{"id":"https://openalex.org/W2515372520","doi":"https://doi.org/10.21437/interspeech.2016-483","title":"Audio-to-Visual Speech Conversion Using Deep Neural Networks","display_name":"Audio-to-Visual Speech Conversion Using Deep Neural Networks","publication_year":2016,"publication_date":"2016-08-28","ids":{"openalex":"https://openalex.org/W2515372520","doi":"https://doi.org/10.21437/interspeech.2016-483","mag":"2515372520"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ueaeprints.uea.ac.uk/id/eprint/60483/1/Accepted_manuscript.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/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":"Sarah Taylor","raw_affiliation_strings":["] University of East Anglia, Norwich, UK [","Disney Research, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"] University of East Anglia, Norwich, UK [","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"Disney Research, Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059038393","display_name":"Akihiro Kato","orcid":"https://orcid.org/0000-0002-5796-2310"},"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":"Akihiro Kato","raw_affiliation_strings":["] University of East Anglia, Norwich, UK [","Disney Research, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"] University of East Anglia, Norwich, UK [","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"Disney Research, Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069055807","display_name":"Iain Matthews","orcid":"https://orcid.org/0009-0000-5004-2397"},"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":"Iain Matthews","raw_affiliation_strings":["Disney Research, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Disney Research, Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","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":"Ben Milner","raw_affiliation_strings":["] University of East Anglia, Norwich, UK [","Disney Research, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"] University of East Anglia, Norwich, UK [","institution_ids":["https://openalex.org/I1118541"]},{"raw_affiliation_string":"Disney Research, Pittsburgh, USA","institution_ids":["https://openalex.org/I4210142140"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0631,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92430372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1482","last_page":"1486"},"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/T11309","display_name":"Music 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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7588643431663513},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6474040746688843},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6007720232009888},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.568506121635437},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45799240469932556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3567558526992798},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.260700523853302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588643431663513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6474040746688843},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6007720232009888},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.568506121635437},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45799240469932556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3567558526992798},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.260700523853302}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2016-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:60483","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/60483/1/Accepted_manuscript.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":"NonPeerReviewed"}],"best_oa_location":{"id":"pmh:oai:ueaeprints.uea.ac.uk:60483","is_oa":true,"landing_page_url":null,"pdf_url":"https://ueaeprints.uea.ac.uk/id/eprint/60483/1/Accepted_manuscript.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":"NonPeerReviewed"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G455538984","display_name":null,"funder_award_id":"EP/M014053/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2515372520.pdf","grobid_xml":"https://content.openalex.org/works/W2515372520.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W161296368","https://openalex.org/W1527240141","https://openalex.org/W1544978329","https://openalex.org/W1547376871","https://openalex.org/W1554803342","https://openalex.org/W1569907127","https://openalex.org/W1665214252","https://openalex.org/W2000911139","https://openalex.org/W2004789217","https://openalex.org/W2014168246","https://openalex.org/W2015143272","https://openalex.org/W2027324763","https://openalex.org/W2070726616","https://openalex.org/W2082308025","https://openalex.org/W2083792893","https://openalex.org/W2097998348","https://openalex.org/W2098923380","https://openalex.org/W2105055531","https://openalex.org/W2110501904","https://openalex.org/W2120067677","https://openalex.org/W2120654454","https://openalex.org/W2129360799","https://openalex.org/W2147885303","https://openalex.org/W2152826865","https://openalex.org/W2157190406","https://openalex.org/W2157986450","https://openalex.org/W2296650210","https://openalex.org/W2401811665","https://openalex.org/W2969945254","https://openalex.org/W3143803406","https://openalex.org/W4385483513"],"related_works":["https://openalex.org/W2386387936","https://openalex.org/W2331065455","https://openalex.org/W2778699561","https://openalex.org/W1629725936","https://openalex.org/W82246966","https://openalex.org/W477036574","https://openalex.org/W2083580856","https://openalex.org/W1530111162","https://openalex.org/W90026711","https://openalex.org/W2164714623"],"abstract_inverted_index":{"We":[0,27,69],"study":[1],"the":[2,12],"problem":[3],"of":[4,14,42,48,87],"mapping":[5,38],"from":[6,22,39,51],"acoustic":[7,43],"to":[8,45,62],"visual":[9,49,58],"speech":[10,19,25,55,67],"with":[11],"goal":[13],"generating":[15],"accurate,":[16],"perceptually":[17],"natural":[18],"animation":[20],"automatically":[21],"an":[23],"audio":[24],"signal.":[26],"present":[28],"a":[29,37,40,46,52,71,84],"sliding":[30],"window":[31,41,47],"deep":[32],"neural":[33],"network":[34],"that":[35],"learns":[36],"features":[44,50],"large":[53],"audio-visual":[54],"dataset.":[56],"Overlapping":[57],"predictions":[59],"are":[60],"averaged":[61],"generate":[63],"continuous,":[64],"smoothly":[65],"varying":[66],"animation.":[68],"outperform":[70],"baseline":[72],"HMM":[73],"inversion":[74],"approach":[75],"in":[76],"both":[77],"objective":[78],"and":[79,82],"subjective":[80],"evaluations":[81],"perform":[83],"thorough":[85],"analysis":[86],"our":[88],"results.":[89]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
