{"id":"https://openalex.org/W3207849023","doi":"https://doi.org/10.1145/3474085.3475280","title":"Imitating Arbitrary Talking Style for Realistic Audio-Driven Talking Face Synthesis","display_name":"Imitating Arbitrary Talking Style for Realistic Audio-Driven Talking Face Synthesis","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207849023","doi":"https://doi.org/10.1145/3474085.3475280","mag":"3207849023"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475280","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475280","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haozhe Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Wu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yishun Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishun Dou","raw_affiliation_strings":["HiSilicon Company, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiSilicon Company, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Duan","raw_affiliation_strings":["HiSilicon Company, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiSilicon Company, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Qingshan Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingshan Deng","raw_affiliation_strings":["HiSilicon Company, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HiSilicon Company, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5899,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94353317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1478","last_page":"1486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.824999988079071},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6582000255584717},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.6525999903678894},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.542900025844574}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.824999988079071},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6582000255584717},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.6525999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337000131607056},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.542900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33329999446868896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475280","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2111.00203","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.00203","pdf_url":"https://arxiv.org/pdf/2111.00203","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"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475280","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475280","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475280","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G99649665","display_name":null,"funder_award_id":"No.61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207849023.pdf","grobid_xml":"https://content.openalex.org/works/W3207849023.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2017107803","https://openalex.org/W2107037917","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2237250383","https://openalex.org/W2331128040","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2803705807","https://openalex.org/W2808631503","https://openalex.org/W2884460600","https://openalex.org/W2914217321","https://openalex.org/W2942074357","https://openalex.org/W2944294033","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963800363","https://openalex.org/W2964449965","https://openalex.org/W2981263323","https://openalex.org/W3006410788","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3093450153","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3174763799","https://openalex.org/W3186090335"],"related_works":[],"abstract_inverted_index":{"People":[0],"talk":[1],"with":[2,30,99,210],"diversified":[3],"styles.":[4,190],"For":[5,23],"one":[6],"piece":[7],"of":[8,88,111,143,152],"speech,":[9],"different":[10,53],"talking":[11,61,65,79,86,97,127,131,156,165,207],"styles":[12,98,132,175,208],"exhibit":[13],"significant":[14],"differences":[15,51],"in":[16,160,167],"the":[17,25,31,36,60,78,89,134,139,153,155,168,180,195,199],"facial":[18],"and":[19,42,104,179,205],"head":[20],"pose":[21],"movements.":[22],"example,":[24],"\"excited\"":[26],"style":[27,38,62,76,87,106,135,157,181],"usually":[28],"talks":[29],"mouth":[32],"wide":[33],"open,":[34],"while":[35],"\"solemn\"":[37],"is":[39,56,158],"more":[40,203],"standardized":[41],"seldomly":[43],"exhibits":[44],"exaggerated":[45],"motions.":[46],"Due":[47],"to":[48,58,74,124,187,201],"such":[49],"huge":[50],"between":[52],"styles,":[54],"it":[55],"necessary":[57],"incorporate":[59],"into":[63,77],"audio-driven":[64],"face":[66,80],"synthesis":[67,81],"framework.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,94,118],"propose":[73],"inject":[75],"framework":[82,197],"through":[83],"imitating":[84,130],"arbitrary":[85,174,177],"particular":[90],"reference":[91],"video.":[92],"Specifically,":[93],"systematically":[95],"investigate":[96],"our":[100,144],"collected":[101],"Ted-HD":[102],"dataset":[103],"construct":[105],"codes":[107,182],"as":[108],"several":[109],"statistics":[110],"3D":[112],"morphable":[113],"model":[114,123],"(3DMM)":[115],"parameters.":[116],"Afterwards,":[117],"devise":[119],"a":[120],"latent-style-fusion":[121],"(LSF)":[122],"synthesize":[125,202],"stylized":[126],"faces":[128],"by":[129],"from":[133,164,176],"codes.":[136],"We":[137],"emphasize":[138],"following":[140],"novel":[141],"characteristics":[142],"framework:":[145],"(1)":[146],"It":[147,171],"doesn't":[148],"require":[149],"any":[150],"annotation":[151],"style,":[154],"learned":[159],"an":[161],"unsupervised":[162],"manner":[163],"videos":[166],"wild.":[169],"(2)":[170],"can":[172,183],"imitate":[173],"videos,":[178],"also":[184],"be":[185],"interpolated":[186],"generate":[188],"new":[189],"Extensive":[191],"experiments":[192],"demonstrate":[193],"that":[194],"proposed":[196],"has":[198],"ability":[200],"natural":[204],"expressive":[206],"compared":[209],"baseline":[211],"methods.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2021-10-25T00:00:00"}