{"id":"https://openalex.org/W4200633626","doi":"https://doi.org/10.1145/3522615","title":"Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation","display_name":"Joint Audio-Text Model for Expressive Speech-Driven 3D Facial Animation","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4200633626","doi":"https://doi.org/10.1145/3522615"},"language":"en","primary_location":{"id":"doi:10.1145/3522615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3522615","pdf_url":null,"source":{"id":"https://openalex.org/S4210220973","display_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","issn_l":"2577-6193","issn":["2577-6193"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","raw_type":"journal-article"},"type":"article","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/A5072087245","display_name":"Yingruo Fan","orcid":"https://orcid.org/0000-0001-8977-4958"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yingruo Fan","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021691940","display_name":"Zhaojiang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhaojiang Lin","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong and HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong and HKUST","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188933","display_name":"Jun Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Saito","raw_affiliation_strings":["Adobe Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668416","display_name":"Wenping Wang","orcid":"https://orcid.org/0000-0002-2284-3952"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenping Wang","raw_affiliation_strings":["Texas A&amp;M University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&amp;M University, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014324841","display_name":"Taku Komura","orcid":"https://orcid.org/0000-0002-2729-5860"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Taku Komura","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072087245"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":2.3773,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88285357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"5","issue":"1","first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973000288009644,"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/T11448","display_name":"Face recognition and analysis","score":0.9951000213623047,"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":0.8160468935966492},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6033065915107727},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5920975804328918},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5849106311798096},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5711007118225098},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4857824146747589},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.47273388504981995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3906433582305908},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35558390617370605},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.24267452955245972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160468935966492},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6033065915107727},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5920975804328918},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5849106311798096},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5711007118225098},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4857824146747589},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.47273388504981995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3906433582305908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35558390617370605},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.24267452955245972},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3522615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3522615","pdf_url":null,"source":{"id":"https://openalex.org/S4210220973","display_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","issn_l":"2577-6193","issn":["2577-6193"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-118302","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85130258970&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6772501718","display_name":null,"funder_award_id":"JPNP21004","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1485743559","https://openalex.org/W1990883837","https://openalex.org/W2064400654","https://openalex.org/W2071096833","https://openalex.org/W2154961933","https://openalex.org/W2191779130","https://openalex.org/W2395639500","https://openalex.org/W2468212864","https://openalex.org/W2583643061","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2804619907","https://openalex.org/W2884460600","https://openalex.org/W2914165399","https://openalex.org/W2944294033","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2979894294","https://openalex.org/W2981263323","https://openalex.org/W2995034616","https://openalex.org/W3002310794","https://openalex.org/W3025521275","https://openalex.org/W3081492798","https://openalex.org/W3083173864","https://openalex.org/W3089177030","https://openalex.org/W3093450153","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3125775899","https://openalex.org/W3174763799","https://openalex.org/W3186090335"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2532377291","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2617644139","https://openalex.org/W2535923857","https://openalex.org/W4400097232","https://openalex.org/W1976926596","https://openalex.org/W4310844315","https://openalex.org/W3020604125"],"abstract_inverted_index":{"Speech-driven":[0],"3D":[1,43,147],"facial":[2,44,148,162],"animation":[3],"with":[4,123],"accurate":[5],"lip":[6],"synchronization":[7],"has":[8,22,94],"been":[9,24],"widely":[10],"studied.":[11],"However,":[12],"synthesizing":[13],"realistic":[14,161],"motions":[15],"for":[16,40,145],"the":[17,37,64,67,82,88,107,112,124,136,140,153,170,178,185],"entire":[18],"face":[19,116],"during":[20],"speech":[21],"rarely":[23],"explored.":[25],"In":[26,126],"this":[27],"work,":[28],"we":[29,78,138],"present":[30],"a":[31],"joint":[32],"audio-text":[33],"model":[34,69,92,190],"to":[35,51,70,80,128],"capture":[36],"contextual":[38,83,97,142],"information":[39],"expressive":[41],"speech-driven":[42,146],"animation.":[45,149],"The":[46,182],"existing":[47,192],"datasets":[48],"are":[49,119],"collected":[50],"cover":[52],"as":[53,57,175,177],"many":[54],"different":[55],"phonemes":[56],"possible":[58],"instead":[59],"of":[60,66,188],"sentences,":[61],"thus":[62],"limiting":[63],"capability":[65],"audio-based":[68],"learn":[71,132],"more":[72],"diverse":[73],"contexts.":[74],"To":[75],"address":[76],"this,":[77],"propose":[79],"leverage":[81],"text":[84,101,108,143],"embeddings":[85],"extracted":[86],"from":[87,99,135],"powerful":[89],"pre-trained":[90],"language":[91],"that":[93,106,152],"learned":[95],"rich":[96],"representations":[98],"large-scale":[100],"data.":[102],"Our":[103],"hypothesis":[104],"is":[105],"features":[109,134,144],"can":[110,159],"disambiguate":[111],"variations":[113],"in":[114],"upper":[115],"expressions,":[117],"which":[118,131],"not":[120],"strongly":[121],"correlated":[122],"audio.":[125],"contrast":[127],"prior":[129],"approaches":[130],"phoneme-level":[133],"text,":[137],"investigate":[139],"high-level":[141],"We":[150,168],"show":[151],"combined":[154],"acoustic":[155],"and":[156,172],"textual":[157],"modalities":[158],"synthesize":[160],"expressions":[163],"while":[164],"maintaining":[165],"audio-lip":[166],"synchronization.":[167],"conduct":[169],"quantitative":[171],"qualitative":[173],"evaluations":[174],"well":[176],"perceptual":[179],"user":[180],"study.":[181],"results":[183],"demonstrate":[184],"superior":[186],"performance":[187],"our":[189],"against":[191],"state-of-the-art":[193],"approaches.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
