{"id":"https://openalex.org/W2105063344","doi":"https://doi.org/10.1109/icassp.2014.6854467","title":"Synthesizing real-time speech-driven facial animation","display_name":"Synthesizing real-time speech-driven facial animation","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2105063344","doi":"https://doi.org/10.1109/icassp.2014.6854467","mag":"2105063344"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854467","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 Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Changwei Luo","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, P.R.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, P.R.C","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, P.R.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, P.R.C","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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["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"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of intelligent machines, P.R.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of intelligent machines, P.R.C","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210159412"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4568","last_page":"4572"},"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":0.9991999864578247,"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":0.9944000244140625,"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":0.8438452482223511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5991562604904175},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5866289734840393},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5626930594444275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5259135961532593},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5182669162750244},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5011787414550781},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4838327467441559},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4771948754787445},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4518080949783325},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3615871071815491},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.1478291153907776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438452482223511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5991562604904175},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5866289734840393},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5626930594444275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5259135961532593},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5182669162750244},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5011787414550781},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4838327467441559},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4771948754787445},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4518080949783325},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3615871071815491},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.1478291153907776},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854467","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 Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W161296368","https://openalex.org/W1552213476","https://openalex.org/W1891702304","https://openalex.org/W1982854652","https://openalex.org/W1992187125","https://openalex.org/W2015081419","https://openalex.org/W2019083158","https://openalex.org/W2038891881","https://openalex.org/W2051434435","https://openalex.org/W2056696101","https://openalex.org/W2070726616","https://openalex.org/W2113774076","https://openalex.org/W2120605154","https://openalex.org/W2127211243","https://openalex.org/W2143640516","https://openalex.org/W2147885303","https://openalex.org/W2152754093","https://openalex.org/W2156034920","https://openalex.org/W2156142001","https://openalex.org/W2295661697","https://openalex.org/W3046645498","https://openalex.org/W6660126109"],"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":{"We":[0],"present":[1],"a":[2,78,116],"real-time":[3],"speech-driven":[4],"facial":[5,95],"animation":[6],"system.":[7],"In":[8],"this":[9,57],"system,":[10],"Gaussian":[11],"Mixture":[12],"Models":[13],"(GMM)":[14],"are":[15,88],"employed":[16],"to":[17,90,93,115],"perform":[18],"the":[19,27,49,65,69,75,84],"audio-to-visual":[20,82],"conversion.":[21],"The":[22,39,110],"conventional":[23],"GMM-based":[24],"method":[25,40],"performs":[26],"conversion":[28,66,70,111],"frame":[29,31],"by":[30],"using":[32],"minimum":[33],"mean":[34],"square":[35],"error":[36],"(MMSE)":[37],"estimation.":[38],"is":[41,72,113],"reasonably":[42],"effective.":[43],"However,":[44],"discontinuities":[45],"often":[46],"appear":[47],"in":[48,74,125],"sequences":[50],"of":[51,77],"estimated":[52,85],"visual":[53,62,86,108],"features.":[54,109],"To":[55],"solve":[56],"problem,":[58],"we":[59],"incorporate":[60],"previous":[61],"features":[63,87,106],"into":[64,107],"so":[67],"that":[68,99],"procedure":[71],"performed":[73],"manner":[76],"Markov":[79],"chain.":[80],"After":[81],"conversion,":[83],"transformed":[89],"blendshape":[91],"weights":[92],"synthesize":[94],"animation.":[96],"Experiments":[97],"show":[98],"our":[100,122],"system":[101,123],"can":[102],"accurately":[103],"convert":[104],"audio":[105],"accuracy":[112],"comparable":[114],"current":[117],"state-of-the-art":[118],"trajectory-based":[119],"approach.":[120],"Moreover,":[121],"runs":[124],"real":[126],"time":[127],"and":[128],"outputs":[129],"high":[130],"quality":[131],"lip-sync":[132],"animations.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}