{"id":"https://openalex.org/W4413054264","doi":"https://doi.org/10.1109/tpami.2025.3597267","title":"Dubbing Movies via Hierarchical Phoneme Modeling and Acoustic Diffusion Denoising","display_name":"Dubbing Movies via Hierarchical Phoneme Modeling and Acoustic Diffusion Denoising","publication_year":2025,"publication_date":"2025-08-08","ids":{"openalex":"https://openalex.org/W4413054264","doi":"https://doi.org/10.1109/tpami.2025.3597267","pmid":"https://pubmed.ncbi.nlm.nih.gov/40779382"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3597267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3597267","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"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":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8437-4824","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, 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/A5008914315","display_name":"Gaoxiang Cong","orcid":null},"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":"Gaoxiang Cong","raw_affiliation_strings":["Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1239-8119","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Information Processing, 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/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":["School of Computing, Macquarie University, Sydney, NSW, Australia","Macqurie University, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4312-5682","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Macqurie University, Sydney, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-2510-8993","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104085728","display_name":"Qi Wu","orcid":"https://orcid.org/0009-0001-7744-7906"},"institutions":[{"id":"https://openalex.org/I4210127558","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82","country_code":"AU","type":"facility","lineage":["https://openalex.org/I4210127558"]},{"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":"Qi Wu","raw_affiliation_strings":["Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]},{"raw_affiliation_string":"Australian Institute for Machine Learning (AIML), School of Computer Science, The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I4210127558","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080744092","display_name":"Quan Z. Sheng","orcid":"https://orcid.org/0000-0002-3326-4147"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"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","CN"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["School of Computing, Macquarie University, Sydney, NSW, Australia","University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-3326-4147","affiliations":[{"raw_affiliation_string":"School of Computing, Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"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":["School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7542-296X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Hsuan Yang","raw_affiliation_strings":["EECS, University of California at Merced, Merced, CA, USA","EECS, University of California at Merced, Merced, USA"],"raw_orcid":"https://orcid.org/0000-0003-4848-2304","affiliations":[{"raw_affiliation_string":"EECS, University of California at Merced, Merced, CA, USA","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"EECS, University of California at Merced, Merced, USA","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":3,"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":0.21300049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"47","issue":"11","first_page":"10361","last_page":"10377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9842000007629395,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9793999791145325,"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":0.8368141651153564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7827476263046265},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6258327960968018},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5179345011711121},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4844377338886261},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.4554741382598877},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4268847405910492},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.42532432079315186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40354323387145996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368141651153564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7827476263046265},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6258327960968018},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5179345011711121},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4844377338886261},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.4554741382598877},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4268847405910492},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.42532432079315186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40354323387145996},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009040","descriptor_name":"Motion Pictures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010700","descriptor_name":"Phonetics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D014741","descriptor_name":"Video