{"id":"https://openalex.org/W142945732","doi":"https://doi.org/10.21437/interspeech.2004-424","title":"AVICAR: audio-visual speech corpus in a car environment","display_name":"AVICAR: audio-visual speech corpus in a car environment","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W142945732","doi":"https://doi.org/10.21437/interspeech.2004-424","mag":"142945732"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5089545632","display_name":"Bowon Lee","orcid":"https://orcid.org/0000-0001-5417-5699"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bowon Lee","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077548822","display_name":"Camille Goudeseune","orcid":"https://orcid.org/0000-0003-3530-8577"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Camille Goudeseune","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073215512","display_name":"Suketu Kamdar","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suketu Kamdar","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050462311","display_name":"Sarah Borys","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Borys","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347820","display_name":"Ming Liu","orcid":"https://orcid.org/0000-0002-9981-0454"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Liu","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I4400573203","display_name":"Nature Inspires Creativity Engineers Lab","ror":"https://ror.org/02bczqy30","country_code":null,"type":"facility","lineage":["https://openalex.org/I201841394","https://openalex.org/I4400573203"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Huang","raw_affiliation_strings":["Coordinated Science Lab"],"affiliations":[{"raw_affiliation_string":"Coordinated Science Lab","institution_ids":["https://openalex.org/I4400573203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5089545632"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":4.2864,"has_fulltext":false,"cited_by_count":177,"citation_normalized_percentile":{"value":0.94208656,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9886999726295471,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7677354216575623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7534992694854736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5989902019500732},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.43305331468582153},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3588145971298218},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3523334264755249},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2701873779296875}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7677354216575623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534992694854736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5989902019500732},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.43305331468582153},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3588145971298218},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3523334264755249},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2701873779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2004-424","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.194.4724","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.194.4724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isl.uiuc.edu/Publications/Lee_et_al.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.3.5160","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.3.5160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.uiuc.edu/speech/pubs/2004/Lee_et_al.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W39021006","https://openalex.org/W151018310","https://openalex.org/W1515932869","https://openalex.org/W1568712909","https://openalex.org/W1799381022","https://openalex.org/W1862597247","https://openalex.org/W1967558850","https://openalex.org/W2004405928","https://openalex.org/W2015394094","https://openalex.org/W2017055088","https://openalex.org/W2040714103","https://openalex.org/W2045956438","https://openalex.org/W2072083949","https://openalex.org/W2075350645","https://openalex.org/W2083792893","https://openalex.org/W2098923380","https://openalex.org/W2101609516","https://openalex.org/W2116418373","https://openalex.org/W2121486117","https://openalex.org/W2144244295","https://openalex.org/W2154912038","https://openalex.org/W2158541934","https://openalex.org/W2891180535"],"related_works":["https://openalex.org/W2122924390","https://openalex.org/W2559040841","https://openalex.org/W2131711534","https://openalex.org/W114661351","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,9,28],"large":[3],"audio-visual":[4],"speech":[5],"corpus":[6,50,113],"recorded":[7],"in":[8,64],"car":[10],"environment,":[11],"as":[12,14],"well":[13],"the":[15,36,44,49,82],"equipment":[16],"and":[17,39,61,75,100,102,110],"procedures":[18],"used":[19],"to":[20,80],"build":[21],"this":[22],"corpus.":[23],"Data":[24],"are":[25,71],"collected":[26],"through":[27,116],"multi-sensory":[29],"array":[30],"consisting":[31],"of":[32,52],"eight":[33],"microphones":[34],"on":[35,43],"sun":[37],"visor":[38],"four":[40,53],"video":[41],"cameras":[42],"dashboard.":[45],"The":[46,112],"script":[47,86],"for":[48],"consists":[51],"categories:":[54],"isolated":[55,57],"digits,":[56],"letters,":[58],"phone":[59],"numbers,":[60],"sentences,":[62],"all":[63],"English.":[65],"Speakers":[66],"from":[67],"various":[68],"language":[69],"backgrounds":[70],"included,":[72],"50":[73,76],"male":[74],"female.":[77],"In":[78],"order":[79],"vary":[81],"signal-to-noise":[83],"ratio,":[84],"each":[85],"has":[87],"five":[88],"different":[89],"noise":[90],"conditions:":[91],"idling,":[92],"driving":[93,103],"at":[94,104],"35":[95],"mph":[96,106],"with":[97,107],"windows":[98,108],"open":[99,109],"closed,":[101],"55":[105],"closed.":[111],"is":[114],"available":[115]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
