{"id":"https://openalex.org/W1583773829","doi":"https://doi.org/10.1109/tmm.2015.2463722","title":"Multimodal Multi-Channel On-Line Speaker Diarization Using Sensor Fusion Through SVM","display_name":"Multimodal Multi-Channel On-Line Speaker Diarization Using Sensor Fusion Through SVM","publication_year":2015,"publication_date":"2015-08-03","ids":{"openalex":"https://openalex.org/W1583773829","doi":"https://doi.org/10.1109/tmm.2015.2463722","mag":"1583773829"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2015.2463722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2015.2463722","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/A5032058419","display_name":"Vicente Peruffo Minotto","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Vicente Peruffo Minotto","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul., Porto Alegre, RS, Brazil","Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul., Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I130442723"]},{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012781859","display_name":"Cl\u00e1udio R. Jung","orcid":"https://orcid.org/0000-0002-4711-5783"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Claudio Rosito Jung","raw_affiliation_strings":["Institute of Informatics, Federal University of Rio Grande do Sul., Porto Alegre, RS, Brazil","Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul., Porto Alegre, RS, Brazil","institution_ids":["https://openalex.org/I130442723"]},{"raw_affiliation_string":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089545632","display_name":"Bowon Lee","orcid":"https://orcid.org/0000-0001-5417-5699"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bowon Lee","raw_affiliation_strings":["Department of Electronic Engineering, Inha University, Nam-gu, Incheon, South Korea","Department of Electronic Engineering, Inha University, Nam-gu, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Nam-gu, Incheon, South Korea","institution_ids":["https://openalex.org/I191879574"]},{"raw_affiliation_string":"Department of Electronic Engineering, Inha University, Nam-gu, South Korea","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3918,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.91940563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"10","first_page":"1694","last_page":"1705"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8763160705566406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6647723913192749},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6256123185157776},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.622280478477478},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48814138770103455},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47972291707992554},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4772869646549225},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4547308385372162},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4525335729122162},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43869149684906006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4258244037628174},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42545977234840393},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4219932556152344},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4118736982345581},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32798415422439575},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11200183629989624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763160705566406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6647723913192749},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6256123185157776},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.622280478477478},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48814138770103455},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47972291707992554},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4772869646549225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4547308385372162},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4525335729122162},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43869149684906006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4258244037628174},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42545977234840393},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4219932556152344},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4118736982345581},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32798415422439575},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11200183629989624},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/tmm.2015.2463722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2015.2463722","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":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1855070427","display_name":null,"funder_award_id":"INHA-51376","funder_id":"https://openalex.org/F4320321370","funder_display_name":"Inha University"}],"funders":[{"id":"https://openalex.org/F4320321370","display_name":"Inha