{"id":"https://openalex.org/W1548212376","doi":"https://doi.org/10.1109/icassp.2015.7178903","title":"A mouth full of words: Visually consistent acoustic redubbing","display_name":"A mouth full of words: Visually consistent acoustic redubbing","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1548212376","doi":"https://doi.org/10.1109/icassp.2015.7178903","mag":"1548212376"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/56081/1/main.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101923852","display_name":"Sarah Taylor","orcid":"https://orcid.org/0000-0003-1299-0446"},"institutions":[{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Taylor","raw_affiliation_strings":["Disney Research, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112911728","display_name":"Barry-John Theobald","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]},{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Barry-John Theobald","raw_affiliation_strings":["Disney Research, Pittsburgh, PA","University of East Anglia, Norwich, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069055807","display_name":"Iain Matthews","orcid":"https://orcid.org/0009-0000-5004-2397"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]},{"id":"https://openalex.org/I4210142140","display_name":"Walt Disney (United States)","ror":"https://ror.org/04eg47h42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142140"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Iain Matthews","raw_affiliation_strings":["Disney Research, Pittsburgh, PA","University of East Anglia, Norwich, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, PA","institution_ids":["https://openalex.org/I4210142140"]},{"raw_affiliation_string":"University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4904","last_page":"4908"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8071367740631104},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.786490797996521},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7504579424858093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6987056136131287},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5674577355384827},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5097014904022217},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47441595792770386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4282628297805786},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4263703525066376},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.4197376072406769},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4154629111289978},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39584898948669434},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30169183015823364},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2763095498085022},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.14479312300682068},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11907336115837097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071367740631104},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.786490797996521},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7504579424858093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6987056136131287},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5674577355384827},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5097014904022217},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47441595792770386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4282628297805786},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4263703525066376},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.4197376072406769},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4154629111289978},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39584898948669434},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30169183015823364},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2763095498085022},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.14479312300682068},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11907336115837097},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:56081","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/56081/1/main.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"Book Section"}],"best_oa_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:56081","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/56081/1/main.pdf","source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"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":"Book Section"},"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1548212376.pdf","grobid_xml":"https://content.openalex.org/works/W1548212376.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1574832834","https://openalex.org/W1597533204","https://openalex.org/W2000911139","https://openalex.org/W2006482757","https://openalex.org/W2013699441","https://openalex.org/W2040454151","https://openalex.org/W2045933515","https://openalex.org/W2071096833","https://openalex.org/W2071828724","https://openalex.org/W2080416463","https://openalex.org/W2083050334","https://openalex.org/W2087964571","https://openalex.org/W2096651761","https://openalex.org/W2337732708","https://openalex.org/W2394527494","https://openalex.org/W2400566389","https://openalex.org/W4243764915","https://openalex.org/W4255959360","https://openalex.org/W6635726886","https://openalex.org/W6650605322","https://openalex.org/W6674569219","https://openalex.org/W6703684149","https://openalex.org/W6711842774"],"related_works":["https://openalex.org/W1483367581","https://openalex.org/W2374130674","https://openalex.org/W2993446842","https://openalex.org/W2008308193","https://openalex.org/W2399356099","https://openalex.org/W2128790081","https://openalex.org/W3184167880","https://openalex.org/W2189097844","https://openalex.org/W2403379316","https://openalex.org/W3080941136"],"abstract_inverted_index":{"This":[0,107],"paper":[1],"introduces":[2],"a":[3,30,42,56,64],"method":[4],"for":[5,97,119],"automatic":[6,120],"redubbing":[7],"of":[8,15,44,67,85,126],"video":[9],"that":[10,48,70,90],"exploits":[11],"the":[12,33,51,75,83,86,110,124],"many-to-many":[13],"mapping":[14],"phoneme":[16,46],"sequences":[17,47,69],"to":[18,40],"lip":[19],"movements":[20],"modelled":[21],"as":[22,100],"dynamic":[23,35],"visemes":[24,94],"(Taylor":[25],"et":[26],"al.,":[27],"2012).":[28],"For":[29],"given":[31],"utterance,":[32],"corresponding":[34],"viseme":[36],"sequence":[37],"is":[38],"sampled":[39],"construct":[41],"graph":[43],"possible":[45],"synchronize":[49],"with":[50,55,74],"video.":[52],"When":[53],"composed":[54],"pronunciation":[57],"dictionary":[58],"and":[59,116,123],"language":[60,127],"model,":[61],"this":[62,98],"produces":[63],"vast":[65],"number":[66],"word":[68,105],"are":[71],"in":[72,113],"sync":[73],"original":[76],"video,":[77],"literally":[78],"putting":[79],"plausible":[80],"words":[81],"into":[82],"mouth":[84],"speaker.":[87],"We":[88],"demonstrate":[89],"traditional,":[91],"many-to-one,":[92],"static":[93],"lack":[95],"flexibility":[96],"application":[99],"they":[101],"produce":[102],"significantly":[103],"fewer":[104],"sequences.":[106],"work":[108],"explores":[109],"natural":[111],"ambiguity":[112],"visual":[114],"speech":[115,121],"offers":[117],"insight":[118],"recognition":[122],"importance":[125],"modeling.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
