{"id":"https://openalex.org/W2119325976","doi":"https://doi.org/10.1109/icme.2001.1237847","title":"Real time speech driven facial animation using formant analysis","display_name":"Real time speech driven facial animation using formant analysis","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2119325976","doi":"https://doi.org/10.1109/icme.2001.1237847","mag":"2119325976"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","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/A5043926363","display_name":"Zhen Wen","orcid":"https://orcid.org/0000-0001-9780-6876"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Wen","raw_affiliation_strings":["Beckman Institute, Urbana-Champaign, IL, USA","Beckman Inst"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Inst","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033168441","display_name":"Pengyu Hong","orcid":"https://orcid.org/0000-0002-3177-2754"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengyu Hong","raw_affiliation_strings":["Beckman Institute, Urbana-Champaign, IL, USA","Beckman Institute, Urbana, Illinois 61801, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, Urbana, Illinois 61801, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Beckman Institute, Urbana-Champaign, IL, USA","Beckman Institute, Urbana, Illinois 61801, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, Urbana, Illinois 61801, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043926363"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.7221,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.77629323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"817","last_page":"820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T12290","display_name":"Human Motion and Animation","score":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.9617671966552734},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800750732421875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.645936906337738},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6037817001342773},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5317935347557068},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4929952323436737},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46479055285453796},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45074301958084106},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.44292616844177246},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4400302767753601},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43229344487190247},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.42475032806396484},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3816450834274292},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22775337100028992},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12144643068313599},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.0863078236579895}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9617671966552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800750732421875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.645936906337738},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6037817001342773},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5317935347557068},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4929952323436737},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46479055285453796},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45074301958084106},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.44292616844177246},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4400302767753601},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43229344487190247},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.42475032806396484},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3816450834274292},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22775337100028992},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12144643068313599},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0863078236579895},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2001.1237847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W160985744","https://openalex.org/W1504187604","https://openalex.org/W1539516100","https://openalex.org/W1866024993","https://openalex.org/W2013806171","https://openalex.org/W2069501481","https://openalex.org/W2071193054","https://openalex.org/W2115276447","https://openalex.org/W2140565496","https://openalex.org/W2295661697","https://openalex.org/W6606539960","https://openalex.org/W6630153011","https://openalex.org/W6632225258"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2025848302","https://openalex.org/W2894697037","https://openalex.org/W1975454382"],"abstract_inverted_index":{"Formant":[0],"analysis":[1,9],"is":[2,36,72,85,100,111,129,138],"a":[3,17,40],"technique":[4],"widely":[5],"used":[6,73,86],"for":[7,23,113],"speech":[8,26],"and":[10,20,69,102],"synthesis.":[11],"In":[12,65,132],"this":[13],"paper,":[14],"we":[15],"present":[16],"simple,":[18],"fast":[19],"effective":[21],"method":[22,99,121,137],"real":[24,114],"time":[25,115],"driven":[27],"facial":[28],"animation":[29],"based":[30],"on":[31,106],"formant":[32,41],"analysis.":[33],"Speech":[34],"signal":[35],"first":[37],"processed":[38],"by":[39],"analyzer.":[42],"Since":[43,119],"the":[44,56,76,120,135],"resulting":[45],"formants":[46,57],"are":[47],"known":[48],"to":[49,62,74,87,141],"be":[50,59],"correlated":[51],"with":[52,94],"vocal":[53],"tract":[54],"shape,":[55],"can":[58],"directly":[60],"mapped":[61],"mouth":[63,77,82,123],"shapes.":[64],"addition,":[66],"median":[67],"filter":[68],"energy":[70],"modulation":[71],"smooth":[75],"shape":[78,83],"sequence.":[79],"The":[80,97],"smoothed":[81],"sequence":[84],"animate":[88],"our":[89],"synthetic":[90],"3D":[91],"head":[92],"model":[93],"synchronized":[95],"audio.":[96],"proposed":[98,136],"simple":[101],"does":[103],"not":[104],"rely":[105],"contextual":[107],"information.":[108],"Thus":[109],"it":[110,128],"good":[112],"two-way":[116],"communication":[117],"applications.":[118],"extracts":[122],"shapes":[124],"from":[125],"acoustic":[126],"features,":[127],"language":[130],"independent.":[131],"speaker-independent":[133],"case,":[134],"also":[139],"shown":[140],"work":[142],"well.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}