{"id":"https://openalex.org/W4414231438","doi":"https://doi.org/10.1109/ialp68296.2024.11156709","title":"EmotionFace: Speech-Driven Emotional 3D Face Animation Based on Facial Decoupling","display_name":"EmotionFace: Speech-Driven Emotional 3D Face Animation Based on Facial Decoupling","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231438","doi":"https://doi.org/10.1109/ialp68296.2024.11156709"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100356545","display_name":"Zhaoyang Wang","orcid":"https://orcid.org/0009-0001-6412-5799"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Wang","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086475995","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0001-5946-676X"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["School of Computer Science, Inner Mongolia University,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"243","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9927999973297119,"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":0.9927999973297119,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9241999983787537,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.636900007724762},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5723000168800354},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.5698999762535095},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5480999946594238},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4065000116825104},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.3765999972820282},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.35659998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318000197410583},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.636900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.5698999762535095},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3765999972820282},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C40346341","wikidata":"https://www.wikidata.org/wiki/Q1391629","display_name":"Facial Action Coding System","level":3,"score":0.33899998664855957},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2944294033","https://openalex.org/W3081192838","https://openalex.org/W3175546442","https://openalex.org/W3197199219","https://openalex.org/W4200630629","https://openalex.org/W4297793551","https://openalex.org/W4385682917","https://openalex.org/W4386072021","https://openalex.org/W4386076250","https://openalex.org/W4387967971","https://openalex.org/W4390872334","https://openalex.org/W4390872742","https://openalex.org/W4390872926","https://openalex.org/W4390873123","https://openalex.org/W4400582137","https://openalex.org/W4400818936","https://openalex.org/W4403081627"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,28],"speech-driven":[3],"3D":[4],"facial":[5,16,34,151],"animation":[6],"models":[7,58],"have":[8],"significantly":[9],"enhanced":[10],"the":[11,37,82,109],"quality":[12],"and":[13,62,66,76,98,119,138],"realism":[14],"of":[15],"animations.":[17],"However,":[18],"existing":[19],"methods":[20],"often":[21],"fail":[22],"to":[23,31,39,71,93,163],"adequately":[24],"capture":[25],"emotional":[26,42,77,96,157],"expressions":[27],"videos":[29],"or":[30],"effectively":[32],"decouple":[33],"features,":[35,158],"limiting":[36],"ability":[38],"independently":[40,72],"control":[41,73],"expressions.":[43,78],"To":[44,127],"address":[45],"these":[46],"limitations,":[47],"we":[48,80,107,131],"propose":[49],"a":[50,55,89,123],"novel":[51],"model":[52,92],"based":[53],"on":[54],"large-scale":[56],"visual":[57,91],"that":[59,144],"integrates":[60],"audio":[61],"textual":[63],"style":[64],"label":[65],"emotion":[67],"source":[68],"video":[69],"prompts":[70],"lip":[74,117,129],"movements":[75,118],"Specifically,":[79],"introduce":[81],"Video-Guided":[83],"Emotional":[84],"Motion":[85,112],"Module,":[86,113],"which":[87,114],"leverages":[88],"large":[90],"extract":[94],"frame-level":[95],"features":[97],"maps":[99],"them":[100,121],"into":[101,122],"an":[102],"independent":[103],"latent":[104,125],"space.":[105,126],"Furthermore,":[106],"present":[108],"Audio-Guided":[110],"Lip":[111],"dynamically":[115],"de-constructs":[116],"encodes":[120],"separate":[124],"enhance":[128],"synchronization,":[130],"incorporate":[132],"Avhubert":[133],"technology,":[134],"improving":[135],"both":[136],"accuracy":[137],"comprehensibility.":[139],"Comprehensive":[140],"experimental":[141],"results":[142],"demonstrate":[143],"our":[145],"method":[146],"not":[147],"only":[148],"generates":[149],"high-quality":[150],"animations":[152],"but":[153],"also":[154],"authentically":[155],"reflects":[156],"achieving":[159],"superior":[160],"performance":[161],"compared":[162],"state-of-the-art":[164],"techniques.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}