{"id":"https://openalex.org/W2156034920","doi":"https://doi.org/10.1109/afgr.2004.1301509","title":"Trainable videorealistic speech animation","display_name":"Trainable videorealistic speech animation","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2156034920","doi":"https://doi.org/10.1109/afgr.2004.1301509","mag":"2156034920"},"language":"en","primary_location":{"id":"doi:10.1109/afgr.2004.1301509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/afgr.2004.1301509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings.","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/A5052503160","display_name":"Tony Ezzat","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Ezzat","raw_affiliation_strings":["Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108376512","display_name":"Gad Geiger","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Geiger","raw_affiliation_strings":["Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001833084","display_name":"Tomaso Poggio","orcid":"https://orcid.org/0000-0002-3944-0455"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Poggio","raw_affiliation_strings":["Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Biological and Computational Learning, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.5723,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.99606112,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"64"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9980999827384949,"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":0.8385581970214844},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7772443294525146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6806684732437134},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.596809983253479},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.577095091342926},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5496991276741028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5225262641906738},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4777728319168091},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4680202901363373},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4627058804035187},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4373646378517151},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4361107051372528},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42789578437805176},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.32289013266563416},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.21862882375717163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385581970214844},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7772443294525146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6806684732437134},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.596809983253479},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.577095091342926},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5496991276741028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5225262641906738},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4777728319168091},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4680202901363373},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4627058804035187},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4373646378517151},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4361107051372528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42789578437805176},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.32289013266563416},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.21862882375717163},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/afgr.2004.1301509","is_oa":false,"landing_page_url":"https://doi.org/10.1109/afgr.2004.1301509","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W215849","https://openalex.org/W1493385272","https://openalex.org/W1496403746","https://openalex.org/W1496801689","https://openalex.org/W1532237134","https://openalex.org/W1541184751","https://openalex.org/W1544596136","https://openalex.org/W1554663460","https://openalex.org/W1554803342","https://openalex.org/W1571461735","https://openalex.org/W1578285471","https://openalex.org/W1578839297","https://openalex.org/W1589686977","https://openalex.org/W1608915237","https://openalex.org/W1623734550","https://openalex.org/W1652191854","https://openalex.org/W1693261796","https://openalex.org/W1778825358","https://openalex.org/W1818840701","https://openalex.org/W1873253341","https://openalex.org/W1938714998","https://openalex.org/W1950150365","https://openalex.org/W1996748132","https://openalex.org/W2001141328","https://openalex.org/W2013196554","https://openalex.org/W2029530604","https://openalex.org/W2046911213","https://openalex.org/W2070320140","https://openalex.org/W2082229127","https://openalex.org/W2097873612","https://openalex.org/W2098362450","https://openalex.org/W2099257899","https://openalex.org/W2100111806","https://openalex.org/W2103071307","https://openalex.org/W2103504761","https://openalex.org/W2103633133","https://openalex.org/W2120458329","https://openalex.org/W2128774947","https://openalex.org/W2132172443","https://openalex.org/W2133575725","https://openalex.org/W2137595331","https://openalex.org/W2139494788","https://openalex.org/W2141477623","https://openalex.org/W2142693409","https://openalex.org/W2144997437","https://openalex.org/W2146610201","https://openalex.org/W2147885303","https://openalex.org/W2149411062","https://openalex.org/W2151467704","https://openalex.org/W2161964681","https://openalex.org/W2165465341","https://openalex.org/W2167737187","https://openalex.org/W2172803778","https://openalex.org/W2216692653","https://openalex.org/W2236592196","https://openalex.org/W2237250383","https://openalex.org/W2293741035","https://openalex.org/W2295661697","https://openalex.org/W2296297070","https://openalex.org/W2428180336","https://openalex.org/W2751023760","https://openalex.org/W2752885492","https://openalex.org/W2861081890","https://openalex.org/W2888871578","https://openalex.org/W3003662786","https://openalex.org/W3004513510","https://openalex.org/W3102105445","https://openalex.org/W3145128584","https://openalex.org/W4231537718","https://openalex.org/W4233118564","https://openalex.org/W4285719527","https://openalex.org/W4298876635","https://openalex.org/W4388297464","https://openalex.org/W6632565788","https://openalex.org/W6634156485","https://openalex.org/W6636383877","https://openalex.org/W6640879616","https://openalex.org/W6676047094","https://openalex.org/W6680688070","https://openalex.org/W6682319494","https://openalex.org/W6682634897"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W615219140","https://openalex.org/W2999276620","https://openalex.org/W4232411666","https://openalex.org/W1978243811","https://openalex.org/W2906438086","https://openalex.org/W1564870812","https://openalex.org/W2096968018","https://openalex.org/W3040900128"],"abstract_inverted_index":{"We":[0],"describe":[1],"how":[2],"to":[3,107],"create":[4],"with":[5],"machine":[6],"learning":[7],"techniques":[8],"a":[9,23,28,37,73,95,121],"generative,":[10],"videorealistic,":[11],"and":[12,80],"speech":[13,30,39],"animation":[14],"module.":[15],"A":[16],"human":[17,52],"subject":[18],"is":[19,41,47,70,86],"first":[20],"recorded":[21,62],"using":[22],"videocamera":[24],"as":[25,124,126],"he/she":[26],"utters":[27],"pre-determined":[29],"corpus.":[31],"After":[32],"processing":[33],"the":[34,44,51,64,89,100,105,108],"corpus":[35],"automatically,":[36],"visual":[38],"module":[40],"learned":[42],"from":[43],"data":[45],"that":[46,59,91],"capable":[48],"of":[49,99],"synthesizing":[50],"subject's":[53],"mouth":[54],"uttering":[55],"entirely":[56],"novel":[57],"utterances":[58],"were":[60],"not":[61],"in":[63,88],"original":[65],"video.":[66],"The":[67,83],"synthesized":[68],"utterance":[69],"re-composited":[71],"onto":[72],"background":[74],"sequence,":[75],"which":[76],"contains":[77],"natural":[78],"head":[79],"eye":[81],"movement.":[82],"final":[84],"output":[85],"videorealistic":[87],"sense":[90],"it":[92],"looks":[93],"like":[94],"video":[96],"camera":[97],"recording":[98],"subject.":[101],"At":[102],"run":[103],"time,":[104],"input":[106],"system":[109],"can":[110],"be":[111],"either":[112],"real":[113],"audio":[114,118],"sequences":[115],"or":[116],"synthetic":[117],"produced":[119],"by":[120],"text-to-speech":[122],"system,":[123],"long":[125],"they":[127],"have":[128],"been":[129],"phonetically":[130],"aligned.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}