{"id":"https://openalex.org/W4398249576","doi":"https://doi.org/10.1007/s40747-024-01481-5","title":"3D facial animation driven by speech-video dual-modal signals","display_name":"3D facial animation driven by speech-video dual-modal signals","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398249576","doi":"https://doi.org/10.1007/s40747-024-01481-5"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01481-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01481-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01481-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01481-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032358287","display_name":"Xuejie Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuejie Ji","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078065807","display_name":"Zhouzhou Liao","orcid":"https://orcid.org/0009-0001-1454-862X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouzhou Liao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764247","display_name":"Lanfang Dong","orcid":"https://orcid.org/0000-0002-0267-9905"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanfang Dong","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China"],"raw_orcid":"https://orcid.org/0000-0002-0267-9905","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025070851","display_name":"Yingchao Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchao Tang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, 230026, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752569","display_name":"Guoming Li","orcid":"https://orcid.org/0000-0001-7624-8051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoming Li","raw_affiliation_strings":["AI Lab, China Merchants Bank, Shenzhen, 518040, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, China Merchants Bank, Shenzhen, 518040, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101731025","display_name":"Meng Mao","orcid":"https://orcid.org/0000-0002-7875-3809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Mao","raw_affiliation_strings":["AI Lab, China Merchants Bank, Shenzhen, 518040, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, China Merchants Bank, Shenzhen, 518040, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032358287"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.7142,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6939209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"10","issue":"5","first_page":"5951","last_page":"5964"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9939000010490417,"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/T12290","display_name":"Human Motion and Animation","score":0.9818999767303467,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6132989525794983},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.607391893863678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6038729548454285},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5949758291244507},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5573350191116333},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.47195544838905334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44349661469459534},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3283866047859192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32430416345596313},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3013582229614258},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2399328649044037},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.18443116545677185},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10454106330871582},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07405519485473633},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05977010726928711}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6132989525794983},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.607391893863678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6038729548454285},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5949758291244507},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5573350191116333},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.47195544838905334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44349661469459534},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3283866047859192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32430416345596313},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3013582229614258},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2399328649044037},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.18443116545677185},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10454106330871582},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07405519485473633},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05977010726928711},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01481-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01481-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01481-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:697ff751d67b464ea02983c2b6bb86ba","is_oa":true,"landing_page_url":"https://doaj.org/article/697ff751d67b464ea02983c2b6bb86ba","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 5, Pp 5951-5964 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01481-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01481-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01481-5.