{"id":"https://openalex.org/W2142075667","doi":"https://doi.org/10.1109/tasl.2008.2011515","title":"Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition","display_name":"Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition","publication_year":2009,"publication_date":"2009-02-13","ids":{"openalex":"https://openalex.org/W2142075667","doi":"https://doi.org/10.1109/tasl.2008.2011515","mag":"2142075667"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2011515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2011515","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doi.org/10.1109/TASL.2008.2011515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034294456","display_name":"George Papandreou","orcid":"https://orcid.org/0000-0002-1468-2976"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Papandreou","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003869083","display_name":"Athanasios Katsamanis","orcid":"https://orcid.org/0000-0002-2642-2354"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanassios Katsamanis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040922549","display_name":"Vassilis Pitsikalis","orcid":"https://orcid.org/0000-0002-1593-7491"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Pitsikalis","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079243420","display_name":"Petros Maragos","orcid":"https://orcid.org/0000-0003-0534-2707"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]},{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Petros Maragos","raw_affiliation_strings":["School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, National and Technical University of Athens, Athens, Greece","institution_ids":["https://openalex.org/I174458059"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng. Nat., Tech. Univ. of Athens, Athens","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6406,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.96333423,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"17","issue":"3","first_page":"423","last_page":"435"},"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":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987999796867371,"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":0.8090674877166748},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6498360633850098},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6102055311203003},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5310203433036804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123625993728638},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46193352341651917},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4600839614868164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4360809326171875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39826223254203796},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34023576974868774},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08629918098449707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090674877166748},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6498360633850098},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6102055311203003},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5310203433036804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123625993728638},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46193352341651917},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4600839614868164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4360809326171875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39826223254203796},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34023576974868774},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08629918098449707},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2008.2011515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2011515","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.7814","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.7814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cvsp.cs.ntua.gr/publications/jpubl+bchap/PapandreouKatsamanisPitsikalisMaragos_MultimodalFusionUncertaintyCompensationAvasr_ieee-j-aslp09.pdf","raw_type":"text"},{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/19344","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TASL.2008.2011515","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:dspace.lib.ntua.gr:123456789/19344","is_oa":true,"landing_page_url":"http://doi.org/10.1109/TASL.2008.2011515","pdf_url":null,"source":{"id":"https://openalex.org/S4377196837","display_name":"DSpace - NTUA (National Technical University of Athens)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I174458059","host_organization_name":"National Technical University of Athens","host_organization_lineage":["https://openalex.org/I174458059"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321917","display_name":"General Secretariat for Research and