{"id":"https://openalex.org/W2067746823","doi":"https://doi.org/10.1145/2503385.2503388","title":"Efficient speech animation synthesis with vocalic lip shapes","display_name":"Efficient speech animation synthesis with vocalic lip shapes","publication_year":2013,"publication_date":"2013-07-16","ids":{"openalex":"https://openalex.org/W2067746823","doi":"https://doi.org/10.1145/2503385.2503388","mag":"2067746823"},"language":"en","primary_location":{"id":"doi:10.1145/2503385.2503388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503385.2503388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGGRAPH 2013 Posters","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/A5014402129","display_name":"Daisuke Mima","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Mima","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082120612","display_name":"Akinobu Maejima","orcid":"https://orcid.org/0000-0002-8005-9218"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinobu Maejima","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083427215","display_name":"Shigeo Morishima","orcid":"https://orcid.org/0000-0001-8859-6539"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeo Morishima","raw_affiliation_strings":["Waseda University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16717502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9979000091552734,"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/T12290","display_name":"Human Motion and Animation","score":0.9829999804496765,"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/computer-science","display_name":"Computer science","score":0.7689580917358398},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.738400936126709},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6770129203796387},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.5789217948913574},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5581877827644348},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.537697434425354},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5098839998245239},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5039731860160828},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4890643060207367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4703129827976227},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3713759183883667},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3666185438632965},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.07031020522117615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689580917358398},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.738400936126709},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6770129203796387},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.5789217948913574},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5581877827644348},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.537697434425354},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5098839998245239},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5039731860160828},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4890643060207367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4703129827976227},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3713759183883667},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3666185438632965},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.07031020522117615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2503385.2503388","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503385.2503388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGGRAPH 2013 Posters","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W72347498","https://openalex.org/W2000911139","https://openalex.org/W2007907868"],"related_works":["https://openalex.org/W2401811665","https://openalex.org/W1974357398","https://openalex.org/W2295574089","https://openalex.org/W2055569256","https://openalex.org/W4241846838","https://openalex.org/W4234707920","https://openalex.org/W2087756952","https://openalex.org/W3133492806","https://openalex.org/W136487047","https://openalex.org/W2166970146"],"abstract_inverted_index":{"Computer-generated":[0],"speech":[1,54,63],"animations":[2],"are":[3,72],"commonly":[4],"seen":[5],"in":[6],"video":[7,51],"games":[8],"and":[9,35],"movies.":[10],"Although":[11],"high-quality":[12],"facial":[13],"motions":[14,82,118],"can":[15,78],"be":[16],"created":[17],"by":[18,90],"the":[19,107,115],"hand":[20],"crafted":[21],"work":[22],"of":[23,33,53,69,94,119],"skilled":[24],"artists,":[25],"this":[26],"approach":[27,40],"is":[28,110],"not":[29,111],"always":[30],"suitable":[31],"because":[32],"time":[34],"cost":[36],"constraints.":[37],"A":[38],"data-driven":[39],"[Taylor":[41],"et":[42,103],"al.":[43,104],"2012],":[44],"such":[45],"as":[46],"machine":[47],"learning":[48],"to":[49,60],"concatenate":[50],"portions":[52],"training":[55],"data,":[56],"has":[57],"been":[58],"utilized":[59],"generate":[61],"natural":[62],"animation,":[64],"while":[65],"a":[66],"large":[67],"number":[68],"target":[70],"shapes":[71,86,96],"often":[73],"required":[74],"for":[75,87],"synthesis.":[76],"We":[77],"obtain":[79],"smooth":[80],"mouth":[81],"from":[83,114],"prepared":[84],"lip":[85,95,117],"typical":[88],"vowels":[89],"using":[91],"an":[92],"interpolation":[93],"with":[97],"Gaussian":[98],"mixture":[99],"models":[100],"(GMMs)":[101],"[Yano":[102],"2007].":[105],"However,":[106],"resulting":[108],"animation":[109],"directly":[112],"generated":[113],"measured":[116],"someone's":[120],"actual":[121],"speech.":[122]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}