{"id":"https://openalex.org/W3029279979","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206665","title":"Identity-Preserving Realistic Talking Face Generation","display_name":"Identity-Preserving Realistic Talking Face Generation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3029279979","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206665","mag":"3029279979"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/2005.12318","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065928641","display_name":"Sanjana Sinha","orcid":"https://orcid.org/0000-0001-6198-1496"},"institutions":[{"id":"https://openalex.org/I4210145666","display_name":"Embedded Systems (United States)","ror":"https://ror.org/04742eh45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjana Sinha","raw_affiliation_strings":["Embedded Systems and Robotics, TCS Research and Innovation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embedded Systems and Robotics, TCS Research and Innovation","institution_ids":["https://openalex.org/I4210145666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056626512","display_name":"Sandika Biswas","orcid":"https://orcid.org/0000-0002-8264-3346"},"institutions":[{"id":"https://openalex.org/I4210145666","display_name":"Embedded Systems (United States)","ror":"https://ror.org/04742eh45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandika Biswas","raw_affiliation_strings":["Embedded Systems and Robotics, TCS Research and Innovation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embedded Systems and Robotics, TCS Research and Innovation","institution_ids":["https://openalex.org/I4210145666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080835883","display_name":"Brojeshwar Bhowmick","orcid":"https://orcid.org/0000-0001-9291-5889"},"institutions":[{"id":"https://openalex.org/I4210145666","display_name":"Embedded Systems (United States)","ror":"https://ror.org/04742eh45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145666"]},{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Brojeshwar Bhowmick","raw_affiliation_strings":["Embedded Systems and Robotics, TCS Research and Innovation","Tata consultancy services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Embedded Systems and Robotics, TCS Research and Innovation","institution_ids":["https://openalex.org/I4210145666"]},{"raw_affiliation_string":"Tata consultancy services","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0966,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37498523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.993399977684021,"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":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532494068145752},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6999484896659851},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6748635768890381},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6404239535331726},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5982667803764343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5435743927955627},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4882974624633789},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4457997679710388},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.438364177942276},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.43189725279808044},{"id":"https://openalex.org/keywords/realism","display_name":"Realism","score":0.4126184582710266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34795308113098145},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3367311954498291},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16660496592521667},{"id":"https://openalex.org/keywords/aesthetics","display_name":"Aesthetics","score":0.15854689478874207},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11355778574943542},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10535940527915955},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.0687805712223053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532494068145752},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6999484896659851},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6748635768890381},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6404239535331726},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5982667803764343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5435743927955627},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4882974624633789},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4457997679710388},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.438364177942276},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.43189725279808044},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.4126184582710266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34795308113098145},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3367311954498291},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16660496592521667},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.15854689478874207},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11355778574943542},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10535940527915955},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0687805712223053},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206665","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206665","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.12318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12318","pdf_url":"https://arxiv.org/pdf/2005.12318","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:3029279979","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2005.12318","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.2005.12318","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.12318","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.12318","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.12318","pdf_url":"https://arxiv.org/pdf/2005.12318","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.46000000834465027,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3029279979.