{"id":"https://openalex.org/W2950448185","doi":"https://doi.org/10.1007/s11263-019-01251-8","title":"Realistic Speech-Driven Facial Animation with GANs","display_name":"Realistic Speech-Driven Facial Animation with GANs","publication_year":2019,"publication_date":"2019-10-13","ids":{"openalex":"https://openalex.org/W2950448185","doi":"https://doi.org/10.1007/s11263-019-01251-8","mag":"2950448185"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-019-01251-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-019-01251-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-019-01251-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-019-01251-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079503255","display_name":"Konstantinos Vougioukas","orcid":"https://orcid.org/0000-0001-8552-5559"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Konstantinos Vougioukas","raw_affiliation_strings":["Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","Department of Computing, Imperial College London, London, UK ("],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK (","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","Samsung AI Research Centre Cambridge, 50 Station Road, Cambridge, CBI 2RE, UK","Department of Computing, Imperial College London, London, UK","Samsung AI Research Centre Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Samsung AI Research Centre Cambridge, 50 Station Road, Cambridge, CBI 2RE, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Samsung AI Research Centre Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","Samsung AI Research Centre Cambridge, 50 Station Road, Cambridge, CBI 2RE, UK","Samsung AI Research Centre Cambridge, Cambridge, UK","Department of Computing, Imperial College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, 180 Queen\u2019s Gate, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Samsung AI Research Centre Cambridge, 50 Station Road, Cambridge, CBI 2RE, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Samsung AI Research Centre Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079503255"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.3281,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.84493277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"128","issue":"5","first_page":"1398","last_page":"1413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.994700014591217,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9829999804496765,"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/computer-science","display_name":"Computer science","score":0.8641153573989868},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6721903085708618},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.6099355816841125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5922693610191345},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5615672469139099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49419358372688293},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.4926629662513733},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43887609243392944},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43390604853630066},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4300459027290344},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.2557302713394165},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.18262231349945068},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.17205148935317993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8641153573989868},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6721903085708618},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.6099355816841125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5922693610191345},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5615672469139099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49419358372688293},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4926629662513733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43887609243392944},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43390604853630066},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4300459027290344},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.2557302713394165},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.18262231349945068},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.17205148935317993},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s11263-019-01251-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-019-01251-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-019-01251-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.06337","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06337","pdf_url":"https://arxiv.org/pdf/1906.06337","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":"","raw_type":"text"},{"id":"mag:2950448185","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1906.06337","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":"pmh:oai:spiral.imperial.ac.uk:10044/1/74522","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/74522","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1413","raw_type":"Journal Article"},{"id":"doi:10.48550/arxiv.1906.06337","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.06337","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":"doi:10.1007/s11263-019-01251-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-019-01251-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-019-01251-8.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1591978968","display_name":null,"funder_award_id":"2130174","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5321982477","display_name":null,"funder_award_id":"Titan V GPU","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950448185.pdf","grobid_xml":"https://content.openalex.org/works/W2950448185.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1569907127","https://openalex.org/W1710476689","https://openalex.org/W1901129140","https://openalex.org/W1982517393","https://openalex.org/W2004789217","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2030931454","https://openalex.org/W2047618352","https://openalex.org/W2054721804","https://openalex.org/W2064400654","https://openalex.org/W2127211243","https://openalex.org/W2147885303","https://openalex.org/W2162220380","https://openalex.org/W2173520492","https://openalex.org/W2265959009","https://openalex.org/W2513140567","https://openalex.org/W2520707650","https://openalex.org/W2529337537","https://openalex.org/W2578229578","https://openalex.org/W2581485081","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2613087992","https://openalex.org/W2737548191","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2764019261","https://openalex.org/W2791895881","https://openalex.org/W2794494400","https://openalex.org/W2804600264","https://openalex.org/W2804619907","https://openalex.org/W2806757392","https://openalex.org/W2883861033","https://openalex.org/W2914447220","https://openalex.org/W2944294033","https://openalex.org/W2950248412","https://openalex.org/W2963066677","https://openalex.org/W2963081548","https://openalex.org/W2963092440","https://openalex.org/W2963125871","https://openalex.org/W2963290645","https://openalex.org/W2964201867","https://openalex.org/W2964245526","https://openalex.org/W6637568146","https://openalex.org/W6693078191","https://openalex.org/W6726983635","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6866486011"],"related_works":["https://openalex.org/W2979894294","https://openalex.org/W2964095416","https://openalex.org/W2738406145","https://openalex.org/W3029279979","https://openalex.org/W3204131973","https://openalex.org/W3154411171","https://openalex.org/W3172598908","https://openalex.org/W2063634999","https://openalex.org/W3176721746","https://openalex.org/W3089177030","https://openalex.org/W2361146042","https://openalex.org/W2468212864","https://openalex.org/W2293491238","https://openalex.org/W2946471225","https://openalex.org/W2138778418","https://openalex.org/W2128673549","https://openalex.org/W2202084177","https://openalex.org/W1502557347","https://openalex.org/W2310226489","https://openalex.org/W2891063225"],"abstract_inverted_index":{"Abstract":[0],"Speech-driven":[1],"facial":[2,99],"animation":[3],"is":[4],"the":[5,94,125,142,146],"process":[6],"that":[7,53,89],"automatically":[8],"synthesizes":[9],"talking":[10,58],"characters":[11],"based":[12,153],"on":[13,76,114,154],"speech":[14],"signals.":[15],"The":[16,148],"majority":[17],"of":[18,56,65,127,145],"work":[19],"in":[20,91,130],"this":[21],"domain":[22],"creates":[23],"a":[24,57,62,66],"mapping":[25],"from":[26],"audio":[27,70,95],"features":[28],"to":[29,41,166],"visual":[30],"features.":[31,79],"This":[32],"approach":[33],"often":[34],"requires":[35],"post-processing":[36],"using":[37,60,133],"computer":[38],"graphics":[39],"techniques":[40],"produce":[42],"realistic":[43,121],"albeit":[44],"subject":[45],"dependent":[46],"results.":[47],"We":[48,123],"present":[49],"an":[50,69,134],"end-to-end":[51],"system":[52],"generates":[54,82],"videos":[55,83,150],"head,":[59],"only":[61],"still":[63],"image":[64],"person":[67],"and":[68,96,104,120,137],"clip":[71],"containing":[72],"speech,":[73],"without":[74],"relying":[75],"handcrafted":[77],"intermediate":[78],"Our":[80,107],"method":[81],"which":[84],"have":[85],"(a)":[86],"lip":[87],"movements":[88],"are":[90,151],"sync":[92],"with":[93],"(b)":[97],"natural":[98,168],"expressions":[100],"such":[101],"as":[102,161,163],"blinks":[103],"eyebrow":[105],"movements.":[106],"temporal":[108],"GAN":[109],"uses":[110],"3":[111],"discriminators":[112],"focused":[113],"achieving":[115],"detailed":[116],"frames,":[117],"audio-visual":[118],"synchronization,":[119],"expressions.":[122],"quantify":[124],"contribution":[126],"each":[128],"component":[129],"our":[131],"model":[132],"ablation":[135],"study":[136],"we":[138],"provide":[139],"insights":[140],"into":[141],"latent":[143],"representation":[144],"model.":[147],"generated":[149],"evaluated":[152],"sharpness,":[155],"reconstruction":[156],"quality,":[157],"lip-reading":[158],"accuracy,":[159],"synchronization":[160],"well":[162],"their":[164],"ability":[165],"generate":[167],"blinks.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}