{"id":"https://openalex.org/W2136813256","doi":"https://doi.org/10.1109/icme.2003.1221366","title":"Using viseme based acoustic models for speech driven lip synthesis","display_name":"Using viseme based acoustic models for speech driven lip synthesis","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2136813256","doi":"https://doi.org/10.1109/icme.2003.1221366","mag":"2136813256"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5101423308","display_name":"Ashish Verma","orcid":"https://orcid.org/0009-0007-3427-3196"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"A. Verma","raw_affiliation_strings":["IBM India Research Lab, Indian Institute of Technology, New Delhi"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Indian Institute of Technology, New Delhi","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109086475","display_name":"Nitendra Rajput","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"N. Rajput","raw_affiliation_strings":["IBM India Research Lab, Indian Institute of Technology, New Delhi","IBM India Research Laboratory, Indian Institute of Technology, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Indian Institute of Technology, New Delhi","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM India Research Laboratory, Indian Institute of Technology, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110205806","display_name":"L. V. Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"L.V. Subramaniam","raw_affiliation_strings":["IBM India Research Lab, Indian Institute of Technology, New Delhi","IBM India Research Laboratory, Indian Institute of Technology, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IBM India Research Lab, Indian Institute of Technology, New Delhi","institution_ids":["https://openalex.org/I4210103279"]},{"raw_affiliation_string":"IBM India Research Laboratory, Indian Institute of Technology, New Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101423308"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":0.2928,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.59201306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9894999861717224,"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/viseme","display_name":"Viseme","score":0.9360687732696533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7530744075775146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6880444288253784},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6746996641159058},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6218484044075012},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.583479642868042},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5740785598754883},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47132542729377747},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.46608632802963257},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42134207487106323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3619436025619507},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07473194599151611}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9360687732696533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530744075775146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6880444288253784},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6746996641159058},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6218484044075012},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.583479642868042},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5740785598754883},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47132542729377747},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.46608632802963257},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42134207487106323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619436025619507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07473194599151611},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1221366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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":15,"referenced_works":["https://openalex.org/W59318173","https://openalex.org/W1521793179","https://openalex.org/W2002591263","https://openalex.org/W2013153079","https://openalex.org/W2031080503","https://openalex.org/W2067031273","https://openalex.org/W2120458329","https://openalex.org/W2138778418","https://openalex.org/W2140565496","https://openalex.org/W2147885303","https://openalex.org/W2148376462","https://openalex.org/W2155658135","https://openalex.org/W2169265436","https://openalex.org/W4255959360","https://openalex.org/W6602419912"],"related_works":["https://openalex.org/W2401811665","https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2124254345","https://openalex.org/W2105537028","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2092406870"],"abstract_inverted_index":{"Speech":[0],"drive":[1],"lip":[2,93],"synthesis":[3,94],"is":[4,17,29],"an":[5],"interesting":[6],"and":[7,77,83,127],"important":[8],"step":[9],"toward":[10],"human-computer":[11],"interaction.":[12],"An":[13],"incoming":[14],"speech":[15,22,70,91],"signal":[16],"time":[18],"aligned":[19],"using":[20],"a":[21,44,85],"recognizer":[23],"to":[24,32,36,66,105,134],"generate":[25],"phonetic":[26],"sequence,":[27,52],"which":[28,53],"then":[30],"converted":[31],"corresponding":[33],"viseme":[34,51,55],"sequence":[35],"be":[37],"animated.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"present":[43],"novel":[45],"method":[46,117],"for":[47],"generation":[48],"of":[49,60,79,89,102],"the":[50,68,80,90,100,115],"uses":[54],"based":[56,63],"acoustic":[57,64,103],"models,":[58,65],"instead":[59],"usual":[61],"phone":[62],"align":[67],"input":[69],"signal.":[71],"This":[72],"results":[73,118],"in":[74,119,124,131],"higher":[75],"accuracy":[76,126],"speed":[78],"alignment":[81],"procedure":[82],"allows":[84],"much":[86],"simpler":[87],"implementation":[88],"driven":[92],"system":[95],"as":[96],"it":[97],"completely":[98],"obviates":[99],"requirement":[101],"unit":[104,107],"visual":[106],"conversion.":[108],"We":[109],"show":[110],"through":[111],"various":[112],"experiments":[113],"that":[114],"proposed":[116],"about":[120,128],"53%":[121],"relative":[122],"improvement":[123],"classification":[125],"52%":[129],"reduction":[130],"time,":[132],"required":[133],"compute":[135],"alignments.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}