Technology","ror":"https://ror.org/04yeh8h63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W135040384","https://openalex.org/W250076511","https://openalex.org/W1211870555","https://openalex.org/W1523010034","https://openalex.org/W1529401398","https://openalex.org/W1557636172","https://openalex.org/W1568281349","https://openalex.org/W1576996184","https://openalex.org/W1589328436","https://openalex.org/W1600785936","https://openalex.org/W1869491686","https://openalex.org/W1877570817","https://openalex.org/W1932968309","https://openalex.org/W1965392255","https://openalex.org/W1978380426","https://openalex.org/W1984746632","https://openalex.org/W2015394094","https://openalex.org/W2021279213","https://openalex.org/W2036205336","https://openalex.org/W2045607566","https://openalex.org/W2049633694","https://openalex.org/W2051091181","https://openalex.org/W2082308025","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2101995396","https://openalex.org/W2102863932","https://openalex.org/W2105523781","https://openalex.org/W2107223151","https://openalex.org/W2111581792","https://openalex.org/W2113814270","https://openalex.org/W2120974626","https://openalex.org/W2121486117","https://openalex.org/W2125838338","https://openalex.org/W2132549764","https://openalex.org/W2133115605","https://openalex.org/W2133906911","https://openalex.org/W2134929491","https://openalex.org/W2138084857","https://openalex.org/W2143451044","https://openalex.org/W2145475542","https://openalex.org/W2149063730","https://openalex.org/W2149361029","https://openalex.org/W2152826865","https://openalex.org/W2158275940","https://openalex.org/W2158289097","https://openalex.org/W2164598857","https://openalex.org/W2165759752","https://openalex.org/W2171209807","https://openalex.org/W2171244697","https://openalex.org/W2341283081","https://openalex.org/W2501398076","https://openalex.org/W2793908218","https://openalex.org/W3042168128","https://openalex.org/W3143949042","https://openalex.org/W4231869218","https://openalex.org/W6627960130","https://openalex.org/W6634430985","https://openalex.org/W6639013534","https://openalex.org/W6675525468","https://openalex.org/W6675752027","https://openalex.org/W6676227212","https://openalex.org/W6684089741"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W2367372208","https://openalex.org/W4306674287","https://openalex.org/W2006363920","https://openalex.org/W2475836838","https://openalex.org/W3100791781","https://openalex.org/W1548344605","https://openalex.org/W2546942002","https://openalex.org/W2970216048","https://openalex.org/W2382607599"],"abstract_inverted_index":{"While":[0],"the":[1,13,84,95,157,216,227],"accuracy":[2],"of":[3,15,73,160,218],"feature":[4,35,90,189],"measurements":[5],"heavily":[6],"depends":[7],"on":[8,139,226],"changing":[9],"environmental":[10],"conditions,":[11],"studying":[12],"consequences":[14],"this":[16,30,151,180],"fact":[17],"in":[18,61,221],"pattern":[19],"recognition":[20,224],"tasks":[21],"has":[22],"received":[23],"relatively":[24],"little":[25],"attention":[26],"to":[27,51,99,110],"date.":[28],"In":[29,179],"paper,":[31],"we":[32,182],"explicitly":[33],"take":[34],"measurement":[36,85],"uncertainty":[37,87,163,192,208],"into":[38,156],"account":[39],"and":[40,45,108,117,191,198],"show":[41,133,167],"how":[42,168,201],"multimodal":[43,62,102,127,135,162,235],"classification":[44],"learning":[46],"rules":[47,104],"should":[48],"be":[49,93,119,172,211],"adjusted":[50],"compensate":[52],"for":[53,88,175,186],"its":[54],"effects.":[55],"Our":[56,112],"approach":[57,220],"is":[58,114],"particularly":[59],"fruitful":[60],"fusion":[63,103,136],"scenarios,":[64],"such":[65,80],"as":[66],"audiovisual":[67,176,222],"speech":[68,177,223],"recognition,":[69],"where":[70],"multiple":[71],"streams":[72],"complementary":[74],"time-evolving":[75],"features":[76,204],"are":[77,106],"integrated.":[78],"For":[79],"applications,":[81],"provided":[82],"that":[83,134],"noise":[86],"each":[89],"stream":[91,140],"can":[92,118,142,171,210],"estimated,":[94],"proposed":[96],"framework":[97],"leads":[98],"highly":[100],"adaptive":[101],"which":[105],"easy":[107],"efficient":[109],"implement.":[111],"technique":[113],"widely":[115],"applicable":[116],"transparently":[120],"integrated":[121],"with":[122,194,206],"either":[123,231],"synchronous":[124,232],"or":[125,233],"asynchronous":[126,234],"sequence":[128],"integration":[129,236],"architectures.":[130],"We":[131,166,214],"further":[132],"methods":[137],"relying":[138],"weights":[141],"naturally":[143],"emerge":[144],"from":[145],"our":[146,161,219],"scheme":[147],"under":[148],"certain":[149],"assumptions;":[150],"connection":[152],"provides":[153],"valuable":[154],"insights":[155],"adaptivity":[158],"properties":[159],"compensation":[164],"approach.":[165],"these":[169],"ideas":[170],"practically":[173],"applied":[174],"recognition.":[178],"context,":[181],"propose":[183],"improved":[184],"techniques":[185],"person-independent":[187],"visual":[188],"extraction":[190],"estimation":[193],"active":[195],"appearance":[196],"models,":[197],"also":[199],"discuss":[200],"enhanced":[202],"audio":[203],"along":[205],"their":[207],"estimates":[209],"effectively":[212],"computed.":[213],"demonstrate":[215],"efficacy":[217],"experiments":[225],"CUAVE":[228],"database":[229],"using":[230],"models.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}