{"id":"https://openalex.org/W2296650210","doi":"https://doi.org/10.21437/interspeech.2013-629","title":"A new language independent, photo-realistic talking head driven by voice only","display_name":"A new language independent, photo-realistic talking head driven by voice only","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2296650210","doi":"https://doi.org/10.21437/interspeech.2013-629","mag":"2296650210"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-629","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100608027","display_name":"Xinjian Zhang","orcid":"https://orcid.org/0009-0000-2940-3928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinjian Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018012012","display_name":"Gang Li","orcid":"https://orcid.org/0000-0002-8573-1608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank K. Soong","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":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2743","last_page":"2747"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9988999962806702,"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/T10057","display_name":"Face and Expression Recognition","score":0.9696000218391418,"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":0.7957464456558228},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7018639445304871},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.568632185459137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5419143438339233},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5069677829742432},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.4913538992404938},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47284868359565735},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45389389991760254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.421160489320755},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.0708707869052887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7957464456558228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7018639445304871},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.568632185459137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5419143438339233},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5069677829742432},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4913538992404938},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47284868359565735},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45389389991760254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421160489320755},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0708707869052887},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-629","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W36879466","https://openalex.org/W44815768","https://openalex.org/W217970951","https://openalex.org/W1498436455","https://openalex.org/W1520448186","https://openalex.org/W1547376871","https://openalex.org/W1998263688","https://openalex.org/W2004789217","https://openalex.org/W2008353316","https://openalex.org/W2046588080","https://openalex.org/W2070726616","https://openalex.org/W2121922650","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2160070749","https://openalex.org/W2160306971","https://openalex.org/W2163334800","https://openalex.org/W3129048579"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,28],"new":[3,24],"photo-realistic,":[4],"voice":[5,14],"driven":[6],"only":[7],"(i.e.":[8],"no":[9],"linguistic":[10],"info":[11],"of":[12,22,41],"the":[13,23,77,88,100,115,142,162],"input":[15,57,164],"is":[16,27,36,50,74,111],"needed)":[17],"talking":[18,25,67],"head.":[19],"The":[20,47,120],"core":[21],"head":[26],"context-dependent,":[29],"multilayer,":[30],"Deep":[31],"Neural":[32],"Network":[33],"(DNN),":[34],"which":[35],"discriminatively":[37],"trained":[38,48,75,122],"over":[39,76],"hundreds":[40],"hours,":[42],"speaker":[43,125],"independent":[44,126],"speech":[45,56,96],"data.":[46],"DNN":[49,98,116,121],"then":[51,112],"used":[52],"to":[53,58,87,140,167],"map":[54],"acoustic":[55],"9,000":[59],"tied":[60],"\u201csenone\u201d":[61],"states":[62,83,102],"probabilistically.":[63],"For":[64],"each":[65],"photo-realistic":[66,108,166],"head,":[68],"an":[69],"HMM-based":[70],"lips":[71,90,109,143],"motion":[72],"synthesizer":[73],"speaker\u2019s":[78],"audio/visual":[79],"training":[80],"data":[81,127],"where":[82],"are":[84,158],"statistically":[85],"mapped":[86],"corresponding":[89],"images.":[91],"In":[92],"test,":[93],"for":[94,154],"given":[95],"input,":[97,135],"predicts":[99],"likely":[101],"in":[103],"their":[104],"posterior":[105],"probabilities":[106],"and":[107,165],"animation":[110],"rendered":[113,153],"through":[114],"predicted":[117],"state":[118],"lattice.":[119],"on":[123],"English,":[124],"has":[128],"also":[129],"been":[130],"tested":[131],"with":[132,161],"other":[133],"language":[134],"e.g.":[136],"Mandarin,":[137],"Spanish,":[138],"etc.":[139],"mimic":[141],"movements":[144],"cross-lingually.":[145],"Subjective":[146],"experiments":[147],"show":[148],"that":[149],"lip":[150],"motions":[151],"thus":[152],"15":[155],"non-English":[156],"languages":[157],"highly":[159],"synchronized":[160],"audio":[163],"human":[168],"eyes":[169],"perceptually.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
