{"id":"https://openalex.org/W2132383236","doi":"https://doi.org/10.1109/icsmc.2003.1244206","title":"3D realistic talking face co-driven by text and speech","display_name":"3D realistic talking face co-driven by text and speech","publication_year":2004,"publication_date":"2004-05-13","ids":{"openalex":"https://openalex.org/W2132383236","doi":"https://doi.org/10.1109/icsmc.2003.1244206","mag":"2132383236"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2003.1244206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1244206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","raw_type":"proceedings-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/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingli Song","raw_affiliation_strings":["College of Computer Science, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103956520","display_name":"Chun Chen","orcid":"https://orcid.org/0009-0005-8416-9587"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Chen","raw_affiliation_strings":["College of Computer Science, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052757755","display_name":"Jiajun Bu","orcid":"https://orcid.org/0000-0002-1097-2044"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["College of Computer Science, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001531117","display_name":"Ronghua Liang","orcid":"https://orcid.org/0000-0003-2077-9608"},"institutions":[{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]},{"id":"https://openalex.org/I4210144142","display_name":"Hangzhou Institute of Applied Acoustics","ror":"https://ror.org/0473ary24","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghua Liang","raw_affiliation_strings":["Hangzhou Institute of Electronics Engineering, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hangzhou Institute of Electronics Engineering, Hangzhou, China","institution_ids":["https://openalex.org/I4210144142","https://openalex.org/I4210110458"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026532752"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.2733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61766996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"2175","last_page":"2186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12290","display_name":"Human Motion and Animation","score":0.9975000023841858,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.9673596024513245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7551919221878052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.69898921251297},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5753466486930847},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5441111922264099},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.48379701375961304},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.482652485370636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43564313650131226},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3559004068374634},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15067672729492188},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.14818206429481506},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1015852689743042}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9673596024513245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551919221878052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.69898921251297},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5753466486930847},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5441111922264099},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.48379701375961304},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.482652485370636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43564313650131226},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3559004068374634},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15067672729492188},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.14818206429481506},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1015852689743042},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2003.1244206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2003.1244206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1523299280","https://openalex.org/W1554803342","https://openalex.org/W1608915237","https://openalex.org/W1950150365","https://openalex.org/W1986394836","https://openalex.org/W2055562771","https://openalex.org/W2096076356","https://openalex.org/W2097127206","https://openalex.org/W2106286519","https://openalex.org/W2122541134","https://openalex.org/W2124254345","https://openalex.org/W2132172443","https://openalex.org/W2141939292","https://openalex.org/W2170854033","https://openalex.org/W2235920218","https://openalex.org/W3004513510","https://openalex.org/W4244298416","https://openalex.org/W4298244900","https://openalex.org/W6631180104","https://openalex.org/W6636383877"],"related_works":["https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W2741151796","https://openalex.org/W2306241824","https://openalex.org/W1974357398","https://openalex.org/W2963024054","https://openalex.org/W2373874394","https://openalex.org/W4212815228","https://openalex.org/W1852407300","https://openalex.org/W2777626350"],"abstract_inverted_index":{"To":[0],"create":[1],"3D":[2,46],"realistic":[3,31,135],"talking":[4,21],"face":[5,22],"has":[6],"been":[7],"a":[8,11,54],"challenge":[9],"for":[10,88],"long":[12],"time.":[13],"Previous":[14],"works":[15],"emphasize":[16],"text":[17,38,50,73,142],"or":[18,32,143],"speech":[19,40,69],"driven":[20],"respectively":[23],"while":[24],"the":[25,35,45,63,68,72,94,98,113,128,141],"animation":[26,129],"result":[27,130],"is":[28,51,65,76,86],"not":[29],"very":[30],"natural-looking.":[33],"In":[34],"proposed":[36],"approach,":[37],"and":[39,97,134],"are":[41,104,121],"considered":[42],"to":[43,71,112,116,126],"drive":[44],"talkingface":[47],"coordinately.":[48],"The":[49],"translated":[52],"into":[53,78],"sequence":[55,64],"of":[56,62],"visemes'":[57],"transcription.":[58],"And":[59,91],"time":[60,95],"vector":[61,85,96],"extracted":[66],"from":[67],"corresponding":[70],"after":[74],"it":[75],"segmented":[77],"phonetic":[79],"sequence.":[80],"A":[81],"muscle":[82],"based":[83,139],"viseme":[84],"defined":[87],"static":[89,99],"viseme.":[90],"then,":[92],"with":[93],"visemes's":[100],"sequence,":[101],"dynamic":[102],"visemes":[103],"generated":[105],"through":[106],"time-related":[107],"dominance":[108],"function.":[109],"Finally,":[110],"according":[111],"frame":[114],"rate":[115],"be":[117],"rendered,":[118],"intermediate":[119],"frames":[120,125],"interpolated":[122],"between":[123],"key":[124],"make":[127],"looks":[131],"more":[132],"natural":[133],"than":[136],"those":[137],"obtained":[138],"on":[140],"speech-driven":[144],"only.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
