{"id":"https://openalex.org/W1984634380","doi":"https://doi.org/10.1145/2141622.2141646","title":"Audio visual speech recognition in noisy visual environments","display_name":"Audio visual speech recognition in noisy visual environments","publication_year":2011,"publication_date":"2011-05-25","ids":{"openalex":"https://openalex.org/W1984634380","doi":"https://doi.org/10.1145/2141622.2141646","mag":"1984634380"},"language":"en","primary_location":{"id":"doi:10.1145/2141622.2141646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2141622.2141646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-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/A5046329678","display_name":"Georgios Galatas","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR","US"],"is_corresponding":true,"raw_author_name":"Georgios Galatas","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington","Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington#TAB#","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I4387152169","display_name":"Institute of Informatics & Telecommunications","ror":"https://ror.org/0396t6k89","country_code":null,"type":"facility","lineage":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR Demokritos, Greece"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR Demokritos, Greece","institution_ids":["https://openalex.org/I203474044","https://openalex.org/I4387152169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014990977","display_name":"Alexandros Papangelis","orcid":null},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]},{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Alexandros Papangelis","raw_affiliation_strings":["Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington","Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington#TAB#"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"Institute of Informatics and Telecommunications, NCSR Demokritos, Greece, and University of Texas at Arlington#TAB#","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044363105","display_name":"Fillia Makedon","orcid":"https://orcid.org/0009-0001-8831-6872"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fillia Makedon","raw_affiliation_strings":["University of Texas at Arlington"],"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046329678"],"corresponding_institution_ids":["https://openalex.org/I189196454","https://openalex.org/I203474044"],"apc_list":null,"apc_paid":null,"fwci":1.2249,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77922683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000755310058594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7914291620254517},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.586097240447998},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5060705542564392},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45995935797691345},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4116547107696533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3683915138244629},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0978817343711853},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07629388570785522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000755310058594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7914291620254517},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.586097240447998},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5060705542564392},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45995935797691345},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4116547107696533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3683915138244629},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0978817343711853},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07629388570785522},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2141622.2141646","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2141622.2141646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on PErvasive Technologies Related to Assistive Environments","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3868596738","display_name":null,"funder_award_id":"MRI 0923494","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6291011351","display_name":null,"funder_award_id":"FP7-PEOPLE-2009-RG-247948","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338368","display_name":"FP7 People: Marie-Curie Actions","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W4952878","https://openalex.org/W88081813","https://openalex.org/W1506806321","https://openalex.org/W1516742535","https://openalex.org/W1663973292","https://openalex.org/W2084843887","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2106284211","https://openalex.org/W2122356972","https://openalex.org/W2254457717","https://openalex.org/W2407414360","https://openalex.org/W3157685993","https://openalex.org/W6603616073"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,31,39],"is":[2],"a":[3,9,12,25,29,100],"natural":[4],"means":[5],"of":[6,43,52,58,79,91,102,104,147],"interaction":[7,20],"for":[8,18],"human":[10],"with":[11],"smart":[13,126],"assistive":[14,127],"environment.":[15],"In":[16,72],"order":[17],"this":[19,73],"to":[21,61,82,137],"be":[22,42,110,123],"effective,":[23],"such":[24,46],"system":[26,131],"should":[27],"attain":[28],"high":[30],"rate":[32],"even":[33],"under":[34,49,95],"adverse":[35],"conditions.":[36],"Audio-visual":[37],"speech":[38],"(AVSR)":[40],"can":[41,109,122],"help":[44],"in":[45,69,125,135,144],"environments,":[47],"especially":[48],"the":[50,56,70,77,87],"presence":[51],"audio":[53],"noise.":[54,106],"However":[55],"impact":[57],"visual":[59,80,105],"noise":[60,81,98],"its":[62],"performance":[63,143],"has":[64],"not":[65],"been":[66],"studied":[67],"sufficiently":[68],"literature.":[71],"paper,":[74],"we":[75],"examine":[76],"effects":[78],"AVSR,":[83],"reporting":[84],"experiments":[85],"on":[86],"relatively":[88],"simple":[89],"task":[90],"connected":[92],"digit":[93],"recognition,":[94],"moderate":[96],"acoustic":[97],"and":[99,141],"variety":[101],"types":[103],"The":[107],"latter":[108],"caused":[111],"by":[112],"either":[113],"faulty":[114],"sensors":[115],"or":[116],"video":[117,149],"signal":[118],"transmission":[119],"problems":[120],"that":[121],"found":[124],"environments.":[128],"Our":[129],"AVSR":[130],"exhibits":[132],"higher":[133],"accuracy":[134],"comparison":[136],"an":[138],"audio-only":[139],"recognizer":[140],"robust":[142],"most":[145],"cases":[146],"noisy":[148],"signals":[150],"considered.":[151]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
