{"id":"https://openalex.org/W2098923380","doi":"https://doi.org/10.1109/icassp.2002.5745028","title":"CUAVE: A new audio-visual database for multimodal human-computer interface research","display_name":"CUAVE: A new audio-visual database for multimodal human-computer interface research","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2098923380","doi":"https://doi.org/10.1109/icassp.2002.5745028","mag":"2098923380"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5101982814","display_name":"Eric Patterson","orcid":"https://orcid.org/0009-0005-6953-032X"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E.K. Patterson","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109745287","display_name":"S. Gurbuz","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Gurbuz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087689483","display_name":"Zekeriya T\u00dcFEKC\u0130","orcid":"https://orcid.org/0000-0001-7835-2741"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Z. Tufekci","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034808001","display_name":"J.N. Gowdy","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.N. Gowdy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"[Dept of Electrical and Computer Eng, Clemson University, SC 29634, USA]","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101982814"],"corresponding_institution_ids":["https://openalex.org/I8078737"],"apc_list":null,"apc_paid":null,"fwci":5.2762,"has_fulltext":false,"cited_by_count":288,"citation_normalized_percentile":{"value":0.96834902,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2017"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music 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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8213049173355103},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6441079378128052},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.622441828250885},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6079289317131042},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6039537191390991},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4679946303367615},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4361085891723633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4200173020362854},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4101729094982147},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3640002906322479},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.1802975833415985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213049173355103},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6441079378128052},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.622441828250885},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6079289317131042},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6039537191390991},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4679946303367615},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4361085891723633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4200173020362854},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4101729094982147},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3640002906322479},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.1802975833415985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5745028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745028","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.6375","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.6375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.clemson.edu/speech/papers/cuave.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W98035269","https://openalex.org/W1514361649","https://openalex.org/W1527240141","https://openalex.org/W1554901277","https://openalex.org/W1959749536","https://openalex.org/W1964178275","https://openalex.org/W1975270274","https://openalex.org/W2021279213","https://openalex.org/W2106137268","https://openalex.org/W2106284211","https://openalex.org/W2118977726","https://openalex.org/W2130602224","https://openalex.org/W2133906911","https://openalex.org/W2142518644","https://openalex.org/W2399996702","https://openalex.org/W3099202502","https://openalex.org/W6604012948","https://openalex.org/W6631618440","https://openalex.org/W6679442541","https://openalex.org/W6681081894","https://openalex.org/W6712207287"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4238262908","https://openalex.org/W4214489098","https://openalex.org/W46679383"],"abstract_inverted_index":{"Multimodal":[0],"signal":[1],"processing":[2],"has":[3,58],"become":[4],"an":[5,182],"important":[6,148],"topic":[7],"of":[8,14,99,103,127,133,150,156,158,165,171],"research":[9,180],"for":[10,63,65,131],"overcoming":[11],"certain":[12],"problems":[13],"audio-only":[15],"speech":[16,19],"processing.":[17],"Audio-visual":[18],"recognition":[20],"is":[21,79,95,110,153,174],"one":[22,90],"area":[23],"with":[24],"great":[25],"potential.":[26],"Difficulties":[27],"due":[28],"to":[29,51,72,87,112,175],"background":[30],"noise":[31],"and":[32,81,106,137],"multiple":[33],"speakers":[34],"are":[35,117,125],"significantly":[36],"reduced":[37],"by":[38,43],"the":[39,128,134,141,151,154,161],"additional":[40],"information":[41,187],"provided":[42],"extra":[44],"visual":[45],"features.":[46],"Despite":[47],"a":[48,61,74,96],"few":[49],"efforts":[50],"create":[52],"databases":[53],"in":[54,119,140],"this":[55,120,166,172],"area,":[56],"none":[57],"emerged":[59],"as":[60,144],"standard":[62],"comparison":[64],"several":[66,114],"possible":[67],"reasons.":[68],"This":[69],"paper":[70],"seeks":[71],"introduce":[73],"new":[75],"audiovisual":[76],"database":[77,94,152,164],"that":[78,116],"flexible":[80],"fairly":[82],"comprehensive,":[83],"yet":[84],"easily":[85,183],"available":[86,184],"researchers":[88],"on":[89,188],"DVD.":[91],"The":[92,122,168],"CUAVE":[93],"speaker-independent":[97],"corpus":[98],"over":[100],"7,000":[101],"utterances":[102],"both":[104],"connected":[105],"isolated":[107],"digits.":[108],"It":[109],"designed":[111],"meet":[113],"goals":[115],"discussed":[118],"paper.":[121],"most":[123],"notable":[124],"availability":[126],"database,":[129],"flexibility":[130],"use":[132],"audio-visual":[135,179],"data,":[136],"realistic":[138],"considerations":[139],"recordings":[142],"(such":[143],"speaker":[145],"movement).":[146],"Another":[147],"focus":[149],"inclusion":[155],"pairs":[157],"simultaneous":[159],"speakers,":[160],"first":[162],"documented":[163],"kind.":[167],"overall":[169],"goal":[170],"project":[173],"facilitate":[176],"more":[177],"widespread":[178],"through":[181],"database.":[185],"For":[186],"obtaining":[189],"CUAVE,":[190],"please":[191],"visit":[192],"our":[193],"webpage":[194],"(http://ece.clemson.edu/speech).":[195]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":15}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
