{"id":"https://openalex.org/W2079025426","doi":"https://doi.org/10.1145/1643823.1643896","title":"Robust audio-visual speaker identification using a modified score-based reliability in modality integration","display_name":"Robust audio-visual speaker identification using a modified score-based reliability in modality integration","publication_year":2009,"publication_date":"2009-10-27","ids":{"openalex":"https://openalex.org/W2079025426","doi":"https://doi.org/10.1145/1643823.1643896","mag":"2079025426"},"language":"en","primary_location":{"id":"doi:10.1145/1643823.1643896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1643823.1643896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Management of Emergent Digital EcoSystems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019358557","display_name":"Md. Tariquzzaman","orcid":"https://orcid.org/0000-0002-3341-7457"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Md. Tariquzzaman","raw_affiliation_strings":["Chonnam National University, Gwangju, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417174","display_name":"Jin Young Kim","orcid":"https://orcid.org/0000-0002-4896-8980"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin Young Kim","raw_affiliation_strings":["Chonnam National University, Gwangju, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051171199","display_name":"Seung You Na","orcid":"https://orcid.org/0000-0001-8754-6230"},"institutions":[{"id":"https://openalex.org/I111277659","display_name":"Chonnam National University","ror":"https://ror.org/05kzjxq56","country_code":"KR","type":"education","lineage":["https://openalex.org/I111277659"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung You Na","raw_affiliation_strings":["Chonnam National University, Gwangju, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chonnam National University, Gwangju, Republic of Korea","institution_ids":["https://openalex.org/I111277659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111277659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10593923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"399","last_page":"403"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.998199999332428,"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":0.76551753282547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5699999332427979},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.5623382329940796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4998805522918701},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45544126629829407},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4341658353805542},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4337715804576874},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.42459675669670105},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4217302203178406},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22019603848457336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76551753282547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5699999332427979},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.5623382329940796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4998805522918701},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45544126629829407},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4341658353805542},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4337715804576874},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.42459675669670105},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4217302203178406},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22019603848457336},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1643823.1643896","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1643823.1643896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Management of Emergent Digital EcoSystems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6899999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W175297027","https://openalex.org/W1825163061","https://openalex.org/W2050693797","https://openalex.org/W2059857061","https://openalex.org/W2069976350","https://openalex.org/W2070176749","https://openalex.org/W2075306129","https://openalex.org/W2098005752","https://openalex.org/W2102051978","https://openalex.org/W2104687512","https://openalex.org/W2109364787","https://openalex.org/W2121122425","https://openalex.org/W2129244720","https://openalex.org/W2133115605","https://openalex.org/W2135433537","https://openalex.org/W2137075158","https://openalex.org/W2140959843","https://openalex.org/W2152239535","https://openalex.org/W2165880886"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"Identity":[0],"recognition":[1],"in":[2,12,60,87,170,177,187],"real":[3],"environment":[4],"with":[5,172],"reliable":[6],"mode":[7],"is":[8],"a":[9,22,127],"key":[10],"issue":[11],"human":[13],"computer":[14],"interaction":[15],"(HCI).":[16],"In":[17,82],"this":[18],"paper,":[19],"we":[20,74],"present":[21],"robust":[23,66],"speaker":[24,62,67,145],"identification":[25,63,146,166],"system":[26,64,176,180],"considering":[27],"score":[28],"based":[29,57],"optimal":[30,49,159],"reliability":[31,50,58,160,185],"measure":[32,59],"of":[33,40,71,121,168,189,196],"different":[34],"modalities.":[35],"We":[36,124],"propose":[37],"an":[38],"extension":[39],"the":[41,119,137,165,173,178,183,194,197],"modified":[42,138],"convection":[43,139],"function's":[44,140],"optimizing":[45,136,141],"parameter":[46],"to":[47,79,102,114],"account":[48],"simultaneously":[51],"via":[52],"audio":[53,104],"and":[54,90,96,105,181],"lip":[55],"information":[56],"bimodal":[61],"for":[65,84,117,135],"identification.":[68],"For":[69],"degradation":[70],"visual":[72,106],"signals,":[73,107],"have":[75,99,125,162],"applied":[76,126],"JPEG":[77],"compression":[78],"test":[80,91,103],"images.":[81],"addition,":[83],"creating":[85],"mismatch":[86],"between":[88],"enrollment":[89],"session,":[92],"acoustic":[93],"Babble":[94],"noises":[95],"artificial":[97],"illumination":[98],"been":[100,112],"added":[101],"respectively.":[108],"Local":[109],"PCA":[110],"has":[111],"used":[113],"both":[115],"modalities":[116],"reducing":[118],"dimension":[120],"feature":[122],"vector.":[123],"swarm":[128,133],"intelligence":[129],"algorithm":[130],"i.e.,":[131],"particle":[132],"optimization":[134],"parameters.":[142],"The":[143],"overall":[144],"experiments":[147],"are":[148],"performed":[149],"using":[150],"VidTimit":[151],"DB.":[152],"Experimental":[153],"results":[154],"show":[155],"that":[156],"our":[157],"proposed":[158,198],"measures":[161],"effectively":[163],"enhanced":[164],"accuracy":[167],"7.73%":[169],"comparison":[171],"best":[174],"classifier":[175],"integration":[179],"maintains":[182],"modality":[184],"statistics":[186],"term":[188],"its":[190],"performance":[191],"thus":[192],"verified":[193],"consistency":[195],"extension.":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
