{"id":"https://openalex.org/W4415541217","doi":"https://doi.org/10.1145/3746027.3754734","title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","display_name":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541217","doi":"https://doi.org/10.1145/3746027.3754734"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5008914315","display_name":"Gaoxiang Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":"Gaoxiang Cong","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1239-8119","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420654","display_name":"Liang Li","orcid":"https://orcid.org/0000-0002-1943-8219"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1943-8219","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100581018","display_name":"Jiadong Pan","orcid":"https://orcid.org/0000-0002-4436-8830"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"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":"Jiadong Pan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4436-8830","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000086710","display_name":"Z L Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhedong Zhang","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-1129-8914","affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056293251","display_name":"Amin Beheshti","orcid":"https://orcid.org/0000-0002-5988-5494"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Amin Beheshti","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5988-5494","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028024287","display_name":"Anton van den Hengel","orcid":"https://orcid.org/0000-0003-3027-8364"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anton van den Hengel","raw_affiliation_strings":["University of Adelaide, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3027-8364","affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070842891","display_name":"Yuankai Qi","orcid":"https://orcid.org/0000-0003-4312-5682"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuankai Qi","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4312-5682","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qingming Huang","orcid":"https://orcid.org/0009-0006-8793-6953"},"institutions":[{"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":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8793-6953","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/scripting-language","display_name":"Scripting language","score":0.4713999927043915},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.4284000098705292},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4221000075340271},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.3921999931335449},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3630000054836273},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.3361000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805899977684021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.640999972820282},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.4284000098705292},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4146000146865845},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.3921999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.26739999651908875},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2747874407","https://openalex.org/W3161480375","https://openalex.org/W4323897324","https://openalex.org/W4392172931","https://openalex.org/W4403791995"],"related_works":[],"abstract_inverted_index":{"Movie":[0],"Dubbing":[1],"aims":[2],"to":[3,113,164],"convert":[4],"scripts":[5,120],"into":[6],"speeches":[7],"that":[8,176],"align":[9],"with":[10,88,143],"the":[11,23,38,44,106,115,125,136,155],"given":[12,28],"movie":[13,119],"clip":[14],"in":[15],"both":[16],"temporal":[17],"and":[18,48,67,79,121],"emotional":[19],"aspects":[20],"while":[21,42,92],"preserving":[22],"vocal":[24],"timbre":[25],"of":[26,46,108],"a":[27,57,83],"brief":[29],"reference":[30,122],"audio.":[31,123],"Existing":[32],"methods":[33,182],"focus":[34],"primarily":[35],"on":[36,62,130,183],"reducing":[37],"word":[39],"error":[40],"rate":[41],"ignoring":[43],"importance":[45],"lip-sync":[47],"acoustic":[49,94],"quality.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55,102],"propose":[56],"novel":[58],"dubbing":[59],"architecture":[60],"based":[61],"Large":[63],"Language":[64],"Model":[65],"(LLM)":[66],"Conditional":[68],"Flow":[69],"Matching":[70],"(CFM),":[71],"named":[72],"FlowDubber,":[73],"which":[74,139],"achieves":[75],"high-quality":[76],"audio-visual":[77],"sync":[78],"pronunciation":[80],"by":[81,167],"incorporating":[82],"large":[84,109],"speech":[85,110],"language":[86,111],"model":[87,112],"dual":[89],"contrastive":[90],"alignment":[91,142],"improving":[93],"quality":[95],"via":[96,149],"Flow-based":[97],"Voice":[98],"Enhancing":[99],"(FVE).":[100],"First,":[101],"introduce":[103],"Qwen2.5":[104],"as":[105],"backbone":[107],"learn":[114],"in-context":[116],"sequence":[117],"from":[118,146],"Second,":[124],"proposed":[126],"semantic-aware":[127],"learning":[128],"focuses":[129],"capturing":[131],"LLM":[132],"semantic":[133],"knowledge":[134],"at":[135,191],"phoneme":[137],"level,":[138],"facilitates":[140],"mutual":[141],"lip":[144],"movement":[145],"silent":[147],"video":[148],"Dual":[150],"Contrastive":[151],"Alignment":[152],"(DCA).":[153],"Third,":[154],"FVE":[156],"introduces":[157],"an":[158],"LLM-based":[159],"acoustics":[160],"flow":[161],"matching":[162],"guidance":[163],"strengthen":[165],"clarity":[166],"decoupling":[168],"Classifier-Free":[169],"Guidance":[170],"(CFG)":[171],"enhancement.":[172],"Extensive":[173],"experiments":[174],"demonstrate":[175],"our":[177],"method":[178],"outperforms":[179],"several":[180],"state-of-the-art":[181],"two":[184],"primary":[185],"benchmarks.":[186],"The":[187],"demos":[188],"are":[189],"available":[190],"https://galaxycong.github.io/LLM-Flow-Dubber/.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
