{"id":"https://openalex.org/W2511870926","doi":"https://doi.org/10.21437/interspeech.2016-1084","title":"Visual Speech Synthesis Using Dynamic Visemes, Contextual Features and DNNs","display_name":"Visual Speech Synthesis Using Dynamic Visemes, Contextual Features and DNNs","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2511870926","doi":"https://doi.org/10.21437/interspeech.2016-1084","mag":"2511870926"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1084","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052815830","display_name":"Ausdang Thangthai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ausdang Thangthai","raw_affiliation_strings":["School of Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023076395","display_name":"Ben Milner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Milner","raw_affiliation_strings":["School of Computing Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101923852","display_name":"Sarah Taylor","orcid":"https://orcid.org/0000-0003-1299-0446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarah Taylor","raw_affiliation_strings":["Faculty of Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.338,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66474131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2458","last_page":"2462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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/T12290","display_name":"Human Motion and Animation","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.8413984775543213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7522976994514465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6536266803741455},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4696083962917328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.368858277797699},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.1677071750164032}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.8413984775543213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522976994514465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6536266803741455},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4696083962917328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.368858277797699},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.1677071750164032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2016-1084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1084","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:60485","is_oa":false,"landing_page_url":null,"pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"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":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W594764791","https://openalex.org/W1779294284","https://openalex.org/W1974357398","https://openalex.org/W1994396704","https://openalex.org/W2000911139","https://openalex.org/W2005030514","https://openalex.org/W2014240681","https://openalex.org/W2032693983","https://openalex.org/W2037042749","https://openalex.org/W2054665642","https://openalex.org/W2082308025","https://openalex.org/W2097398294","https://openalex.org/W2102003408","https://openalex.org/W2120067677","https://openalex.org/W2120654454","https://openalex.org/W2142487393","https://openalex.org/W2143072537","https://openalex.org/W2147885303","https://openalex.org/W2152826865","https://openalex.org/W2154920538","https://openalex.org/W2170429722","https://openalex.org/W2170849167","https://openalex.org/W2578930077","https://openalex.org/W3006295631","https://openalex.org/W4231109964","https://openalex.org/W4385483513"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W4253235840","https://openalex.org/W1559261064","https://openalex.org/W2124254345","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W2105537028","https://openalex.org/W131634123","https://openalex.org/W1910748333"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"methods":[3],"to":[4,53,77,134],"improve":[5],"visual":[6,79,88,139],"speech":[7],"synthesis":[8],"from":[9,49,60],"a":[10,14,61,112,144],"text":[11,24],"input":[12,23,73],"using":[13],"deep":[15],"neural":[16],"network":[17],"(DNN).":[18],"Two":[19],"representations":[20],"of":[21,86,126],"the":[22,54,75,84,99,120,124,127,138],"are":[25,40,58,72],"considered,":[26],"namely":[27],"into":[28,74,119],"phoneme":[29,100],"sequences":[30],"or":[31],"dynamic":[32,102],"viseme":[33,103,115],"sequences.":[34],"From":[35],"these":[36,87],"sequences,":[37],"contextual":[38],"features":[39,70,89,121],"extracted":[41,59],"that":[42,65,71,97],"include":[43],"information":[44,130],"at":[45],"varying":[46],"linguistic":[47],"levels,":[48],"frame":[50,128],"level":[51,129],"down":[52],"utterance":[55],"level.":[56],"These":[57],"broad":[62],"sliding":[63],"window":[64],"captures":[66],"context":[67],"and":[68,101,142,146],"produces":[69,143],"DNN":[76],"estimate":[78],"features.":[80],"Experiments":[81],"first":[82],"compare":[83],"accuracy":[85],"against":[90],"an":[91],"HMM":[92],"baseline":[93],"method":[94],"which":[95,131],"establishes":[96],"both":[98],"systems":[104],"perform":[105],"better":[106],"with":[107],"best":[108],"performance":[109],"obtained":[110],"by":[111],"combined":[113],"phoneme-dynamic":[114],"system.":[116],"An":[117],"investigation":[118],"then":[122],"reveals":[123],"importance":[125],"is":[132],"able":[133],"avoid":[135],"discontinuities":[136],"in":[137],"feature":[140],"sequence":[141],"smooth":[145],"realistic":[147],"output.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}