{"id":"https://openalex.org/W2132774916","doi":"https://doi.org/10.1109/cvpr.2003.1211404","title":"Improving continuous gesture recognition with spoken prosody","display_name":"Improving continuous gesture recognition with spoken prosody","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2132774916","doi":"https://doi.org/10.1109/cvpr.2003.1211404","mag":"2132774916"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2003.1211404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2003.1211404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.","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/A5058998065","display_name":"S. Kettebekov","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Kettebekov","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069645522","display_name":"Mohammed Yeasin","orcid":"https://orcid.org/0000-0003-0579-3030"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Yeasin","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812502","display_name":"Rajeev Sharma","orcid":"https://orcid.org/0000-0002-3354-558X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Sharma","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Pennsylvania State University  University Park PA USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058998065"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.9174,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76298972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2254","issue":null,"first_page":"I","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/T12031","display_name":"Speech and dialogue systems","score":0.9876000285148621,"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/gesture","display_name":"Gesture","score":0.8325174450874329},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7597659826278687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7567741870880127},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.7470207810401917},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6856268048286438},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5330549478530884},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48812946677207947},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4437950849533081},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4239826798439026}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8325174450874329},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7597659826278687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567741870880127},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.7470207810401917},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6856268048286438},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5330549478530884},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48812946677207947},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4437950849533081},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4239826798439026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2003.1211404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2003.1211404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W147554451","https://openalex.org/W164929510","https://openalex.org/W1555356986","https://openalex.org/W1556135330","https://openalex.org/W1570018840","https://openalex.org/W1864566053","https://openalex.org/W1922942272","https://openalex.org/W1935857547","https://openalex.org/W1974555773","https://openalex.org/W1990191258","https://openalex.org/W2015478238","https://openalex.org/W2118244636","https://openalex.org/W2120701504","https://openalex.org/W2125838338","https://openalex.org/W2134518303","https://openalex.org/W2135643110","https://openalex.org/W2156927436","https://openalex.org/W2166954095","https://openalex.org/W4248137600","https://openalex.org/W4285719527","https://openalex.org/W6605944733","https://openalex.org/W6633358753","https://openalex.org/W6633498899","https://openalex.org/W6634159548","https://openalex.org/W6639220162","https://openalex.org/W6640355936","https://openalex.org/W6677576504"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2028966255","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2466763065","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W1994032303"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,26,46,117,122],"gesture":[4,39,52,82,94,191],"recognition,":[5,53],"reliance":[6],"on":[7,97,162],"the":[8,64,157,168,187],"visual":[9],"signal":[10,115],"alone":[11],"to":[12,37,50,143,176],"classify":[13],"unrestricted":[14],"continuous":[15,93,190],"gesticulation":[16,22],"is":[17,23,61,134],"inherently":[18],"error-prone.":[19],"Since":[20],"spontaneous":[21,81],"mostly":[24],"coverbal":[25],"nature,":[27],"there":[28],"have":[29,43],"been":[30,44],"some":[31],"attempts":[32,42],"of":[33,58,66,80,108,140,146,156,189],"using":[34,47,128,136],"speech":[35,48,84,149],"cues":[36,49],"improve":[38,51],"recognition.":[40,192],"Some":[41],"made":[45],"e.g.,":[54],"keyword-gesture":[55],"co-analysis.":[56],"Use":[57],"such":[59],"scheme":[60],"burdened":[62],"by":[63,76,179],"complexity":[65],"natural":[67],"language":[68],"understanding.":[69],"This":[70],"paper":[71],"offers":[72],"a":[73,88,137,163],"\"signal-level\"":[74],"perspective":[75],"exploring":[77],"prosodic":[78,109],"phenomena":[79,99],"and":[83,104,151],"co-production.":[85],"We":[86],"present":[87],"computational":[89],"framework":[90,127],"for":[91],"improving":[92],"recognition":[95],"based":[96],"two":[98],"that":[100],"capture":[101],"voluntary":[102],"(co-articulation)":[103],"involuntary":[105],"(physiological)":[106],"contributions":[107],"synchronization.":[110],"Physiological":[111],"constraints,":[112],"manifested":[113],"as":[114],"interruptions":[116],"multimodal":[118,164],"production,":[119],"are":[120],"exploited":[121],"an":[123],"audio-visual":[124],"feature":[125],"integration":[126],"hidden":[129],"Markov":[130],"models":[131],"(HMMs).":[132],"Co-articulation":[133],"analyzed":[135],"Bayesian":[138],"network":[139],"naive":[141],"classifiers":[142],"explore":[144],"alignment":[145],"intonationally":[147],"prominent":[148],"segments":[150],"hand":[152],"kinematics.":[153],"The":[154],"efficacy":[155],"proposed":[158],"approach":[159],"was":[160],"demonstrated":[161],"corpus":[165],"created":[166],"from":[167],"Weather":[169],"Channel":[170],"broadcast.":[171],"Both":[172],"schemas":[173],"were":[174],"found":[175],"contribute":[177],"uniquely":[178],"reducing":[180],"different":[181],"error":[182],"types,":[183],"which":[184],"subsequently":[185],"improves":[186],"performance":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