University","ror":"https://ror.org/01easw929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W9688279","https://openalex.org/W142991516","https://openalex.org/W143001888","https://openalex.org/W164219236","https://openalex.org/W202968570","https://openalex.org/W1504694836","https://openalex.org/W1509663858","https://openalex.org/W1514579074","https://openalex.org/W1515932869","https://openalex.org/W1545641654","https://openalex.org/W1560013842","https://openalex.org/W1569447338","https://openalex.org/W1587845029","https://openalex.org/W1589339348","https://openalex.org/W1591607137","https://openalex.org/W1771384906","https://openalex.org/W1968849517","https://openalex.org/W1971791733","https://openalex.org/W1973067693","https://openalex.org/W1974352992","https://openalex.org/W1978607478","https://openalex.org/W1991048564","https://openalex.org/W1992106273","https://openalex.org/W1996601463","https://openalex.org/W1997137108","https://openalex.org/W2000466020","https://openalex.org/W2021848030","https://openalex.org/W2032647955","https://openalex.org/W2034356580","https://openalex.org/W2041649634","https://openalex.org/W2045540602","https://openalex.org/W2060280062","https://openalex.org/W2063880242","https://openalex.org/W2074394031","https://openalex.org/W2081074144","https://openalex.org/W2084237818","https://openalex.org/W2088989807","https://openalex.org/W2090088747","https://openalex.org/W2098693229","https://openalex.org/W2098726438","https://openalex.org/W2101775574","https://openalex.org/W2110783210","https://openalex.org/W2115175902","https://openalex.org/W2115694019","https://openalex.org/W2116529913","https://openalex.org/W2121647436","https://openalex.org/W2125055259","https://openalex.org/W2125336414","https://openalex.org/W2129120544","https://openalex.org/W2130499067","https://openalex.org/W2133042973","https://openalex.org/W2135035670","https://openalex.org/W2135625868","https://openalex.org/W2140192608","https://openalex.org/W2144273330","https://openalex.org/W2145303093","https://openalex.org/W2149220986","https://openalex.org/W2153635508","https://openalex.org/W2157145630","https://openalex.org/W2157363431","https://openalex.org/W2157494921","https://openalex.org/W2159094433","https://openalex.org/W2163343350","https://openalex.org/W2166980079","https://openalex.org/W2169165592","https://openalex.org/W2172257986","https://openalex.org/W2222512263","https://openalex.org/W2338994564","https://openalex.org/W3094114204","https://openalex.org/W3173503818","https://openalex.org/W4233450617","https://openalex.org/W4249052411","https://openalex.org/W4285719527","https://openalex.org/W4298870604","https://openalex.org/W6608271823","https://openalex.org/W6630463007","https://openalex.org/W6632636493","https://openalex.org/W6633847657","https://openalex.org/W6635141280","https://openalex.org/W6635144179","https://openalex.org/W6661426310","https://openalex.org/W6671574273","https://openalex.org/W6677131165","https://openalex.org/W6677380243","https://openalex.org/W6681388093","https://openalex.org/W6683386074","https://openalex.org/W6797375751","https://openalex.org/W6843883022"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":{"Speaker":[0,188],"diarization":[1,211],"(SD)":[2],"is":[3,66,190,225],"the":[4,20,39],"process":[5],"of":[6,10,22,127,183,196,214],"assigning":[7],"speech":[8],"segments":[9],"an":[11,134,209],"audio":[12],"stream":[13,121],"to":[14,140,172,220,227],"its":[15],"corresponding":[16],"speakers,":[17,223],"thus":[18],"comprising":[19],"problem":[21],"voice":[23],"activity":[24],"detection":[25],"(VAD),":[26],"speaker":[27],"labeling/identification,":[28],"and":[29,50,77,85,98,159,185,200,224],"often":[30],"sound":[31],"source":[32],"localization":[33],"(SSL).":[34],"Most":[35],"research":[36,64],"activities":[37],"in":[38,78,81,142,216],"past":[40],"aimed":[41],"towards":[42],"applications":[43,92],"as":[44,80,163],"broadcast":[45],"news,":[46],"meetings,":[47],"conversational":[48],"telephony,":[49],"automatic":[51],"multimodal":[52,136],"data":[53,120],"annotation,":[54],"where":[55,71],"SD":[56,72,137,205],"may":[57,122],"be":[58,74,173],"performed":[59,75],"off-line.":[60],"However,":[61],"a":[62,119,143,153,156,160,177,193],"recent":[63],"focus":[65],"human-computer":[67],"interaction":[68,86],"(HCI)":[69],"systems":[70],"must":[73],"on-line,":[76],"real-time,":[79],"modern":[82],"gaming":[83],"devices":[84],"with":[87,146,218],"large":[88],"displays.":[89],"Often,":[90],"such":[91,106],"further":[93],"suffer":[94],"from":[95,166],"noise,":[96],"reverberations,":[97],"overlapping":[99,148],"speech,":[100],"making":[101],"them":[102],"increasingly":[103],"challenging.":[104],"In":[105],"situations,":[107],"multimodal/multisensory":[108],"approaches":[109],"can":[110],"provide":[111],"more":[112],"accurate":[113],"results":[114],"than":[115],"unimodal":[116],"ones,":[117],"given":[118],"compensate":[123],"for":[124],"occasional":[125],"instabilities":[126],"other":[128],"modalities.":[129],"Accordingly,":[130],"this":[131],"paper":[132],"presents":[133],"on-line":[135],"algorithm":[138],"designed":[139],"work":[141,151],"realistic":[144],"environment":[145],"multiple,":[147],"speakers.":[149],"Our":[150,203],"employs":[152],"microphone":[154],"array,":[155],"color":[157],"camera,":[158],"depth":[161],"sensor":[162],"input":[164],"streams,":[165],"which":[167],"speech-related":[168],"features":[169],"are":[170],"extracted":[171],"later":[174],"merged":[175],"through":[176,192],"support":[178],"vector":[179],"machine":[180],"approach":[181,206],"consisting":[182],"VAD":[184],"SSL":[186],"modules.":[187],"identification":[189],"incorporated":[191],"hybrid":[194],"technique":[195],"face":[197,201],"positioning":[198],"history":[199],"recognition.":[202],"final":[204],"experimentally":[207],"achieves":[208],"average":[210],"error":[212],"rate":[213],"11.48%":[215],"scenarios":[217],"up":[219],"three":[221],"simultaneous":[222],"able":[226],"run":[228],"3.2":[229],"\u00d7":[230],"real-time.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
