{"id":"https://openalex.org/W2090088747","doi":"https://doi.org/10.1109/tmm.2014.2305632","title":"Simultaneous-Speaker Voice Activity Detection and Localization Using Mid-Fusion of SVM and HMMs","display_name":"Simultaneous-Speaker Voice Activity Detection and Localization Using Mid-Fusion of SVM and HMMs","publication_year":2014,"publication_date":"2014-02-11","ids":{"openalex":"https://openalex.org/W2090088747","doi":"https://doi.org/10.1109/tmm.2014.2305632","mag":"2090088747"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2014.2305632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2014.2305632","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 P. 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 R. 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/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bowon Lee","raw_affiliation_strings":["Hewlett-Packard Laboratories, Palo Alto, CA, USA","Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett\u2013Packard Laboratories, Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2137,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.96260864,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"1032","last_page":"1044"},"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":0.9983999729156494,"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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8639814853668213},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.761095404624939},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6393638253211975},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6169324517250061},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5711687207221985},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5581971406936646},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5348058938980103},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4819302558898926},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47738736867904663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46674615144729614},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37640732526779175},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08304741978645325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639814853668213},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.761095404624939},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6393638253211975},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6169324517250061},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5711687207221985},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5581971406936646},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5348058938980103},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4819302558898926},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47738736867904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46674615144729614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37640732526779175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08304741978645325},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2014.2305632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2014.2305632","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W705233","https://openalex.org/W126779258","https://openalex.org/W143001888","https://openalex.org/W147998453","https://openalex.org/W604305329","https://openalex.org/W1506558619","https://openalex.org/W1510526001","https://openalex.org/W1515932869","https://openalex.org/W1565206031","https://openalex.org/W1570419640","https://openalex.org/W1973067693","https://openalex.org/W1975846642","https://openalex.org/W1991899119","https://openalex.org/W1997137108","https://openalex.org/W2000466020","https://openalex.org/W2016157229","https://openalex.org/W2020657260","https://openalex.org/W2021848030","https://openalex.org/W2032647955","https://openalex.org/W2033571983","https://openalex.org/W2034356580","https://openalex.org/W2041649634","https://openalex.org/W2046033161","https://openalex.org/W2053101950","https://openalex.org/W2061074721","https://openalex.org/W2063880242","https://openalex.org/W2065257586","https://openalex.org/W2103568877","https://openalex.org/W2109349638","https://openalex.org/W2114065807","https://openalex.org/W2114661268","https://openalex.org/W2115694019","https://openalex.org/W2116529913","https://openalex.org/W2118877769","https://openalex.org/W2119842211","https://openalex.org/W2121973264","https://openalex.org/W2125838338","https://openalex.org/W2129120544","https://openalex.org/W2130103520","https://openalex.org/W2136484266","https://openalex.org/W2144273330","https://openalex.org/W2150946027","https://openalex.org/W2153635508","https://openalex.org/W2154613441","https://openalex.org/W2157363431","https://openalex.org/W2157494921","https://openalex.org/W2163343350","https://openalex.org/W2400967734","https://openalex.org/W3094114204","https://openalex.org/W3147539069","https://openalex.org/W3173503818","https://openalex.org/W4249052411","https://openalex.org/W4285719527","https://openalex.org/W6630424276","https://openalex.org/W6633567737","https://openalex.org/W6634092760","https://openalex.org/W6677032448","https://openalex.org/W6677131165","https://openalex.org/W6677380243","https://openalex.org/W6679388247","https://openalex.org/W6681388093","https://openalex.org/W6712911086","https://openalex.org/W6797375751"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W1977167953","https://openalex.org/W2122030153","https://openalex.org/W2078842457","https://openalex.org/W2162449135","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481"],"abstract_inverted_index":{"Humans":[0],"can":[1,89],"extract":[2],"speech":[3,95,106],"signals":[4,45],"that":[5,39,150],"they":[6],"need":[7],"to":[8,191,212],"understand":[9],"from":[10,91],"a":[11,147,173,188],"mixture":[12],"of":[13,54,64,117,221,227,235],"background":[14],"noise,":[15],"interfering":[16],"sound":[17,44],"sources,":[18],"and":[19,28,59,69,105,115,120,156,165,172,183,195,200],"reverberation":[20],"for":[21,77,93,102,161,197],"effective":[22],"communication.":[23],"Voice":[24],"Activity":[25],"Detection":[26],"(VAD)":[27],"Sound":[29],"Source":[30],"Localization":[31],"(SSL)":[32],"are":[33,127],"the":[34,52,61,65,73,138,163,178,205,232,236],"key":[35],"signal":[36],"processing":[37,43],"components":[38],"humans":[40],"perform":[41,192],"by":[42,57],"received":[46],"at":[47],"both":[48,193],"ears,":[49],"sometimes":[50],"with":[51,86,210,223],"help":[53],"visual":[55],"cues":[56],"locating":[58],"observing":[60],"lip":[62],"movements":[63],"speaker.":[66],"Both":[67],"VAD":[68,119,194,219],"SSL":[70,121,196],"serve":[71],"as":[72],"crucial":[74],"design":[75,114],"elements":[76],"building":[78],"applications":[79],"involving":[80],"human":[81],"speech.":[82],"For":[83],"example,":[84],"systems":[85],"microphone":[87,174],"arrays":[88],"benefit":[90],"these":[92],"robust":[94,118],"capture":[96],"in":[97,108,123,137,208],"video":[98,164],"conferencing":[99],"applications,":[100],"or":[101],"speaker":[103],"identification":[104],"recognition":[107],"Human":[109],"Computer":[110],"Interfaces":[111],"(HCIs).":[112],"The":[113],"implementation":[116],"algorithms":[122],"practical":[124],"acoustic":[125],"environments":[126],"still":[128],"challenging":[129],"problems,":[130],"particularly":[131],"when":[132,230],"multiple":[133,198],"simultaneous":[134,214],"speakers":[135],"exist":[136],"same":[139],"audiovisual":[140],"scene.":[141],"In":[142],"this":[143],"work":[144],"we":[145,186],"propose":[146,187],"multimodal":[148],"approach":[149,190],"uses":[151],"Support":[152],"Vector":[153],"Machines":[154],"(SVMs)":[155],"Hidden":[157],"Markov":[158],"Models":[159],"(HMMs)":[160],"assessing":[162],"audio":[166],"modalities":[167],"through":[168],"an":[169,217,224],"RGB":[170],"camera":[171],"array.":[175],"By":[176],"analyzing":[177],"individual":[179],"speakers'":[180],"spatio-temporal":[181],"activities":[182],"mouth":[184],"movements,":[185],"mid-fusion":[189],"active":[199],"inactive":[201],"speakers.":[202,237],"We":[203],"tested":[204],"proposed":[206],"algorithm":[207],"scenarios":[209],"up":[211],"three":[213],"speakers,":[215],"showing":[216],"average":[218,225],"accuracy":[220],"95.06%":[222],"error":[226],"10.9":[228],"cm":[229],"estimating":[231],"three-dimensional":[233],"locations":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}