{"id":"https://openalex.org/W4297095647","doi":"https://doi.org/10.1109/tcsvt.2022.3210002","title":"Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis","display_name":"Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4297095647","doi":"https://doi.org/10.1109/tcsvt.2022.3210002"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3210002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3210002","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.00030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043375205","display_name":"Linsen Song","orcid":"https://orcid.org/0000-0003-0817-2600"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linsen Song","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0817-2600","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000896822","display_name":"Wayne Wu","orcid":"https://orcid.org/0000-0002-1364-8151"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayne Wu","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014172220","display_name":"Chaoyou Fu","orcid":"https://orcid.org/0000-0002-0079-7668"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyou Fu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0079-7668","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"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":"Chen Change Loy","raw_affiliation_strings":["S-Laboratory, Nanyang Technological University, Jurong West, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-5345-1591","affiliations":[{"raw_affiliation_string":"S-Laboratory, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3807-991X","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, CASIA, Center for Research on Intelligent Perception and Computing, CASIA, Center for Excellence in Brain Science and Intelligence Technology, CAS, and the School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1602,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76157292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"33","issue":"3","first_page":"1247","last_page":"1261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991000294685364,"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":0.9962999820709229,"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":0.8632740378379822},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6561598777770996},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5364896059036255},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.48529404401779175},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4735904335975647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4532133936882019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3368711471557617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8632740378379822},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6561598777770996},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5364896059036255},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.48529404401779175},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4735904335975647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4532133936882019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3368711471557617},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2022.3210002","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3210002","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2309.00030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.00030","pdf_url":"https://arxiv.org/pdf/2309.00030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.00030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.00030","pdf_url":"https://arxiv.org/pdf/2309.00030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8442675014","display_name":null,"funder_award_id":"U20A20223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8709529125","display_name":null,"funder_award_id":"U21B2045","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297095647.pdf","grobid_xml":"https://content.openalex.org/works/W4297095647.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W1987875999","https://openalex.org/W2017107803","https://openalex.org/W2064675550","https://openalex.org/W2070604790","https://openalex.org/W2080277992","https://openalex.org/W2082285544","https://openalex.org/W2146991130","https://openalex.org/W2152826865","https://openalex.org/W2154851929","https://openalex.org/W2163819245","https://openalex.org/W2217241238","https://openalex.org/W2237250383","https://openalex.org/W2301937176","https://openalex.org/W2331128040","https://openalex.org/W2344899809","https://openalex.org/W2502312327","https://openalex.org/W2515372520","https://openalex.org/W2518172956","https://openalex.org/W2593414223","https://openalex.org/W2603777577","https://openalex.org/W2604379605","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2803193013","https://openalex.org/W2806833697","https://openalex.org/W2883183894","https://openalex.org/W2884460600","https://openalex.org/W2902266071","https://openalex.org/W2902836694","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2960274051","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2962974533","https://openalex.org/W2963092440","https://openalex.org/W2963290645","https://openalex.org/W2963609956","https://openalex.org/W2963684088","https://openalex.org/W2963789946","https://openalex.org/W2971634123","https://openalex.org/W2972659941","https://openalex.org/W2988149145","https://openalex.org/W2999966482","https://openalex.org/W3006410788","https://openalex.org/W3010434693","https://openalex.org/W3019952993","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3155375169","https://openalex.org/W3163658555","https://openalex.org/W3165405144","https://openalex.org/W3194230325","https://openalex.org/W3199474181","https://openalex.org/W6631190155","https://openalex.org/W6638545294","https://openalex.org/W6640090968","https://openalex.org/W6685352114","https://openalex.org/W6724804524","https://openalex.org/W6765657114","https://openalex.org/W6765779288","https://openalex.org/W6772994595","https://openalex.org/W6774285787"],"related_works":["https://openalex.org/W3037187668","https://openalex.org/W4234772502","https://openalex.org/W2380685755","https://openalex.org/W2252100032","https://openalex.org/W2963436428","https://openalex.org/W2734796617","https://openalex.org/W2102405864","https://openalex.org/W3034087822","https://openalex.org/W2477982797","https://openalex.org/W2171591485"],"abstract_inverted_index":{"Existing":[0],"automated":[1],"dubbing":[2,34],"methods":[3],"are":[4,47,62,82],"usually":[5],"designed":[6],"for":[7,40,55,163],"Professionally":[8],"Generated":[9,42],"Content":[10,43],"(PGC)":[11],"production,":[12],"which":[13,139],"requires":[14],"massive":[15],"training":[16,19,146,191,194],"data":[17,78,147,192],"and":[18,64,108,193],"time":[20,195],"to":[21,51,70,87,100,124,127,198],"learn":[22],"a":[23,53,95,116,128,135,153,160,205],"person-specific":[24],"audio-video":[25],"mapping.":[26],"In":[27,85],"this":[28],"paper,":[29],"we":[30,92,132,158],"investigate":[31],"an":[32],"audio-driven":[33],"method":[35,54,68,176,203],"that":[36,174,179],"is":[37],"more":[38,168],"feasible":[39],"User":[41],"(UGC)":[44],"production.":[45],"There":[46],"two":[48],"unique":[49],"challenges":[50],"design":[52],"UGC:":[56],"1)":[57],"the":[58,67,75,89,102,106,109,113,144,149,164],"appearances":[59],"of":[60,79,105,112,143,148,190],"speakers":[61],"diverse":[63],"arbitrary":[65],"as":[66],"needs":[69],"generalize":[71],"across":[72],"users;":[73],"2)":[74],"available":[76],"video":[77,137],"one":[80],"speaker":[81,151],"very":[83],"limited.":[84],"order":[86],"tackle":[88],"above":[90],"challenges,":[91],"first":[93],"introduce":[94],"new":[96,129],"Style":[97],"Translation":[98],"Network":[99],"integrate":[101],"speaking":[103,110,183],"style":[104],"target":[107],"content":[111],"source":[114],"via":[115,152],"cross-modal":[117],"AdaIN":[118],"module.":[119],"It":[120],"enables":[121],"our":[122,175,202],"model":[123],"quickly":[125],"adapt":[126],"speaker.":[130],"Then,":[131],"further":[133],"develop":[134],"semi-parametric":[136,165],"renderer,":[138,166],"takes":[140],"full":[141],"advantage":[142],"limited":[145],"unseen":[150],"video-level":[154],"retrieve-warp-refine":[155],"pipeline.":[156],"Finally,":[157],"propose":[159],"temporal":[161],"regularization":[162],"generating":[167],"continuous":[169],"videos.":[170],"Extensive":[171],"experiments":[172],"show":[173],"generates":[177],"videos":[178],"accurately":[180],"preserve":[181],"various":[182],"styles,":[184],"yet":[185],"with":[186],"considerably":[187],"lower":[188],"amount":[189],"in":[196],"comparison":[197],"existing":[199],"methods.":[200,212],"Besides,":[201],"achieves":[204],"faster":[206],"testing":[207],"speed":[208],"than":[209],"most":[210],"recent":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}