{"id":"https://openalex.org/W2807420428","doi":"https://doi.org/10.1109/fg.2018.00066","title":"Expressive Speech-Driven Lip Movements with Multitask Learning","display_name":"Expressive Speech-Driven Lip Movements with Multitask Learning","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2807420428","doi":"https://doi.org/10.1109/fg.2018.00066","mag":"2807420428"},"language":"en","primary_location":{"id":"doi:10.1109/fg.2018.00066","doi":"https://doi.org/10.1109/fg.2018.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2018.00066","pdf_url":null,"source":{"id":"https://openalex.org/S4306419159","display_name":"International Conference on Automatic Face and Gesture Recognition","issn_l":"1541-5058","issn":["1541-5058","2326-5396"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 13th IEEE International Conference on Automatic Face &amp; Gesture Recognition (FG 2018)","raw_type":"proceedings-article"},"volume":null,"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/A5001956187","display_name":"Najmeh Sadoughi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najmeh Sadoughi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072","observed_orcids":["https://orcid.org/0000-0002-4075-4072"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.6274,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90676401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.4440999925136566,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.4440999925136566,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.39750000834465027,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06949999928474426,"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/multi-task-learning","display_name":"multi-task learning","score":0.8560000061988831},{"id":"https://openalex.org/keywords/speech-articulation","display_name":"speech articulation","score":0.8669999837875366},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.8320000171661377},{"id":"https://openalex.org/keywords/chatbots","display_name":"chatbots","score":0.9319999814033508},{"id":"https://openalex.org/keywords/facial-expression-synthesis","display_name":"facial expression synthesis","score":0.6639999747276306},{"id":"https://openalex.org/keywords/shared-representations","display_name":"shared representations","score":0.8980000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121498584747314},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6447938680648804},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.6072171926498413},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.47444379329681396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4739668071269989},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.4706377685070038},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.46377983689308167},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4498054087162018},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43041878938674927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34678757190704346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3369271755218506},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3322480022907257},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1813475787639618},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg.2018.00066","doi":"https://doi.org/10.1109/fg.2018.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2018.00066","pdf_url":null,"source":{"id":"https://openalex.org/S4306419159","display_name":"International Conference on Automatic Face and Gesture Recognition","issn_l":"1541-5058","issn":["1541-5058","2326-5396"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 13th IEEE International Conference on Automatic Face &amp; Gesture Recognition (FG 2018)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1554803342","https://openalex.org/W1569907127","https://openalex.org/W1586674080","https://openalex.org/W1974597084","https://openalex.org/W1984333007","https://openalex.org/W1990883837","https://openalex.org/W2004789217","https://openalex.org/W2014621385","https://openalex.org/W2018506469","https://openalex.org/W2064400654","https://openalex.org/W2064675550","https://openalex.org/W2072125514","https://openalex.org/W2083731490","https://openalex.org/W2097998348","https://openalex.org/W2117752179","https://openalex.org/W2128173845","https://openalex.org/W2129360799","https://openalex.org/W2146334809","https://openalex.org/W2151458022","https://openalex.org/W2239141610","https://openalex.org/W2399733683","https://openalex.org/W2514026573","https://openalex.org/W2515372520","https://openalex.org/W2745980686","https://openalex.org/W4252434905"],"related_works":["https://openalex.org/W2745980686","https://openalex.org/W2064400654","https://openalex.org/W7100122912","https://openalex.org/W7095963732","https://openalex.org/W4390872334","https://openalex.org/W2806723288","https://openalex.org/W2889214350","https://openalex.org/W2017208747","https://openalex.org/W4281698221","https://openalex.org/W4386211337"],"abstract_inverted_index":{"The":[0,73,105],"orofacial":[1,91,121],"area":[2],"conveys":[3],"a":[4],"range":[5],"of":[6],"information,":[7],"including":[8],"speech":[9,68],"articulation":[10,69],"and":[11,25,31,70,99],"emotions.":[12],"These":[13],"two":[14,61],"factors":[15,42],"add":[16],"constraints":[17],"to":[18,66,118],"the":[19,38,119,130],"facial":[20],"movements,":[21,122],"creating":[22],"non-trivial":[23],"integrations":[24],"interplays.":[26],"To":[27],"generate":[28,111],"more":[29,50,127],"expressive":[30],"naturalistic":[32],"movements":[33],"for":[34,52],"conversational":[35],"agents":[36],"(CAs)":[37],"relationship":[39],"between":[40],"these":[41],"should":[43],"be":[44],"carefully":[45],"modeled.":[46],"Data-driven":[47],"models":[48],"are":[49,86,116,125],"appropriate":[51],"this":[53],"task":[54,134],"than":[55,129],"rule-based":[56],"systems.":[57],"This":[58],"paper":[59],"provides":[60],"deep":[62],"learning":[63,79],"speech-driven":[64],"structures":[65],"integrate":[67],"emotional":[71],"cues.":[72],"proposed":[74],"approaches":[75],"rely":[76],"on":[77],"multitask":[78],"(MTL)":[80],"strategies,":[81],"where":[82],"related":[83],"secondary":[84,103],"tasks":[85],"jointly":[87],"solved":[88],"when":[89],"synthesizing":[90],"movements.":[92],"In":[93],"particular,":[94],"we":[95],"evaluate":[96],"emotion":[97],"recognition":[98,101],"viseme":[100],"as":[102],"tasks.":[104],"approach":[106],"creates":[107],"shared":[108],"representations":[109],"that":[110,113],"behaviors":[112],"not":[114],"only":[115],"closer":[117],"original":[120],"but":[123],"also":[124],"perceived":[126],"natural":[128],"results":[131],"from":[132],"single":[133],"learning.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-06-13T00:00:00"}