Recording","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3597267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3597267","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40779382","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40779382","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2127141656","https://openalex.org/W2133665775","https://openalex.org/W2166563626","https://openalex.org/W2593414223","https://openalex.org/W2747874407","https://openalex.org/W2760103357","https://openalex.org/W2890952074","https://openalex.org/W2963307811","https://openalex.org/W2963524571","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2997540646","https://openalex.org/W3016011581","https://openalex.org/W3035626590","https://openalex.org/W3046890131","https://openalex.org/W3093287838","https://openalex.org/W3095019822","https://openalex.org/W3095545636","https://openalex.org/W3158762648","https://openalex.org/W3161959914","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3189347889","https://openalex.org/W3196584150","https://openalex.org/W3204420730","https://openalex.org/W3207628370","https://openalex.org/W3216942228","https://openalex.org/W3216976702","https://openalex.org/W4240592325","https://openalex.org/W4285019302","https://openalex.org/W4294068600","https://openalex.org/W4294435344","https://openalex.org/W4297841574","https://openalex.org/W4304099317","https://openalex.org/W4313065316","https://openalex.org/W4327662218","https://openalex.org/W4360884927","https://openalex.org/W4372263908","https://openalex.org/W4372269797","https://openalex.org/W4375868850","https://openalex.org/W4379929801","https://openalex.org/W4382464561","https://openalex.org/W4385245566","https://openalex.org/W4385822362","https://openalex.org/W4386057728","https://openalex.org/W4386072021","https://openalex.org/W4387540674","https://openalex.org/W4387934928","https://openalex.org/W4389383543","https://openalex.org/W4389519587","https://openalex.org/W4391020683","https://openalex.org/W4391164079","https://openalex.org/W4392761692","https://openalex.org/W4392931432","https://openalex.org/W4402683936","https://openalex.org/W4404781855"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036"],"abstract_inverted_index":{"Given":[0],"a":[1,5,111,195,205,208],"piece":[2],"of":[3,61,255],"text,":[4],"video":[6,35,71,93,185],"clip,":[7],"and":[8,30,39,124,146,176,178,216,229,239,262],"reference":[9,28,217],"audio,":[10],"the":[11,34,53,57,62,143,158,190,201,224,230,247,252,256,270],"movie":[12,113],"dubbing":[13,114],"(also":[14],"known":[15],"as":[16,137],"Visual":[17],"Voice":[18],"Cloning,":[19],"V2C)":[20],"task":[21],"aims":[22],"to":[23,73,84,96,173,199,235,269],"generate":[24],"speeches":[25],"that":[26],"clone":[27],"voice":[29],"align":[31,52],"well":[32],"with":[33,56,157],"in":[36],"both":[37],"emotion":[38],"lip":[40,59,155],"movement,":[41],"which":[42,116],"is":[43],"more":[44],"challenging":[45],"than":[46,103],"conventional":[47],"text-to-speech":[48],"synthesis":[49],"tasks.":[50],"To":[51,105],"generated":[54],"speech":[55,86,148,159],"inherent":[58],"motion":[60],"given":[63],"silent":[64],"video,":[65],"most":[66],"existing":[67],"works":[68],"utilize":[69],"each":[70,163],"frame":[72],"query":[74],"textual":[75,214],"phonemes.":[76],"However,":[77],"such":[78],"an":[79],"attention":[80],"operation":[81],"usually":[82],"leads":[83],"mumble":[85],"because":[87],"different":[88],"phonemes":[89,215],"are":[90,101],"fused":[91],"for":[92],"frames":[94,100],"corresponding":[95,147],"one":[97],"phoneme":[98,164],"(video":[99],"finer-grained":[102],"phonemes).":[104],"address":[106],"this":[107],"issue,":[108],"we":[109],"propose":[110],"diffusion-based":[112],"architecture,":[115],"improves":[117],"pronunciation":[118,241],"by":[119,166],"Hierarchical":[120],"Phoneme":[121],"Modeling":[122],"(HPM)":[123],"generates":[125],"better":[126],"mel-spectrogram":[127,206],"through":[128],"Acoustic":[129],"Diffusion":[130],"Denoising":[131],"(ADD).":[132],"We":[133],"term":[134],"our":[135,140],"model":[136],"HD-Dubber.":[138],"Specifically,":[139],"HPM":[141],"bridges":[142],"visual":[144],"information":[145],"prosody":[149],"from":[150,184],"three":[151,248],"aspects:":[152],"(1)":[153],"aligning":[154],"movement":[156],"duration":[160],"based":[161],"on":[162,213,246],"unit":[165],"contrastive":[167],"learning;":[168],"(2)":[169],"conveying":[170],"facial":[171],"expression":[172],"phoneme-level":[174],"energy":[175],"pitch;":[177],"(3)":[179],"injecting":[180],"global":[181],"emotions":[182],"captured":[183],"scenes":[186],"into":[187,204],"prosody.":[188],"On":[189],"other":[191],"hand,":[192],"ADD":[193,219],"exploits":[194],"denoising":[196],"diffusion":[197],"framework":[198],"transform":[200],"noise":[202],"signal":[203],"via":[207],"parameterized":[209],"Markov":[210],"chain":[211],"conditioned":[212],"audio.":[218],"has":[220],"two":[221],"novel":[222],"denoisers,":[223],"Style-adaptive":[225],"Residual":[226],"Denoiser":[227,233],"(SRD)":[228],"Phoneme-enhanced":[231],"U-net":[232],"(PUD),":[234],"enhance":[236],"speaker":[237],"similarity":[238],"improve":[240],"quality.":[242],"Extensive":[243],"experimental":[244],"results":[245],"benchmark":[249],"datasets":[250],"demonstrate":[251],"state-of-the-art":[253],"performance":[254],"proposed":[257],"method.":[258],"The":[259],"source":[260],"code":[261],"trained":[263],"models":[264],"will":[265],"be":[266],"made":[267],"available":[268],"public.":[271]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
