{"id":"https://openalex.org/W2890137412","doi":"https://doi.org/10.1109/icip.2018.8451435","title":"Towards View-Independent Viseme Recognition Based on CNNS and Synthetic Data","display_name":"Towards View-Independent Viseme Recognition Based on CNNS and Synthetic Data","publication_year":2018,"publication_date":"2018-09-07","ids":{"openalex":"https://openalex.org/W2890137412","doi":"https://doi.org/10.1109/icip.2018.8451435","mag":"2890137412"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2018.8451435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","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/A5064860556","display_name":"Andr\u00e9a Britto Mattos","orcid":"https://orcid.org/0009-0009-8696-1446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Britto Mattos","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051251449","display_name":"D\u00e1rio Augusto Borges Oliveira","orcid":"https://orcid.org/0000-0002-0674-5332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dario Augusto Borges Oliveira","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson Da Silva Morais","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3608,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51417212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1611 1599","issue":null,"first_page":"589","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11448","display_name":"Face recognition and analysis","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.8404653072357178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8393566608428955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294583678245544},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5863958597183228},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5372118353843689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5102794170379639},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46241283416748047},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45996078848838806},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4464058578014374},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4341159462928772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34172409772872925},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2347046136856079},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.09016016125679016}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.8404653072357178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8393566608428955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294583678245544},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5863958597183228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5372118353843689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5102794170379639},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46241283416748047},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45996078848838806},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4464058578014374},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4341159462928772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34172409772872925},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2347046136856079},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.09016016125679016},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/icip.2018.8451435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2018.8451435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1556470778","https://openalex.org/W1578725541","https://openalex.org/W1908325895","https://openalex.org/W1982883756","https://openalex.org/W2015143272","https://openalex.org/W2060510034","https://openalex.org/W2098355375","https://openalex.org/W2113270438","https://openalex.org/W2113814270","https://openalex.org/W2115252128","https://openalex.org/W2151323546","https://openalex.org/W2163516157","https://openalex.org/W2163973301","https://openalex.org/W2243738093","https://openalex.org/W2293862876","https://openalex.org/W2474638510","https://openalex.org/W2531409750","https://openalex.org/W2550980560","https://openalex.org/W2585824449","https://openalex.org/W2741151796","https://openalex.org/W2799525592","https://openalex.org/W2891226622","https://openalex.org/W2952746495","https://openalex.org/W4293862381","https://openalex.org/W6605769872","https://openalex.org/W6639968709","https://openalex.org/W6677618333","https://openalex.org/W6729540071","https://openalex.org/W6750475725","https://openalex.org/W6765296696"],"related_works":["https://openalex.org/W4312659495","https://openalex.org/W4385366257","https://openalex.org/W3101007570","https://openalex.org/W4387910575","https://openalex.org/W3176425421","https://openalex.org/W3091312527","https://openalex.org/W1555087354","https://openalex.org/W4287865546","https://openalex.org/W3007306981","https://openalex.org/W2949555133"],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"is":[3],"the":[4,30,45,63,84],"ability":[5],"to":[6,55],"interpret":[7],"spoken":[8],"text":[9],"using":[10,103,139,150],"video":[11],"information":[12],"only.":[13],"To":[14],"address":[15],"such":[16,60],"task":[17],"automatically,":[18],"recent":[19],"works":[20],"have":[21],"employed":[22],"Deep":[23],"Learning":[24],"and":[25,34,51,76,100,105,125],"obtained":[26],"high":[27],"accuracy":[28,46,145],"on":[29,117,154],"recognition":[31,91],"of":[32,72,86,92],"words":[33],"sentences":[35],"uttered":[36],"in":[37,94],"controlled":[38,99],"environments,":[39,102],"with":[40,123],"limited":[41],"head-pose":[42],"variation.":[43],"However,":[44],"drops":[47],"for":[48,89],"multi-view":[49,126],"datasets":[50,88,115],"when":[52],"it":[53],"comes":[54],"interpreting":[56],"isolated":[57],"mouth":[58,127],"shapes,":[59],"as":[61,69],"visemes,":[62],"values":[64],"reported":[65],"are":[66],"considerably":[67],"lower,":[68],"shorter":[70],"segments":[71],"speech":[73],"lack":[74],"temporal":[75],"contextual":[77],"information.":[78],"In":[79],"this":[80],"work,":[81],"we":[82],"evaluate":[83],"applicability":[85],"synthetic":[87,113,140],"assisting":[90],"visemes":[93],"real-world":[95],"data":[96,141,152],"acquired":[97],"under":[98],"uncontrolled":[101],"GRID":[104],"AVICAR":[106],"datasets,":[107],"respectively.":[108],"We":[109,129],"create":[110],"two":[111],"large-scale":[112],"2D":[114],"based":[116],"realistic":[118],"3D":[119],"facial":[120],"models":[121],"-":[122],"near-frontal":[124],"images.":[128],"perform":[130],"experiments":[131],"that":[132,134],"indicate":[133],"a":[135],"transfer":[136],"learning":[137],"approach":[138],"can":[142],"get":[143],"higher":[144],"than":[146],"training":[147],"from":[148],"scratch":[149],"real":[151],"only,":[153],"both":[155],"scenarios.":[156]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}