{"id":"https://openalex.org/W2089114070","doi":"https://doi.org/10.1109/icassp.2013.6639244","title":"Speaker-independent lips and tongue visualization of vowels","display_name":"Speaker-independent lips and tongue visualization of vowels","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2089114070","doi":"https://doi.org/10.1109/icassp.2013.6639244","mag":"2089114070"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5100348588","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-4019-3420"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027059634","display_name":"Minghao Yang","orcid":"https://orcid.org/0000-0003-3243-0569"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Yang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4089,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8302106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8106","last_page":"8110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9763000011444092,"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/visualization","display_name":"Visualization","score":0.8078494071960449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426257133483887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6324694752693176},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.5875932574272156},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5366427898406982},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4335757791996002},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4144185483455658},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.337161123752594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33283478021621704},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.16324564814567566},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11796656250953674},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07256695628166199}],"concepts":[{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.8078494071960449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426257133483887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6324694752693176},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.5875932574272156},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5366427898406982},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4335757791996002},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4144185483455658},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.337161123752594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33283478021621704},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.16324564814567566},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11796656250953674},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07256695628166199},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W46785905","https://openalex.org/W275819404","https://openalex.org/W1525807100","https://openalex.org/W2019083158","https://openalex.org/W2019977809","https://openalex.org/W2031698970","https://openalex.org/W2032662392","https://openalex.org/W2037042749","https://openalex.org/W2055115647","https://openalex.org/W2056387890","https://openalex.org/W2134539847","https://openalex.org/W2141697795","https://openalex.org/W3014296750","https://openalex.org/W6601897821","https://openalex.org/W6609917237","https://openalex.org/W6631452893"],"related_works":["https://openalex.org/W3136794468","https://openalex.org/W2367950022","https://openalex.org/W4310844315","https://openalex.org/W2365707941","https://openalex.org/W2366141844","https://openalex.org/W2383946220","https://openalex.org/W2358428239","https://openalex.org/W3011636953","https://openalex.org/W2532377291","https://openalex.org/W2351206852"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,13],"scheme":[4],"of":[5,53,68,83,91],"speech-driven":[6],"lips":[7,33,69,84],"and":[8,34,70,78,85],"tongue":[9,35,71,86],"animation":[10],"synthesis":[11],"in":[12,111],"speaker-independent":[14],"manner.":[15],"Directional":[16],"relative":[17],"displacement":[18],"(DRD)":[19],"features":[20],"are":[21,38,55,108],"proposed":[22],"based":[23],"on":[24],"the":[25,45,59,75,79,104],"Electromagnetic":[26],"Articulograph":[27],"(EMA)":[28],"data":[29,52],"to":[30,57],"describe":[31],"human's":[32],"movements,":[36],"which":[37],"more":[39],"stable":[40],"across":[41],"different":[42],"speakers":[43],"than":[44],"raw":[46],"EMA":[47],"data.":[48],"Multi":[49],"speakers'":[50],"acoustic-articulatory":[51],"vowels":[54,92],"used":[56],"learn":[58],"acoustic-toarticulatory":[60],"inversion":[61],"mapping.":[62],"We":[63],"build":[64],"2D":[65],"geometric":[66,80],"models":[67],"for":[72],"visualization.":[73],"With":[74],"trained":[76],"mapping":[77],"models,":[81],"visualization":[82],"movements":[87],"from":[88],"acoustic":[89],"signal":[90],"uttered":[93],"by":[94],"arbitrary":[95],"speaker":[96],"is":[97],"realized.":[98],"The":[99],"experimental":[100],"results":[101],"demonstrate":[102],"that":[103],"animations":[105],"we":[106],"synthesized":[107],"effective":[109],"aids":[110],"helping":[112],"people":[113],"identifying":[114],"vowels.":[115]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
