{"id":"https://openalex.org/W4392931432","doi":"https://doi.org/10.1109/icassp48485.2024.10446049","title":"DiffDub: Person-Generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-Encoder","display_name":"DiffDub: Person-Generic Visual Dubbing Using Inpainting Renderer with Diffusion Auto-Encoder","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931432","doi":"https://doi.org/10.1109/icassp48485.2024.10446049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100716705","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0002-3672-3599"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN","US"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["AI Institute,MoE Key Lab of Artificial Intelligence","MoE Key Lab of Artificial Intelligence, AI Institute","X-LANCE Lab, Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I4210156221"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":[]},{"raw_affiliation_string":"X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035532752","display_name":"Chenpeng Du","orcid":"https://orcid.org/0000-0001-5329-0847"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN","US"],"is_corresponding":false,"raw_author_name":"Chenpeng Du","raw_affiliation_strings":["AI Institute,MoE Key Lab of Artificial Intelligence","X-LANCE Lab, Shanghai Jiao Tong University","MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I4210156221"]},{"raw_affiliation_string":"X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102608449","display_name":"Shuai Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Fan","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667541","display_name":"Feilong Chen","orcid":"https://orcid.org/0000-0002-4860-8483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feilong Chen","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN","US"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["AI Institute,MoE Key Lab of Artificial Intelligence","X-LANCE Lab, Shanghai Jiao Tong University","MoE Key Lab of Artificial Intelligence, AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute,MoE Key Lab of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I4210156221"]},{"raw_affiliation_string":"X-LANCE Lab, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3124,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80367583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3630","last_page":"3634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9976000189781189,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9976000189781189,"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/T11448","display_name":"Face recognition and analysis","score":0.9876999855041504,"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":0.98580002784729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.841179609298706},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6319164037704468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5832371711730957},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5647781491279602},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5643843412399292},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5521489977836609},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.49903225898742676},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3377801179885864},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13059356808662415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841179609298706},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6319164037704468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5832371711730957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5647781491279602},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5643843412399292},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5521489977836609},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.49903225898742676},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3377801179885864},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13059356808662415},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3405895753","display_name":null,"funder_award_id":"92370206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","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":41,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2015394094","https://openalex.org/W2133665775","https://openalex.org/W2604379605","https://openalex.org/W2949662773","https://openalex.org/W2962785568","https://openalex.org/W2964110616","https://openalex.org/W2981767644","https://openalex.org/W3019952993","https://openalex.org/W3036167779","https://openalex.org/W3081492798","https://openalex.org/W3097777922","https://openalex.org/W3101631197","https://openalex.org/W3104792420","https://openalex.org/W3109114891","https://openalex.org/W3162926177","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3197580070","https://openalex.org/W3205904637","https://openalex.org/W3209059054","https://openalex.org/W3216352822","https://openalex.org/W3217030260","https://openalex.org/W4200630629","https://openalex.org/W4312497550","https://openalex.org/W4315589026","https://openalex.org/W4372262450","https://openalex.org/W4382240211","https://openalex.org/W4385245566","https://openalex.org/W4385682917","https://openalex.org/W4386065999","https://openalex.org/W4386066256","https://openalex.org/W4386075487","https://openalex.org/W4391072501","https://openalex.org/W4392780157","https://openalex.org/W4394597549","https://openalex.org/W6629923403","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6795288823"],"related_works":["https://openalex.org/W291250033","https://openalex.org/W2035757446","https://openalex.org/W3137044537","https://openalex.org/W2008385118","https://openalex.org/W880955280","https://openalex.org/W2106647072","https://openalex.org/W2172753644","https://openalex.org/W2170209930","https://openalex.org/W4246858109","https://openalex.org/W54172855"],"abstract_inverted_index":{"Generating":[0],"high-quality":[1],"and":[2,22,76,137,148,167,189,196],"person-generic":[3,195],"visual":[4],"dubbing":[5],"remains":[6],"a":[7,16,31,44,70,144,153],"challenge.":[8],"Recent":[9],"innovation":[10],"has":[11],"seen":[12],"the":[13,20,62,85,90,101,114],"advent":[14],"of":[15,84],"two-stage":[17],"paradigm,":[18],"decoupling":[19],"rendering":[21],"lip":[23],"synchronization":[24],"process":[25],"facilitated":[26],"by":[27,65,152],"intermediate":[28],"representation":[29],"as":[30],"conduit.":[32],"Still,":[33],"previous":[34],"methodologies":[35],"rely":[36],"on":[37,170],"rough":[38],"landmarks":[39],"or":[40,121],"are":[41],"confined":[42],"to":[43,72,109,160],"single":[45],"speaker,":[46],"thus":[47],"limiting":[48],"their":[49],"performance.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,96,130,142],"propose":[55],"DiffDub:":[56],"Diffusion-based":[57],"dubbing.":[58],"We":[59],"first":[60],"craft":[61],"Diffusion":[63],"auto-encoder":[64],"an":[66],"inpainting":[67],"renderer":[68],"incorporating":[69],"mask":[71],"delineate":[73],"editable":[74],"zones":[75],"unaltered":[77],"regions.":[78],"This":[79,156],"allows":[80],"for":[81],"seamless":[82],"filling":[83],"lower-face":[86],"region":[87],"while":[88],"preserving":[89],"remaining":[91],"parts.":[92],"Throughout":[93],"our":[94,158,180],"experiments,":[95],"encountered":[97],"several":[98],"challenges.":[99],"Primarily,":[100],"semantic":[102],"encoder":[103,147],"lacks":[104],"robustness,":[105],"constricting":[106],"its":[107],"ability":[108],"capture":[110],"high-level":[111],"features.":[112],"Besides,":[113],"modeling":[115],"ignored":[116],"facial":[117],"positioning,":[118],"causing":[119],"mouth":[120],"nose":[122],"jitters":[123],"across":[124],"frames.":[125],"To":[126],"tackle":[127],"these":[128],"issues,":[129],"employ":[131],"versatile":[132],"strategies,":[133],"including":[134],"data":[135],"augmentation":[136],"supplementary":[138],"eye":[139],"guidance.":[140],"Moreover,":[141],"encapsulated":[143],"conformer-based":[145],"reference":[146],"motion":[149],"generator":[150],"fortified":[151],"cross-attention":[154],"mechanism.":[155],"enables":[157],"model":[159],"learn":[161],"person-specific":[162],"textures":[163],"with":[164,186],"varying":[165],"references":[166],"reduces":[168],"reliance":[169],"paired":[171],"audio-visual":[172],"data.":[173],"Our":[174],"rigorous":[175],"experiments":[176],"comprehensively":[177],"highlight":[178],"that":[179],"ground-breaking":[181],"approach":[182],"outpaces":[183],"existing":[184],"methods":[185],"considerable":[187],"margins":[188],"delivers":[190],"seamless,":[191],"intelligible":[192],"videos":[193],"in":[194],"multilingual":[197],"scenarios.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}