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1487641199","https://openalex.org/W1569907127","https://openalex.org/W1922655562","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2054721804","https://openalex.org/W2064400654","https://openalex.org/W2084235337","https://openalex.org/W2087681821","https://openalex.org/W2099471712","https://openalex.org/W2125865219","https://openalex.org/W2146932984","https://openalex.org/W2146991130","https://openalex.org/W2162220380","https://openalex.org/W2593414223","https://openalex.org/W2613087992","https://openalex.org/W2738406145","https://openalex.org/W2796931171","https://openalex.org/W2806757392","https://openalex.org/W2807126412","https://openalex.org/W2883861033","https://openalex.org/W2886934227","https://openalex.org/W2904622387","https://openalex.org/W2944294033","https://openalex.org/W2951270715","https://openalex.org/W2959650063","https://openalex.org/W2963066677","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964559396","https://openalex.org/W2979894294","https://openalex.org/W3025498998","https://openalex.org/W6629354409","https://openalex.org/W6640090968","https://openalex.org/W6678814708","https://openalex.org/W6729966448","https://openalex.org/W6737896281","https://openalex.org/W6749904982","https://openalex.org/W6751846511","https://openalex.org/W6754123467","https://openalex.org/W6756702432","https://openalex.org/W6765657114"],"related_works":["https://openalex.org/W3089455867","https://openalex.org/W2979894294","https://openalex.org/W3154411171","https://openalex.org/W3089177030","https://openalex.org/W2032587929","https://openalex.org/W3195529437","https://openalex.org/W2468212864","https://openalex.org/W1569740590","https://openalex.org/W1532237134","https://openalex.org/W3083394627","https://openalex.org/W2093386409","https://openalex.org/W2895226286","https://openalex.org/W2964095416","https://openalex.org/W1549200780","https://openalex.org/W94140459","https://openalex.org/W2556634673","https://openalex.org/W2032993994","https://openalex.org/W2739192055","https://openalex.org/W2310226489","https://openalex.org/W3120602499"],"abstract_inverted_index":{"Speech-driven":[0],"facial":[1,79,87,109,126,147,151,220],"animation":[2,23,80,200,221],"is":[3,213],"useful":[4],"for":[5,65,76,94],"a":[6,20,74,176,230],"variety":[7],"of":[8,18,31,41,61,132,136,166,181,198,209,229],"applications":[9],"such":[10],"as":[11],"telepresence,":[12],"chatbots,":[13],"etc.":[14,100],"The":[15,45],"necessary":[16],"attributes":[17,228],"having":[19],"realistic":[21,78,231],"face":[22,234],"are":[24],"1)":[25],"audiovisual":[26,51],"synchronization":[27,183],"(2)":[28],"identity":[29],"preservation":[30],"the":[32,50,116,124,137,146,171,203,207,214,226],"target":[33,138],"individual":[34],"(3)":[35],"plausible":[36,133],"mouth":[37,134],"movements":[38],"(4)":[39],"presence":[40],"natural":[42,62],"eye":[43,63,106],"blinks.":[44],"existing":[46],"methods":[47,174],"mostly":[48],"address":[49],"lip":[52,182],"synchronization,":[53],"and":[54,114,189],"few":[55],"recent":[56],"works":[57],"have":[58],"addressed":[59],"synthesis":[60],"blinks":[64,107],"overall":[66],"video":[67],"realism.":[68],"In":[69],"this":[70,212],"paper,":[71],"we":[72,104,141],"propose":[73],"method":[75,169],"identity-preserving":[77],"from":[81,89,149],"speech.":[82],"We":[83],"first":[84,215],"generate":[85,145],"person-independent":[86,117],"landmarks":[88,110,118,121],"audio":[90],"using":[91,111,153],"DeepSpeech":[92],"features":[93],"invariance":[95],"to":[96,119,122,144,159],"different":[97],"voices,":[98],"accents,":[99],"To":[101,206],"add":[102],"realism,":[103],"impose":[105],"on":[108],"unsupervised":[112],"learning":[113],"retarget":[115],"person-specific":[120,150],"preserve":[123,160],"identity-related":[125,161],"structure":[127],"which":[128],"helps":[129,158],"in":[130,179,217],"generation":[131],"shapes":[135],"identity.":[139],"Finally,":[140],"use":[142],"LSGAN":[143],"texture":[148],"landmarks,":[152],"an":[154],"attention":[155],"mechanism":[156],"that":[157,222],"texture.":[162],"An":[163],"extensive":[164],"comparison":[165],"our":[167,199,210],"proposed":[168],"with":[170],"current":[172],"state-of-the-art":[173,204],"demonstrate":[175],"significant":[177],"improvement":[178],"terms":[180],"accuracy,":[184],"image":[185],"reconstruction":[186],"quality,":[187],"sharpness,":[188],"identity-preservation.":[190],"A":[191],"user":[192],"study":[193],"also":[194],"reveals":[195],"improved":[196],"realism":[197],"results":[201],"over":[202],"methods.":[205],"best":[208],"knowledge,":[211],"work":[216],"speech-driven":[218],"2D":[219],"simultaneously":[223],"addresses":[224],"all":[225],"above-mentioned":[227],"speech":[232],"driven":[233],"animation.":[235]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}
