{"id":"https://openalex.org/W7164842730","doi":"https://doi.org/10.1145/3805622.3810884","title":"ExpV2S: Zero-Shot Expressive Video-to-Speech Synthesis via Latent Diffusion Model","display_name":"ExpV2S: Zero-Shot Expressive Video-to-Speech Synthesis via Latent Diffusion Model","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164842730","doi":"https://doi.org/10.1145/3805622.3810884"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810884","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138636381","display_name":"Fang Zhang","orcid":"https://orcid.org/0009-0002-6870-8657"},"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":"Fang Zhang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0002-6870-8657","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027387710","display_name":"Anqi Gou","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":"Anqi Gou","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-9863-7689","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009732907","display_name":"Linli Xu","orcid":"https://orcid.org/0000-0003-0227-3793"},"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":"Linli Xu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0227-3793","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.93805209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"855","last_page":"864"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7652000188827515,"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":0.7652000188827515,"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":0.11680000275373459,"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":0.08749999850988388,"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/generalization","display_name":"Generalization","score":0.7124999761581421},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5605000257492065},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5166000127792358},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4408000111579895},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4345000088214874},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3684999942779541},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.32190001010894775}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.710099995136261},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810884","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810884","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.42755454778671265,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2015143272","https://openalex.org/W2030931454","https://openalex.org/W2194775991","https://openalex.org/W2326925005","https://openalex.org/W2516001803","https://openalex.org/W2604379605","https://openalex.org/W2803193013","https://openalex.org/W2962788625","https://openalex.org/W2981263323","https://openalex.org/W3035626590","https://openalex.org/W3099284785","https://openalex.org/W3157840621","https://openalex.org/W3162707322","https://openalex.org/W3196584150","https://openalex.org/W4224926225","https://openalex.org/W4283809657","https://openalex.org/W4307929907","https://openalex.org/W4312933868","https://openalex.org/W4372348072","https://openalex.org/W4375868850","https://openalex.org/W4385823403","https://openalex.org/W4386075767","https://openalex.org/W4390872449","https://openalex.org/W4396877837","https://openalex.org/W4402961784","https://openalex.org/W4409262657"],"related_works":[],"abstract_inverted_index":{"Video-to-Speech":[0],"(V2S)":[1],"Synthesis":[2],"aims":[3],"to":[4,22,39,98,123,199],"generate":[5],"speech":[6,153],"that":[7,154,172],"synchronizes":[8],"with":[9],"lip":[10,85,101],"motions":[11,102],"and":[12,35,87,106,129,158,161,182],"reflects":[13],"the":[14,24,47,100,125,145,200],"speaker\u2019s":[15,25,41],"unique":[16],"characteristics.":[17],"However,":[18],"existing":[19],"methods":[20,177],"tend":[21],"overlook":[23],"emotional":[26,112],"state,":[27],"which":[28],"is":[29,121,148,155],"crucial":[30],"for":[31,43,63,190],"producing":[32],"expressive":[33,152,187],"speech,":[34,188],"they":[36],"often":[37],"struggle":[38],"retain":[40],"characteristics":[42],"unseen":[44],"individuals,":[45],"reducing":[46],"model\u2019s":[48],"generalization":[49],"capability.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55,70,92],"propose":[56],"ExpV2S:":[57],"a":[58,75,79,115,138,143],"latent":[59,80],"diffusion":[60],"model":[61],"(LDM)":[62],"zero-shot":[64,192],"Expressive":[65],"Video2Speech":[66],"synthesis.":[67],"In":[68],"general,":[69],"reformulate":[71],"video-to-speech":[72],"synthesis":[73,136],"as":[74],"denoising":[76],"process":[77],"in":[78,178],"space,":[81],"guided":[82],"jointly":[83],"by":[84,109],"movements":[86],"facial":[88],"features.":[89],"More":[90],"specifically,":[91],"introduce":[93],"an":[94],"emotion":[95,105],"disentangling":[96],"module":[97],"decompose":[99],"into":[103],"seperate":[104],"context":[107],"embeddings":[108],"generating":[110,151],"cross-reconstructed":[111],"speech.":[113],"Then,":[114],"face-speech":[116],"contrastive":[117],"learning":[118],"mechanism":[119],"(FSCL)":[120],"proposed":[122,146],"capture":[124],"correspondence":[126],"between":[127],"visual":[128],"acoustic":[130],"speaker":[131],"characteristics,":[132],"enabling":[133],"accurate":[134],"voice":[135],"from":[137],"single":[139],"face":[140],"image.":[141],"As":[142],"result,":[144],"ExpV2S":[147],"capable":[149],"of":[150],"both":[156,179],"intelligible":[157],"emotionally":[159],"consistent,":[160],"more":[162,195],"importantly,":[163],"it":[164],"generalizes":[165],"across":[166],"different":[167],"speakers.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"our":[173],"approach":[174],"outperforms":[175],"state-of-the-art":[176],"quantitative":[180],"metrics":[181],"human":[183],"evaluations,":[184],"effectively":[185],"synthesizing":[186],"especially":[189],"generalized":[191],"individuals.":[193],"For":[194],"samples,":[196],"please":[197],"refer":[198],"supplementary":[201],"material.":[202]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}