{"id":"https://openalex.org/W4408345766","doi":"https://doi.org/10.1109/icassp49660.2025.10889186","title":"SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space","display_name":"SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345766","doi":"https://doi.org/10.1109/icassp49660.2025.10889186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5087911107","display_name":"Zeren Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeren Zhang","raw_affiliation_strings":["Peking University,School of Mathematical Sciences,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Mathematical Sciences,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064275022","display_name":"Haibo Qin","orcid":"https://orcid.org/0000-0002-7404-3703"},"institutions":[{"id":"https://openalex.org/I4210099741","display_name":"Yonyou (China)","ror":"https://ror.org/016dc7q50","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Qin","raw_affiliation_strings":["Youdao AI,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youdao AI,Beijing,China,100084","institution_ids":["https://openalex.org/I4210099741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671259","display_name":"Jiayu Huang","orcid":"https://orcid.org/0009-0000-7537-331X"},"institutions":[{"id":"https://openalex.org/I4210099741","display_name":"Yonyou (China)","ror":"https://ror.org/016dc7q50","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Huang","raw_affiliation_strings":["Youdao AI,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youdao AI,Beijing,China,100084","institution_ids":["https://openalex.org/I4210099741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013467571","display_name":"Jo-Ku Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jo-Ku Cheng","raw_affiliation_strings":["Peking University,School of Mathematical Sciences,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Mathematical Sciences,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076970563","display_name":"Y Li","orcid":"https://orcid.org/0000-0001-6963-0957"},"institutions":[{"id":"https://openalex.org/I4210099741","display_name":"Yonyou (China)","ror":"https://ror.org/016dc7q50","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Li","raw_affiliation_strings":["Youdao AI,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youdao AI,Beijing,China,100084","institution_ids":["https://openalex.org/I4210099741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101656277","display_name":"Lin Hui","orcid":"https://orcid.org/0000-0001-8223-3999"},"institutions":[{"id":"https://openalex.org/I4210099741","display_name":"Yonyou (China)","ror":"https://ror.org/016dc7q50","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Lin","raw_affiliation_strings":["Youdao AI,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youdao AI,Beijing,China,100084","institution_ids":["https://openalex.org/I4210099741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108663480","display_name":"Yitao Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099741","display_name":"Yonyou (China)","ror":"https://ror.org/016dc7q50","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitao Duan","raw_affiliation_strings":["Youdao AI,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Youdao AI,Beijing,China,100084","institution_ids":["https://openalex.org/I4210099741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067164993","display_name":"Jinwen Ma","orcid":"https://orcid.org/0000-0002-7388-4295"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwen Ma","raw_affiliation_strings":["Peking University,School of Mathematical Sciences,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Mathematical Sciences,Beijing,China,100871","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.02847298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9753000140190125,"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":0.9635000228881836,"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/personalization","display_name":"Personalization","score":0.745984673500061},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281417846679688},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6328808069229126},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6023709177970886},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.552910566329956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37995272874832153},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.36693504452705383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34982722997665405},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1919407844543457}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.745984673500061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281417846679688},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6328808069229126},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6023709177970886},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.552910566329956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37995272874832153},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36693504452705383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34982722997665405},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1919407844543457},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":36,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2166465411","https://openalex.org/W2608058963","https://openalex.org/W2962770929","https://openalex.org/W2969985801","https://openalex.org/W3034301684","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3092709185","https://openalex.org/W3180355996","https://openalex.org/W3180391059","https://openalex.org/W3191243633","https://openalex.org/W3197199219","https://openalex.org/W3197199501","https://openalex.org/W3209059054","https://openalex.org/W4280631290","https://openalex.org/W4297793551","https://openalex.org/W4312301053","https://openalex.org/W4312411334","https://openalex.org/W4312551140","https://openalex.org/W4312911690","https://openalex.org/W4312933868","https://openalex.org/W4313068475","https://openalex.org/W4319300274","https://openalex.org/W4375868939","https://openalex.org/W4385245566","https://openalex.org/W4385490328","https://openalex.org/W4386071653","https://openalex.org/W4386075501","https://openalex.org/W4386076090","https://openalex.org/W4390871677","https://openalex.org/W4390872297","https://openalex.org/W4394597155","https://openalex.org/W4394597549","https://openalex.org/W6745560452","https://openalex.org/W6765779288"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2141531133"],"abstract_inverted_index":{"Combining":[0],"face-swapping":[1,48,75,136],"with":[2,70,81],"lip":[3,50,133],"synchronization":[4,51,79,134],"offers":[5],"a":[6,43,102],"cost-effective":[7],"solution":[8],"for":[9,59],"generating":[10],"customized":[11],"talking":[12],"faces.":[13],"However,":[14],"directly":[15],"cascading":[16],"existing":[17,128],"models":[18],"can":[19],"introduce":[20,101],"significant":[21],"interference":[22],"and":[23,49,62,77,138],"reduce":[24],"video":[25,131],"clarity":[26],"due":[27],"to":[28,67,95,107],"limited":[29],"interaction":[30],"space":[31],"in":[32,73,117,130],"the":[33,53,74,92,111],"low-level":[34],"RGB":[35],"domain.":[36],"To":[37,85],"solve":[38],"this,":[39],"we":[40,90,100],"propose":[41],"SwapTalk,":[42],"unified":[44],"framework":[45],"that":[46,125],"performs":[47],"within":[52],"same":[54],"latent":[55],"VQ-embedding":[56],"space,":[57],"known":[58],"its":[60],"editability":[61],"fidelity.":[63],"We":[64],"enhance":[65],"generalization":[66],"unseen":[68],"identities":[69],"identity":[71,104,112,139],"loss":[72],"module":[76],"improve":[78],"quality":[80],"expert":[82],"discriminator":[83],"supervision.":[84],"better":[86],"approximate":[87],"real-world":[88],"applications,":[89],"expand":[91],"evaluation":[93],"scope":[94],"asynchronous":[96],"audio-video":[97],"scenarios.":[98],"Furthermore,":[99],"novel":[103],"consistency":[105,113],"metric":[106],"more":[108],"comprehensively":[109],"assess":[110],"over":[114],"time":[115],"series":[116],"generated":[118],"facial":[119],"videos.":[120],"Experiments":[121],"on":[122],"HDTF":[123],"show":[124],"SwapTalk":[126],"outperforms":[127],"methods":[129],"quality,":[132],"accuracy,":[135],"fidelity,":[137],"consistency.":[140]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}