{"id":"https://openalex.org/W2092890371","doi":"https://doi.org/10.1145/2342896.2342997","title":"3D human head geometry estimation from a speech","display_name":"3D human head geometry estimation from a speech","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2092890371","doi":"https://doi.org/10.1145/2342896.2342997","mag":"2092890371"},"language":"en","primary_location":{"id":"doi:10.1145/2342896.2342997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2342896.2342997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGGRAPH 2012 Posters on - SIGGRAPH '12","raw_type":"proceedings-article"},"type":"conference-abstract","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/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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.9994999766349792,"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":0.998199999332428,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6341172456741333},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5966670513153076},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5597001910209656},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5266953706741333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5203351974487305},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42267823219299316},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.41399139165878296},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.40545541048049927},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.38513004779815674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3411688804626465},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08389830589294434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6341172456741333},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5966670513153076},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5597001910209656},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5266953706741333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5203351974487305},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42267823219299316},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.41399139165878296},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.40545541048049927},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.38513004779815674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411688804626465},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08389830589294434},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2342896.2342997","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2342896.2342997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGGRAPH 2012 Posters on - SIGGRAPH '12","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2165880886","https://openalex.org/W2168722300"],"related_works":["https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W2060888333","https://openalex.org/W2053092242","https://openalex.org/W2028342517","https://openalex.org/W3042758298","https://openalex.org/W2050311283","https://openalex.org/W2942435052","https://openalex.org/W3169184738","https://openalex.org/W2007544974"],"abstract_inverted_index":{"We":[0],"can":[1,43],"visualize":[2],"acquaintances'":[3],"appearance":[4],"by":[5,156,188],"just":[6],"hearing":[7],"their":[8],"voice":[9,29,71,210],"if":[10],"we":[11,42,110,132,148,197],"have":[12,60,92],"met":[13],"them":[14],"in":[15,27],"past":[16],"few":[17,94],"years.":[18],"Thus,":[19],"it":[20],"would":[21],"appear":[22],"that":[23,199],"some":[24,45],"relationships":[25],"exist":[26],"between":[28,66,99,160],"and":[30,72,81,102,128,170,191],"appearance.":[31],"If":[32],"3D":[33,104,114,145,171,178,200],"head":[34,105,115,146,172,201],"geometry":[35,116,173,202],"could":[36,211],"be":[37,212],"estimated":[38,213],"from":[39,117,166],"a":[40,64,70,88,97,118,125,134,150,158,167,177,195],"voice,":[41],"realize":[44],"applications":[46],"(e.g,":[47],"avatar":[48],"generation,":[49],"character":[50],"modeling":[51],"for":[52],"video":[53],"game,":[54],"etc.).":[55],"Previously,":[56],"although":[57],"many":[58],"researchers":[59],"been":[61,93],"reported":[62],"about":[63,96],"relationship":[65,98],"acoustic":[67,100,163],"features":[68,77,101,121,164],"of":[69,183],"its":[73,129],"corresponding":[74],"dynamical":[75],"visual":[76],"including":[78],"lip,":[79],"tongue,":[80],"jaw":[82],"movements":[83],"or":[84],"vocal":[85],"articulation":[86],"during":[87],"speech,":[89],"however,":[90],"there":[91],"reports":[95],"static":[103],"geometry.":[106],"In":[107],"this":[108,141],"paper,":[109],"focus":[111],"on":[112,124,176],"estimating":[113],"voice.":[119],"Acoustic":[120],"vary":[122],"depending":[123],"speech":[126],"context":[127,135],"intonation.":[130],"Therefore":[131],"restrict":[133],"to":[136,143,207],"Japanese":[137,168],"5":[138],"vowels.":[139],"Under":[140],"assumption,":[142],"estimate":[144],"geometry,":[147],"use":[149],"Feedforward":[151],"Neural":[152],"Network":[153],"(FNN)":[154],"trained":[155],"using":[157],"correspondence":[159],"an":[161,208],"individual":[162],"extracted":[165],"vowel":[169],"generated":[174],"based":[175],"range":[179],"scan.":[180],"The":[181],"performance":[182],"our":[184],"method":[185],"is":[186,204],"shown":[187],"both":[189],"closed":[190],"open":[192],"tests.":[193],"As":[194],"result,":[196],"found":[198],"which":[203],"acoustically":[205],"similar":[206],"input":[209],"under":[214],"the":[215],"limited":[216],"condition.":[217]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
