{"id":"https://openalex.org/W7131828803","doi":"https://doi.org/10.1109/tmm.2026.3668534","title":"SimDEM: Audio-Driven Emotional Talking Head Generation With Simplified and Decoupled Expression Modeling","display_name":"SimDEM: Audio-Driven Emotional Talking Head Generation With Simplified and Decoupled Expression Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131828803","doi":"https://doi.org/10.1109/tmm.2026.3668534"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2026.3668534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668534","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/A5078967811","display_name":"Jianzhi Long","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jianzhi Long","raw_affiliation_strings":["Sydney Artificial Intelligence Centre, School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sydney Artificial Intelligence Centre, School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008273094","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9567-159X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9567-159X","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127441762","display_name":"Dacheng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20591338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"5798","last_page":"5808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5874999761581421,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.5874999761581421,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.15680000185966492,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.07249999791383743,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/naturalness","display_name":"Naturalness","score":0.8101999759674072},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.6972000002861023},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6556000113487244},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.49129998683929443},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4498000144958496},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.41929998993873596},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.41850000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337000012397766},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8101999759674072},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6972000002861023},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6556000113487244},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41850000619888306},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39500001072883606},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3767000138759613},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2026.3668534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2026.3668534","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/211919","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/211919","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Emotional":[0],"talking":[1,56,136],"head":[2,57,137],"generation":[3,58],"has":[4],"advanced":[5],"significantly":[6],"because":[7],"of":[8,71,91,107,115],"its":[9],"potential":[10],"to":[11],"enhance":[12],"naturalness":[13],"and":[14,22,40,62,84,100,130],"expressiveness":[15],"in":[16,82,133],"applications":[17],"like":[18],"gaming,":[19],"virtual":[20],"reality,":[21],"video":[23],"conferencing.":[24],"However,":[25],"existing":[26],"methods":[27],"struggle":[28],"with":[29],"overcomplicated":[30],"facial":[31,92],"expression":[32,64,73,77],"modeling,":[33,78],"which":[34],"introduces":[35],"redundancies,":[36],"reduces":[37],"learning":[38,106],"efficiency,":[39],"limits":[41],"emotion":[42,86,128],"accuracy.":[43,87],"To":[44],"address":[45],"these":[46],"limitations,":[47],"we":[48,79],"propose":[49],"SimDEM,":[50],"a":[51],"novel":[52],"framework":[53],"for":[54,97],"emotional":[55,109],"that":[59,121],"leverages":[60],"simplified":[61],"decoupled":[63],"modeling.":[65],"By":[66],"retaining":[67],"only":[68],"critical":[69],"dimensions":[70],"the":[72,89,98,112,116],"representation":[74],"via":[75],"key":[76],"reduce":[80],"noise":[81],"training":[83],"improve":[85],"Furthermore,":[88],"decoupling":[90],"regions":[93],"into":[94],"independent":[95],"dynamics":[96],"upper":[99],"lower":[101],"face":[102],"enables":[103],"more":[104],"effective":[105],"localized":[108],"expressions,":[110],"enhancing":[111],"visual":[113,131],"fidelity":[114],"output.":[117],"Extensive":[118],"evaluations":[119],"demonstrate":[120],"SimDEM":[122],"outperforms":[123],"state-of-the-art":[124],"methods,":[125],"achieving":[126],"superior":[127],"accuracy":[129],"quality":[132],"synthesizing":[134],"expressive":[135],"videos.":[138]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-02-28T00:00:00"}