{"id":"https://openalex.org/W7119084123","doi":"https://doi.org/10.1109/tmm.2026.3651074","title":"EmoSpeaker: One-Shot Fine-Grained Emotion-Controlled Talking Face Generation","display_name":"EmoSpeaker: One-Shot Fine-Grained Emotion-Controlled Talking Face Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7119084123","doi":"https://doi.org/10.1109/tmm.2026.3651074"},"language":null,"primary_location":{"id":"doi:10.1109/tmm.2026.3651074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651074","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","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/A5122268249","display_name":"Guanwen Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanwen Feng","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-1190-676X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122223174","display_name":"Haoran Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Cheng","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0001-3210-4272","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122068343","display_name":"Yunan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunan Li","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-7316-4354","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Ma","orcid":"https://orcid.org/0009-0003-7154-7206"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Ma","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0003-7154-7206","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063155651","display_name":"Chaoneng Li","orcid":"https://orcid.org/0000-0002-2781-4683"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoneng Li","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-2781-4683","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023284797","display_name":"Zhihao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Qian","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0009-0002-7435-7136","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103213763","display_name":"Qiguang Miao","orcid":"https://orcid.org/0000-0001-6766-8310"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Miao","raw_affiliation_strings":["School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0001-6766-8310","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104337937","display_name":"Chi-Man Pun","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chi-Man Pun","raw_affiliation_strings":["Department of Computer and Information Science, University of Macau, Macao, China"],"raw_orcid":"https://orcid.org/0000-0003-1788-3746","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Macau, Macao, China","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5122268249"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":31.7139,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.98100286,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2681","last_page":"2692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.720300018787384,"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":0.720300018787384,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.21549999713897705,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.028599999845027924,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/rendering","display_name":"Rendering (computer graphics)","score":0.6638000011444092},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5949000120162964},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.565500020980835},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4675000011920929},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4366999864578247},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.39160001277923584},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.375},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3497999906539917},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8639000058174133},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6638000011444092},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5949000120162964},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.375},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3068999946117401},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.2935999929904938},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C3020014160","wikidata":"https://www.wikidata.org/wiki/Q6987190","display_name":"Negative emotion","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.2581999897956848},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2026.3651074","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3651074","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1552275008","display_name":null,"funder_award_id":"62472342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6834291205","display_name":null,"funder_award_id":"62272364","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Implementing":[0],"fine-grained":[1,44,107,122],"emotion":[2,7,108,116,123,140],"control":[3,118,128],"is":[4],"crucial":[5],"for":[6],"generation":[8,150,185],"tasks":[9],"because":[10],"it":[11,21],"enhances":[12],"the":[13,17,35,78,86,90,133,160,168],"expressive":[14],"capability":[15],"of":[16,40,80,92,139,147,162,189],"generative":[18],"model,":[19],"allowing":[20],"to":[22,65,85,154,166],"accurately":[23,48],"and":[24,27,38,56,136,192],"comprehensively":[25],"capture":[26],"express":[28],"various":[29],"nuanced":[30],"emotional":[31,36,50,102,130,182],"states,":[32],"thereby":[33],"improving":[34],"quality":[37],"personalization":[39],"generated":[41,134],"content.":[42],"Generating":[43],"facial":[45],"animations":[46],"that":[47,175],"portray":[49],"expressions":[51],"using":[52,120],"only":[53],"a":[54,61,71,106,121,145,163],"portrait":[55],"an":[57,115],"audio":[58,74,87],"recording":[59],"presents":[60],"challenge.":[62],"In":[63],"order":[64],"address":[66],"this":[67],"challenge,":[68],"we":[69,104,113],"propose":[70,114],"visual":[72],"attribute-guided":[73],"decoupler.":[75],"This":[76],"enables":[77],"obtention":[79],"content":[81],"vectors":[82],"solely":[83],"related":[84],"content,":[88],"enhancing":[89],"stability":[91],"subsequent":[93],"lip":[94,193],"movement":[95],"coefficient":[96,109,149],"predictions.":[97],"To":[98],"achieve":[99],"more":[100],"precise":[101],"expression,":[103],"introduce":[105],"prediction":[110],"module.":[111],"Additionally,":[112],"intensity":[117,141],"method":[119],"matrix.":[124],"Through":[125],"these,":[126],"effective":[127],"over":[129],"expression":[131,190],"in":[132,187],"videos":[135],"finer":[137],"classification":[138],"are":[142,152],"accomplished.":[143],"Subsequently,":[144],"series":[146],"3DMM":[148],"networks":[151],"designed":[153],"predict":[155],"3D":[156],"coefficients,":[157],"followed":[158],"by":[159],"utilization":[161],"rendering":[164],"network":[165],"generate":[167],"final":[169],"video.":[170],"Our":[171],"experimental":[172],"results":[173],"demonstrate":[174],"our":[176],"proposed":[177],"method,":[178],"EmoSpeaker,":[179],"outperforms":[180],"existing":[181],"talking":[183],"face":[184],"methods":[186],"terms":[188],"variation":[191],"synchronization.":[194],"Project":[195],"page:":[196],"<uri":[197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://peterfanfan.github.io/EmoSpeaker/</uri>":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2026-01-08T00:00:00"}
