{"id":"https://openalex.org/W2959515469","doi":"https://doi.org/10.1109/fg.2019.8756589","title":"Improving Viseme Recognition with GAN-based Muti-view Mapping","display_name":"Improving Viseme Recognition with GAN-based Muti-view Mapping","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2959515469","doi":"https://doi.org/10.1109/fg.2019.8756589","mag":"2959515469"},"language":"en","primary_location":{"id":"doi:10.1109/fg.2019.8756589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2019.8756589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","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/A5051251449","display_name":"D\u00e1rio Augusto Borges Oliveira","orcid":"https://orcid.org/0000-0002-0674-5332"},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Dario Augusto Borges Oliveira","raw_affiliation_strings":["IBM Research, Sao Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064860556","display_name":"Andr\u00e9a Britto Mattos","orcid":"https://orcid.org/0009-0009-8696-1446"},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Andrea Britto Mattos","raw_affiliation_strings":["IBM Research, Sao Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113516","display_name":"IBM Research - Brazil","ror":"https://ror.org/01fxqdx25","country_code":"BR","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210113516","https://openalex.org/I4210114115"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edmilson da Silva Morais","raw_affiliation_strings":["IBM Research, Sao Paulo, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Sao Paulo, Brazil","institution_ids":["https://openalex.org/I4210113516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113516"],"apc_list":null,"apc_paid":null,"fwci":0.1912,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33851446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1809 981","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9962000250816345,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9700999855995178,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/viseme","display_name":"Viseme","score":0.8983154296875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519115447998047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6383204460144043},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5821214914321899},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5443366169929504},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4546204209327698},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.45376765727996826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4399019479751587},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43989184498786926},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4127455949783325},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.16934281587600708},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.07850518822669983}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.8983154296875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519115447998047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6383204460144043},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5821214914321899},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5443366169929504},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4546204209327698},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.45376765727996826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4399019479751587},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43989184498786926},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4127455949783325},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.16934281587600708},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.07850518822669983},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg.2019.8756589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2019.8756589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1503762774","https://openalex.org/W1526392145","https://openalex.org/W1578725541","https://openalex.org/W1982883756","https://openalex.org/W2015143272","https://openalex.org/W2099471712","https://openalex.org/W2113814270","https://openalex.org/W2115252128","https://openalex.org/W2125389028","https://openalex.org/W2151323546","https://openalex.org/W2163973301","https://openalex.org/W2243738093","https://openalex.org/W2474638510","https://openalex.org/W2487271655","https://openalex.org/W2531409750","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2747874407","https://openalex.org/W2755403114","https://openalex.org/W2763858995","https://openalex.org/W2768242826","https://openalex.org/W2770173563","https://openalex.org/W2785885246","https://openalex.org/W2799525592","https://openalex.org/W2799956544","https://openalex.org/W2817444562","https://openalex.org/W2884547199","https://openalex.org/W2889871190","https://openalex.org/W2890137412","https://openalex.org/W2890234956","https://openalex.org/W2893436174","https://openalex.org/W2897846591","https://openalex.org/W2952746495","https://openalex.org/W2953050027","https://openalex.org/W2962912639","https://openalex.org/W2963073614","https://openalex.org/W2963613219","https://openalex.org/W4293862381","https://openalex.org/W4301183790","https://openalex.org/W4320013936","https://openalex.org/W6605769872","https://openalex.org/W6630093300","https://openalex.org/W6677618333","https://openalex.org/W6678815747","https://openalex.org/W6729540071","https://openalex.org/W6729966448","https://openalex.org/W6744989064","https://openalex.org/W6746638498","https://openalex.org/W6750475725","https://openalex.org/W6754460971","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W2741151796","https://openalex.org/W2401811665","https://openalex.org/W2306241824","https://openalex.org/W2963024054","https://openalex.org/W2108033344","https://openalex.org/W2161997376","https://openalex.org/W2099257899"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,74,109,236],"technologies":[2],"in":[3,14,76,110,143,154],"the":[4,20,41,73,88,115,156,177,187,194,200,223,228,234],"visual":[5,22],"domain":[6],"currently":[7],"can":[8,71],"only":[9,185],"identify":[10],"words":[11],"and":[12,113,137,150,165,179,215,218],"sentences":[13],"still":[15,111],"images.":[16],"Identifying":[17],"visemes":[18,178],"(i.e.,":[19],"smallest":[21],"units":[23],"of":[24,87,118],"spoken":[25],"text)":[26],"is":[27,39,49,158],"useful":[28],"when":[29,183],"there":[30],"are":[31,92,230],"no":[32],"language":[33],"models":[34],"or":[35],"dictionaries":[36],"available,":[37],"which":[38,155],"often":[40],"case":[42],"for":[43,175],"languages":[44],"besides":[45],"English;":[46],"however,":[47,85],"it":[48],"a":[50,95,144,170],"challenge,":[51],"as":[52],"temporal":[53],"information":[54],"cannot":[55],"be":[56],"extracted.":[57],"In":[58,103],"parallel,":[59],"previous":[60],"works":[61],"demonstrated":[62],"that":[63,222],"exploring":[64],"data":[65,136],"acquired":[66,142,209],"simultaneously":[67],"under":[68,210],"multiple":[69],"views":[70,120,152,196,225],"improve":[72,122,233],"accuracy":[75,237],"comparison":[77],"to":[78,100,121,148,232],"single-view":[79,189],"data.":[80],"For":[81,125],"many":[82],"different":[83,211],"applications,":[84],"most":[86],"available":[89],"audio-visual":[90],"datasets":[91],"obtained":[93],"from":[94,139],"single":[96,145],"view,":[97],"essentially":[98],"due":[99],"acquisition":[101],"limitations.":[102],"this":[104],"work,":[105],"we":[106,127,168],"address":[107],"viseme":[108,235],"images":[112,141,190],"explore":[114],"synthetic":[116,135],"generation":[117],"additional":[119,195,224],"overall":[123],"accuracy.":[124],"that,":[126],"use":[128,169],"Generative":[129],"Adversarial":[130],"Networks":[131],"(GANs)":[132],"trained":[133],"with":[134,186,193],"map":[138],"mouth":[140],"arbitrary":[146],"view":[147],"frontal":[149],"side":[151],"-":[153],"face":[157],"rotated":[159],"vertically":[160],"at":[161],"approximately":[162],"30\u00b0,":[163],"45\u00b0,":[164],"60\u00b0.":[166],"Then,":[167],"state-of-art":[171],"Convolutional":[172],"Neural":[173],"Network":[174],"classifying":[176],"compare":[180],"its":[181],"performance":[182],"training":[184,192],"original":[188],"versus":[191],"artificially":[197],"generated":[198],"by":[199,227],"GANs.":[201],"We":[202],"run":[203],"experiments":[204],"using":[205],"three":[206],"audiovisual":[207],"corpora":[208],"conditions":[212],"(GRID,":[213],"AVICAR,":[214],"OuluVS2":[216],"datasets)":[217],"our":[219],"results":[220],"indicate":[221],"synthesized":[226],"GANs":[229],"able":[231],"on":[238],"all":[239],"tested":[240],"scenarios.":[241]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}