{"id":"https://openalex.org/W90651302","doi":null,"title":"Two- and Three-Dimensional Audio-Visual Speech Synthesis.","display_name":"Two- and Three-Dimensional Audio-Visual Speech Synthesis.","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W90651302","mag":"90651302"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.399.215","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.399.215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/avsp98/av98_213.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5113323230","display_name":"N. Michael Brooke","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N. Michael Brooke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113465441","display_name":"Simon D. Scott","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon D. Scott","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3271,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.80036582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5077999830245972,"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":0.5077999830245972,"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":0.47850000858306885,"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/T12290","display_name":"Human Motion and Animation","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/audio-visual-speech-synthesis","display_name":"audio-visual speech synthesis","score":0.9950000047683716},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.4180000126361847},{"id":"https://openalex.org/keywords/facial-animation","display_name":"facial animation","score":0.6510000228881836},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.8130000233650208},{"id":"https://openalex.org/keywords/data-driven-synthesis","display_name":"data-driven synthesis","score":0.6420000195503235},{"id":"https://openalex.org/keywords/british-english","display_name":"British English","score":0.640999972820282},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.6060000061988831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331976294517517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839184165000916},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.594507098197937},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5394514203071594},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5387706756591797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5100601315498352},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.504073977470398},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.49805569648742676},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4897024929523468},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4446813464164734},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4426635503768921},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4271388649940491},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41698282957077026},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3700181841850281},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35041338205337524},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2869266867637634},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.14205387234687805},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.399.215","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.399.215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isca-speech.org/archive_open/archive_papers/avsp98/av98_213.pdf","raw_type":"text"},{"id":"mag:90651302","doi":null,"is_oa":false,"landing_page_url":"http://www.isca-speech.org/archive_open/archive_papers/avsp98/av98_213.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306503912","display_name":"AVSP","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"AVSP","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2002621203","https://openalex.org/W2124174353","https://openalex.org/W2128597598","https://openalex.org/W2133575725","https://openalex.org/W2171758405"],"related_works":["https://openalex.org/W7095718573","https://openalex.org/W2092760763","https://openalex.org/W7098015425","https://openalex.org/W1974439553","https://openalex.org/W1495185238","https://openalex.org/W2017071914","https://openalex.org/W2039649369","https://openalex.org/W7097837282","https://openalex.org/W7000855197","https://openalex.org/W2145377038"],"abstract_inverted_index":{"An":[0],"audio-visual":[1],"speech":[2,91,106,162],"synthesiser":[3,48],"has":[4],"been":[5],"built":[6],"that":[7,79],"will":[8],"generate":[9],"animated":[10],"computer-graphics":[11],"displays":[12,24],"of":[13,17,29,33,40,62,89,93,143,147],"high-resolution,":[14],"colour":[15],"images":[16,59],"a":[18,34,44,52,63,139,148,158],"speaker's":[19],"mouth":[20],"area.":[21],"The":[22,47],"visual":[23,161],"can":[25,118,135],"simulate":[26],"the":[27,30,82,90,100,105,111,128,144,152],"movements":[28],"lower":[31,145],"face":[32],"talker":[35],"for":[36,87],"any":[37],"spoken":[38],"sentence":[39],"British":[41,94],"English,":[42],"given":[43],"text":[45],"input.":[46],"is":[49,155],"based":[50],"on":[51],"data-driven":[53],"technique.":[54],"It":[55],"uses":[56],"encoded,":[57],"video-recorded":[58],"and":[60,84,124],"sounds":[61,83,92,107],"real":[64],"speaker":[65],"to":[66,114],"find":[67],"optimal":[68],"parameter":[69],"values":[70],"for,":[71],"or":[72],"'train',":[73],"hidden":[74],"Markov":[75],"models":[76],"(or":[77],"HMMs)":[78],"capture":[80],"both":[81],"facial":[85],"gestures":[86],"each":[88],"English.":[95],"To":[96],"synthesise":[97],"an":[98,122],"utterance,":[99],"trained":[101],"HMMs":[102],"associated":[103],"with":[104],"are":[108,132],"invoked":[109],"in":[110],"appropriate":[112],"sequence":[113],"produce":[115],"outputs":[116],"which":[117],"be":[119,136],"decoded":[120],"into":[121],"image":[123,130],"sound":[125],"sequence.":[126],"Whilst":[127],"basic":[129],"syntheses":[131],"two-dimensional,":[133],"they":[134],"pasted":[137],"onto":[138],"three-dimensional":[140,160],"wireframe":[141],"model":[142],"part":[146],"head,":[149],"which,":[150],"when":[151],"jaw":[153],"outline":[154],"adjusted,":[156],"produces":[157],"plausible":[159],"animation.":[163],"1.":[164]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}