{"id":"https://openalex.org/W2599380898","doi":"https://doi.org/10.5220/0006102100520063","title":"Automatic Viseme Vocabulary Construction to Enhance Continuous Lip-reading","display_name":"Automatic Viseme Vocabulary Construction to Enhance Continuous Lip-reading","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2599380898","doi":"https://doi.org/10.5220/0006102100520063","mag":"2599380898"},"language":"en","primary_location":{"id":"doi:10.5220/0006102100520063","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0006102100520063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1704.08035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079540599","display_name":"Adriana Fernandez-Lopez","orcid":"https://orcid.org/0000-0001-8839-6537"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adriana Fernandez-Lopez","raw_affiliation_strings":["Pompeu Fabra University, Spain","Pompeu Fabra University, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019420087","display_name":"Federico M. Sukno","orcid":"https://orcid.org/0000-0002-2029-1576"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Federico M. Sukno","raw_affiliation_strings":["Pompeu Fabra University, Spain","Pompeu Fabra University, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01944861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"63"},"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/T11309","display_name":"Music and Audio Processing","score":0.9851999878883362,"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/T12032","display_name":"Multisensory perception and integration","score":0.9699000120162964,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.9845741987228394},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.795063853263855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6934630274772644},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6029201745986938},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49000754952430725},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4372550845146179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43097907304763794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4295384883880615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42155763506889343},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23892009258270264},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16549286246299744},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.11669939756393433}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9845741987228394},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.795063853263855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934630274772644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6029201745986938},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49000754952430725},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4372550845146179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43097907304763794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4295384883880615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42155763506889343},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23892009258270264},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16549286246299744},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.11669939756393433},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.5220/0006102100520063","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0006102100520063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/32161","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/32161","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:1704.08035","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.08035","pdf_url":"https://arxiv.org/pdf/1704.08035","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2599380898","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1704.08035.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1704.08035","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.08035","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1704.08035","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.08035","pdf_url":"https://arxiv.org/pdf/1704.08035","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3402147602","display_name":null,"funder_award_id":"MDM-2015-0502","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G7865797263","display_name":"Knowledge-Based Information Agent with Social Competence and Human Interaction Capabilities","funder_award_id":"645012","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W242871668","https://openalex.org/W1499889635","https://openalex.org/W1527482779","https://openalex.org/W1908325895","https://openalex.org/W1991893000","https://openalex.org/W2002322356","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2059300355","https://openalex.org/W2071096833","https://openalex.org/W2071828724","https://openalex.org/W2094829487","https://openalex.org/W2096391593","https://openalex.org/W2096651761","https://openalex.org/W2101013379","https://openalex.org/W2107435954","https://openalex.org/W2108033344","https://openalex.org/W2121486117","https://openalex.org/W2125013164","https://openalex.org/W2125838338","https://openalex.org/W2136155248","https://openalex.org/W2138527036","https://openalex.org/W2157342624","https://openalex.org/W2163973301","https://openalex.org/W2164450870","https://openalex.org/W2170413589","https://openalex.org/W2208724044","https://openalex.org/W2407584378","https://openalex.org/W2579335913","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W2741151796","https://openalex.org/W2963024054","https://openalex.org/W2914051086","https://openalex.org/W3098841379","https://openalex.org/W2422219919","https://openalex.org/W3128582036","https://openalex.org/W2983717799","https://openalex.org/W2621099724","https://openalex.org/W2888864950","https://openalex.org/W3155765542","https://openalex.org/W2775488304","https://openalex.org/W2742351105","https://openalex.org/W3115363692","https://openalex.org/W2237869926","https://openalex.org/W2159667924","https://openalex.org/W2155477915","https://openalex.org/W1550092932","https://openalex.org/W2101918136","https://openalex.org/W2051884718","https://openalex.org/W2981978471"],"abstract_inverted_index":{"Speech":[0],"is":[1,39,50,53,63,242],"the":[2,11,25,42,45,60,64,67,80,83,128,138,160,164,171,182,185,218,222,227,236],"most":[3],"common":[4],"communication":[5],"method":[6],"between":[7,95],"humans":[8],"and":[9,16,52,73,88,97,112,167,177,191,224,234],"involves":[10],"perception":[12],"of":[13,47,59,66,82,131,140,163,174,184,203,217,221,226],"both":[14,175],"auditory":[15],"visual":[17,68],"channels.":[18],"Automatic":[19],"speech":[20,232],"recognition":[21],"focuses":[22],"on":[23,127,137],"interpreting":[24],"audio":[26],"signals,":[27],"but":[28],"it":[29],"has":[30],"been":[31,105],"demonstrated":[32],"that":[33,38,153,209,235],"video":[34],"can":[35],"provide":[36],"information":[37],"complementary":[40],"to":[41,85,158,169,213],"audio.":[43],"Thus,":[44],"study":[46],"automatic":[48,129,151],"lip-reading":[49],"important":[51],"still":[54],"an":[55,132,150],"open":[56],"problem.":[57],"One":[58],"key":[61],"challenges":[62],"definition":[65],"elementary":[69],"units":[70],"(the":[71],"visemes)":[72],"their":[74,109],"vocabulary.":[75],"Many":[76],"researchers":[77],"have":[78,89,103],"analyzed":[79],"importance":[81],"phoneme":[84,178],"viseme":[86,91,101,134,176,238],"mapping":[87],"proposed":[90],"vocabularies":[92,102],"with":[93,142],"lengths":[94],"11":[96],"15":[98],"visemes.":[99,246],"These":[100],"usually":[104],"manually":[106],"defined":[107],"by":[108,244],"linguistic":[110],"properties":[111],"in":[113,199,229],"some":[114],"cases":[115],"using":[116],"decision":[117],"trees":[118],"or":[119],"clustering":[120],"techniques.":[121],"In":[122],"this":[123,146],"work,":[124],"we":[125,148,210],"focus":[126],"construction":[130],"optimal":[133,237],"vocabulary":[135,239],"based":[136],"association":[139],"phonemes":[141,223],"similar":[143],"appearance.":[144],"To":[145,180],"end,":[147],"construct":[149],"system":[152,186,198],"uses":[154],"local":[155],"appearance":[156],"descriptors":[157,188],"extract":[159],"main":[161],"characteristics":[162],"mouth":[165],"region":[166],"HMMs":[168],"model":[170],"statistic":[172],"relations":[173],"sequences.":[179],"compare":[181],"performance":[183],"different":[187],"(PCA,":[189],"DCT":[190],"SIFT)":[192],"are":[193,211],"analyzed.":[194],"We":[195],"test":[196],"our":[197],"a":[200,230],"Spanish":[201,241],"corpus":[202],"continuous":[204,231],"speech.":[205],"Our":[206],"results":[207],"indicate":[208],"able":[212],"recognize":[214],"approximately":[215],"58%":[216],"visemes,":[219],"47%":[220],"23%":[225],"words":[228],"scenario":[233],"for":[240],"composed":[243],"20":[245]},"counts_by_year":[],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-10-10T00:00:00"}