{"id":"https://openalex.org/W7160284642","doi":"https://doi.org/10.1109/wacv61042.2026.00442","title":"SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding","display_name":"SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160284642","doi":"https://doi.org/10.1109/wacv61042.2026.00442"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5111254274","display_name":"Phyo Thet Yee","orcid":null},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Phyo Thet Yee","raw_affiliation_strings":["IIT Ropar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Ropar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029879679","display_name":"Dimitrios Kollias","orcid":"https://orcid.org/0000-0002-8188-3751"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitrios Kollias","raw_affiliation_strings":["Queen Mary University of London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055393595","display_name":"Sudeepta Mishra","orcid":"https://orcid.org/0000-0003-4821-4318"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeepta Mishra","raw_affiliation_strings":["IIT Ropar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Ropar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abhinav Dhall","raw_affiliation_strings":["Monash University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.51728206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4546","last_page":"4555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7724999785423279,"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":0.7724999785423279,"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":0.13369999825954437,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04529999941587448,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41429999470710754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2750000059604645},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2667999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5809000134468079},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31439998745918274},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W2964449965","https://openalex.org/W2981767644","https://openalex.org/W3081492798","https://openalex.org/W3096831136","https://openalex.org/W3099284785","https://openalex.org/W3197199219","https://openalex.org/W4247405818","https://openalex.org/W4280631290","https://openalex.org/W4304014863","https://openalex.org/W4312933868","https://openalex.org/W4361994820","https://openalex.org/W4386075487","https://openalex.org/W4390874181","https://openalex.org/W4392904679","https://openalex.org/W4394597155","https://openalex.org/W4400527566","https://openalex.org/W4400573497","https://openalex.org/W4402728455","https://openalex.org/W4403791206","https://openalex.org/W4404965490","https://openalex.org/W4409369524","https://openalex.org/W4410986028","https://openalex.org/W4413147005","https://openalex.org/W4413557526","https://openalex.org/W4415799309"],"related_works":[],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,104],"face":[2,105],"generation":[3,102],"has":[4],"received":[5],"growing":[6],"interest,":[7],"particularly":[8],"for":[9,31],"applications":[10],"requiring":[11],"expressive":[12],"and":[13,90,96,109,114,121,161,171,177,181,200,222],"natural":[14,118],"human-avatar":[15],"interaction.":[16],"However,":[17],"most":[18,43],"existing":[19],"emotion-aware":[20],"methods":[21,44,216],"rely":[22],"on":[23,46,168,184],"a":[24,47,72,77],"single":[25,48],"modality":[26],"(either":[27],"audio":[28,91],"or":[29,61],"image)":[30],"emotion":[32,79,94],"embedding,":[33],"limiting":[34],"their":[35],"ability":[36,54],"to":[37,55,157],"capture":[38,158],"nuanced":[39],"affective":[40],"cues.":[41],"Additionally,":[42],"condition":[45],"reference":[49],"image,":[50],"restricting":[51],"the":[52,101,137,166,191],"model\u2019s":[53],"represent":[56],"dynamic":[57,159],"changes":[58],"in":[59,195,217],"actions":[60,160],"attributes":[62],"across":[63],"time.":[64],"To":[65,116],"address":[66],"these":[67],"issues,":[68],"we":[69],"introduce":[70],"SynchroRaMa,":[71],"novel":[73],"framework":[74],"that":[75,131,188,208],"integrates":[76],"multi-modal":[78],"embedding":[80],"by":[81,146],"combining":[82],"emotional":[83,112],"signals":[84],"from":[85],"text":[86],"(via":[87,92],"sentiment":[88],"analysis)":[89],"speech-based":[93],"recognition":[95],"audio-derived":[97],"valence-arousal":[98],"features),":[99],"enabling":[100,155],"of":[103],"videos":[106],"with":[107,136],"richer":[108],"more":[110],"authentic":[111],"expressiveness":[113],"fidelity.":[115],"ensure":[117],"head":[119],"motion":[120,133,201,220],"accurate":[122],"lip":[123],"synchronization,":[124],"SynchroRaMa":[125,141,189,209],"includes":[126],"an":[127],"audio-to-motion":[128],"(A2M)":[129],"module":[130],"generates":[132],"frames":[134],"aligned":[135],"input":[138],"audio.":[139],"Finally,":[140],"incorporates":[142],"scene":[143],"descriptions":[144],"generated":[145],"Large":[147],"Language":[148],"Model":[149],"(LLM)":[150],"as":[151],"additional":[152],"textual":[153,172],"input,":[154],"it":[156],"high-level":[162],"semantic":[163],"attributes.":[164],"Conditioning":[165],"model":[167],"both":[169],"visual":[170,178],"cues":[173],"enhances":[174],"temporal":[175],"consistency":[176],"realism.":[179,202],"Quantitative":[180],"qualitative":[182],"experiments":[183],"benchmark":[185],"datasets":[186],"demonstrate":[187],"outperforms":[190],"state-of-the-art,":[192],"achieving":[193],"improvements":[194],"image":[196],"quality,":[197],"expression":[198],"preservation,":[199],"A":[203],"user":[204],"study":[205],"further":[206],"confirms":[207],"achieves":[210],"higher":[211],"subjective":[212],"ratings":[213],"than":[214],"competing":[215],"overall":[218],"naturalness,":[219],"diversity,":[221],"video":[223],"smoothness.":[224],"Our":[225],"project":[226],"page":[227],"is":[228],"available":[229],"at":[230],"https://novicemm.github.io/synchrorama.":[231]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}