first":[173],"real-time":[174],"deployed":[181],"commercial":[183],"products.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