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398249576.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1635512741","https://openalex.org/W2004789217","https://openalex.org/W2029199293","https://openalex.org/W2035953391","https://openalex.org/W2038891881","https://openalex.org/W2070726616","https://openalex.org/W2114336453","https://openalex.org/W2128173845","https://openalex.org/W2295661697","https://openalex.org/W2623464795","https://openalex.org/W2737658251","https://openalex.org/W2739192055","https://openalex.org/W2804619907","https://openalex.org/W2891063225","https://openalex.org/W2949662773","https://openalex.org/W2968193852","https://openalex.org/W2970152259","https://openalex.org/W2981263323","https://openalex.org/W3094612121","https://openalex.org/W3099284785","https://openalex.org/W3104792420","https://openalex.org/W3120163087","https://openalex.org/W3131407164","https://openalex.org/W3154411171","https://openalex.org/W3180794345","https://openalex.org/W3194006130","https://openalex.org/W4200630629","https://openalex.org/W4292411680","https://openalex.org/W4297841641","https://openalex.org/W4307286264","https://openalex.org/W4308233968","https://openalex.org/W4312421757","https://openalex.org/W4312590328","https://openalex.org/W4385801342","https://openalex.org/W4392908489","https://openalex.org/W6600655691","https://openalex.org/W6601026004"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2796042130","https://openalex.org/W2142490914","https://openalex.org/W2741151796","https://openalex.org/W2306241824","https://openalex.org/W2963024054","https://openalex.org/W2108033344","https://openalex.org/W2161997376","https://openalex.org/W2099257899","https://openalex.org/W1524860023"],"abstract_inverted_index":{"Abstract":[0],"In":[1,61,276,308],"recent":[2],"years,":[3],"the":[4,15,21,47,63,69,103,135,175,220,225,236,247,255,272,298,327,330],"applications":[5],"of":[6,14,23,288,306,310,319,329],"digital":[7],"humans":[8],"have":[9],"become":[10],"increasingly":[11],"widespread.":[12],"One":[13],"most":[16],"challenging":[17],"core":[18],"technologies":[19],"is":[20,98,160,171,185,295],"generation":[22,117],"highly":[24],"realistic":[25],"and":[26,35,52,122,129,149,166,182,195,202,214,242,250,269,286,302,317],"automated":[27],"3D":[28,39,82,131],"facial":[29,33,40,54,79,83,109,132,178],"animation":[30,41,170,222],"that":[31,119,254,283,291],"combines":[32],"movements":[34,55,137],"speech.":[36],"The":[37,157,180],"single-modal":[38],"driven":[42],"by":[43,95,143,154],"speech":[44,51,121,140,164,201],"typically":[45],"ignores":[46],"weak":[48],"correlation":[49],"between":[50],"upper":[53],"as":[56,58,100,102,174,265],"well":[57],"head":[59,196],"posture.":[60],"contrast,":[62],"video-driven":[64,96],"approach":[65],"can":[66],"perfectly":[67],"solve":[68],"posture":[70,197,208],"problem":[71],"while":[72,146],"obtaining":[73],"natural":[74,128],"expressions.":[75],"However,":[76],"mapping":[77],"2D":[78],"information":[80,84,88,124],"to":[81,87,125,139,162,187,205,211,218,234,239],"may":[85],"lead":[86],"loss,":[89],"which":[90],"make":[91],"lip":[92,136,169,212,221,311],"synchronization":[93],"generated":[94,142,152,223],"methods":[97,105,325],"not":[99],"good":[101],"speech-driven":[104,158,226],"trained":[106],"on":[107,246,261],"4D":[108],"data.":[110],"Therefore,":[111],"this":[112,292],"paper":[113,229],"proposes":[114],"a":[115,278],"dual-modal":[116],"method":[118,257,294],"uses":[120],"video":[123,155,203],"generate":[126,240],"more":[127],"vivid":[130],"animation.":[133,179],"Specifically,":[134],"related":[138,210],"are":[141,151],"speech-video":[144],"information,":[145],"speech-uncorrelated":[147],"postures":[148],"expressions":[150,241],"solely":[153],"information.":[156],"module":[159,184],"used":[161,173,186],"extract":[163,188],"features,":[165],"its":[167],"output":[168],"then":[172],"foundation":[176],"for":[177,192],"expression":[181,194],"pose":[183],"temporal":[189],"visual":[190],"features":[191,204],"regressing":[193],"parameters.":[198],"We":[199],"fuse":[200],"obtain":[206],"chin":[207],"parameters":[209,217],"movements,":[213],"use":[215],"these":[216],"fine-tune":[219],"form":[224],"module.":[227],"This":[228],"introduces":[230],"multiple":[231],"consistency":[232],"losses":[233],"enhance":[235],"network\u2019s":[237],"capability":[238],"postures.":[243],"Experiments":[244],"conducted":[245],"LRS3,":[248],"TCD-TIMIT":[249],"MEAD":[251],"datasets":[252],"show":[253,282],"proposed":[256,331],"achieves":[258],"better":[259,296],"performance":[260],"evaluation":[262,324],"metrics":[263],"such":[264],"CER,":[266],"WER,":[267],"VER":[268],"VWER":[270],"than":[271,297],"current":[273],"state-of-the-art":[274],"methods.":[275],"addition,":[277],"perceptual":[279],"user":[280],"study":[281],"over":[284,315],"77%":[285],"70%":[287],"cases":[289,320],"believe":[290],"paper\u2019s":[293],"comparative":[299],"algorithms":[300],"EMOCA":[301],"SPECTRE":[303],"in":[304],"terms":[305,309],"realism.":[307],"synchronization,":[312],"it":[313],"received":[314],"79%":[316],"66%":[318],"support,":[321],"respectively.":[322],"Both":[323],"demonstrate":[326],"effectiveness":[328],"method.":[332]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}