{"id":"https://openalex.org/W4409906996","doi":"https://doi.org/10.1109/iccv51701.2025.01357","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","display_name":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4409906996","doi":"https://doi.org/10.1109/iccv51701.2025.01357"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.02386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103159153","display_name":"Sung-Bin Kim","orcid":"https://orcid.org/0009-0005-8455-3298"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kim Sung-Bin","raw_affiliation_strings":["POSTECH,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH,Department of Electrical Engineering","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111556720","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0000-0002-5554-3657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":["School of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075735963","display_name":"Puyuan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puyuan Peng","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["School of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114111","display_name":"Tae-Hyun Oh","orcid":"https://orcid.org/0000-0003-0468-1571"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Hyun Oh","raw_affiliation_strings":["School of Computing, KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103159153"],"corresponding_institution_ids":["https://openalex.org/I123900574","https://openalex.org/I2799891827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08923108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14623","last_page":"14632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9896000027656555,"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/T10860","display_name":"Speech and Audio Processing","score":0.9896000027656555,"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/T11309","display_name":"Music 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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9775999784469604,"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/codec","display_name":"Codec","score":0.8310876488685608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5678815841674805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3894193172454834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3335961103439331},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.18471837043762207}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8310876488685608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5678815841674805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3894193172454834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3335961103439331},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.18471837043762207}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.02386","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02386","pdf_url":"https://arxiv.org/pdf/2504.02386","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.02386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.02386","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.02386","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02386","pdf_url":"https://arxiv.org/pdf/2504.02386","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1536571850","display_name":null,"funder_award_id":"NRF-2021R1C1C1006799","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5704809196","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409906996.pdf","grobid_xml":"https://content.openalex.org/works/W4409906996.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W2107680156","https://openalex.org/W4301184752","https://openalex.org/W2288771647"],"abstract_inverted_index":{"We":[0,145],"present":[1],"VoiceCraft-Dub,":[2],"a":[3,103],"novel":[4],"approach":[5],"for":[6,42,112,149,156],"automated":[7,113],"video":[8,52,114],"dubbing":[9],"that":[10,55,119],"synthesizes":[11],"high-quality":[12],"speech":[13,43,57,127],"from":[14],"text":[15],"and":[16,28,60,86,125,139],"facial":[17,64,79],"cues.":[18],"This":[19],"task":[20],"has":[21],"broad":[22],"applications":[23],"in":[24,136,142],"filmmaking,":[25],"multimedia":[26],"creation,":[27],"assisting":[29],"voice-impaired":[30],"individuals.":[31],"Building":[32],"on":[33],"the":[34,82,96,150],"success":[35],"of":[36,106],"Neural":[37],"Codec":[38],"Language":[39],"Models":[40],"(NCLMs)":[41],"synthesis,":[44],"our":[45,120],"method":[46],"extends":[47],"their":[48],"capabilities":[49],"by":[50],"incorporating":[51],"features,":[53],"ensuring":[54],"synthesized":[56],"is":[58],"time-synchronized":[59],"expressively":[61],"aligned":[62],"with":[63,81,129],"movements":[65],"while":[66],"preserving":[67],"natural":[68,126],"prosody.":[69],"To":[70],"inject":[71],"visual":[72],"cues,":[73],"we":[74,100],"design":[75],"adapters":[76],"to":[77,91],"align":[78],"features":[80],"NCLM":[83,97],"token":[84],"space":[85],"introduce":[87],"audio-visual":[88,93],"fusion":[89],"layers":[90],"merge":[92],"information":[94],"within":[95],"framework.":[98],"Additionally,":[99],"curate":[101],"CelebV-Dub,":[102],"new":[104],"dataset":[105],"expressive,":[107],"real-world":[108],"videos":[109],"specifically":[110],"designed":[111],"dubbing.":[115],"Extensive":[116],"experiments":[117],"show":[118],"model":[121],"achieves":[122],"high-quality,":[123],"intelligible,":[124],"synthesis":[128],"accurate":[130],"lip":[131],"synchronization,":[132],"outperforming":[133],"existing":[134],"methods":[135],"human":[137],"perception":[138],"performing":[140],"favorably":[141],"objective":[143],"evaluations.":[144],"also":[146],"adapt":[147],"VoiceCraft-Dub":[148],"video-to-speech":[151],"task,":[152],"demonstrating":[153],"its":[154],"versatility":[155],"various":[157],"applications.":[158]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
