{"id":"https://openalex.org/W2014240681","doi":"https://doi.org/10.1109/icmew.2014.6890554","title":"Realtime speech-driven facial animation using Gaussian Mixture Models","display_name":"Realtime speech-driven facial animation using Gaussian Mixture Models","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2014240681","doi":"https://doi.org/10.1109/icmew.2014.6890554","mag":"2014240681"},"language":"en","primary_location":{"id":"doi:10.1109/icmew.2014.6890554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2014.6890554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5091503481","display_name":"Changwei Luo","orcid":"https://orcid.org/0000-0002-3107-7022"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changwei Luo","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607986","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-8636-2421"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210159412","display_name":"Intelligent Machines (Sweden)","ror":"https://ror.org/05nzk9q32","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210159412"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China","Institute of intelligent machines, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of intelligent machines, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210159412","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091503481"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.1645,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7833912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9932000041007996,"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":0.8635952472686768},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7173066735267639},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6240062713623047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5970757007598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5717712640762329},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5481089949607849},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5151466131210327},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5118710398674011},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47147539258003235},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4481453597545624},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4117588996887207},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.37599241733551025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3665871024131775},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.13263919949531555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8635952472686768},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7173066735267639},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6240062713623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5970757007598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5717712640762329},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5481089949607849},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5151466131210327},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5118710398674011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47147539258003235},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4481453597545624},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4117588996887207},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.37599241733551025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3665871024131775},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.13263919949531555},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew.2014.6890554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2014.6890554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W161296368","https://openalex.org/W1552213476","https://openalex.org/W1982854652","https://openalex.org/W1992187125","https://openalex.org/W2000359198","https://openalex.org/W2019083158","https://openalex.org/W2038891881","https://openalex.org/W2097711399","https://openalex.org/W2152754093","https://openalex.org/W2156142001","https://openalex.org/W2157986450","https://openalex.org/W2163512471","https://openalex.org/W3006295631","https://openalex.org/W3046645498","https://openalex.org/W6660126109","https://openalex.org/W6684075110"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W2535923857","https://openalex.org/W3094080214","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Synthesizing":[0],"speech-driven":[1,25,152],"facial":[2,26,153],"animation":[3,154],"is":[4,21,77,136],"the":[5,14,22,46,63,67,99,112,146,156],"process":[6],"of":[7,24,69],"animating":[8],"a":[9,104,117,139,151],"virtual":[10],"face":[11],"according":[12],"to":[13,62,110,138],"input":[15],"audio":[16,128],"signal.":[17],"Actually,":[18],"audio-to-visual":[19,38],"conversion":[20,47,85,106,134],"core":[23],"animation.":[27],"In":[28],"this":[29],"paper,":[30],"Gaussian":[31],"Mixture":[32],"Models":[33],"(GMM)":[34],"are":[35,86],"employed":[36],"for":[37],"conversion.":[39,100],"The":[40,133],"conventional":[41,64],"GMM":[42,82,113],"based":[43,108],"method":[44,124],"performs":[45],"frame":[48,50],"by":[49],"using":[51],"minimum":[52,105],"mean":[53],"square":[54],"error":[55,107],"estimation.":[56],"We":[57,101],"consider":[58],"two":[59],"issues":[60],"related":[61],"method:":[65],"1)":[66],"influence":[68],"previous":[70,95],"visual":[71,75,96,131],"features":[72,97,129],"on":[73,116,145],"current":[74,140],"feature":[76],"not":[78],"considered,":[79],"and":[80,84,162],"2)":[81],"training":[83],"inconsistent.":[87],"To":[88],"address":[89],"these":[90],"issues,":[91],"we":[92,149],"propose":[93,103],"incorporating":[94],"into":[98,130],"also":[102],"approach":[109],"refine":[111],"parameters.":[114],"Experiments":[115],"public":[118],"available":[119],"database":[120],"show":[121],"that":[122],"our":[123],"can":[125],"accurately":[126],"convert":[127],"features.":[132],"accuracy":[135],"comparable":[137],"state-of-the-art":[141],"trajectory-based":[142],"approach.":[143],"Based":[144],"proposed":[147],"method,":[148],"develop":[150],"system,":[155],"system":[157],"runs":[158],"in":[159],"real":[160],"time":[161],"outputs":[163],"realistic":[164],"speech":[165],"animations.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
