{"id":"https://openalex.org/W4392909592","doi":"https://doi.org/10.1109/icassp48485.2024.10446901","title":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","display_name":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909592","doi":"https://doi.org/10.1109/icassp48485.2024.10446901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5015193961","display_name":"Jeongkyun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeongkyun Park","raw_affiliation_strings":["Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050870658","display_name":"Jung-Wook Hwang","orcid":"https://orcid.org/0000-0002-6112-5523"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Wook Hwang","raw_affiliation_strings":["Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023799668","display_name":"Kwanghee Choi","orcid":"https://orcid.org/0000-0001-5254-1093"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwanghee Choi","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA,15213"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017457774","display_name":"Seung-Hyeon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Hyeon Lee","raw_affiliation_strings":["Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040588643","display_name":"Jun Hwan Ahn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Hwan Ahn","raw_affiliation_strings":["Mindslab Inc.,Gyeonggi-do,Republic of Korea,13493"],"affiliations":[{"raw_affiliation_string":"Mindslab Inc.,Gyeonggi-do,Republic of Korea,13493","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027304168","display_name":"Rae\u2010Hong Park","orcid":"https://orcid.org/0000-0002-4792-2980"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Rae-Hong Park","raw_affiliation_strings":["Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107","ICT Convergence Disaster/Safety Research Institute, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Electronic Engineering,Seoul,Republic of Korea,04107","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"ICT Convergence Disaster/Safety Research Institute, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031280750","display_name":"Hyung\u2010Min Park","orcid":"https://orcid.org/0000-0002-7105-5493"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Min Park","raw_affiliation_strings":["Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107","ICT Convergence Disaster/Safety Research Institute, Sogang University, Seoul, Republic of Korea","Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Artificial Intelligence,Seoul,Republic of Korea,04107","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"ICT Convergence Disaster/Safety Research Institute, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5015193961"],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":1.4942,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80703539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6385","last_page":"6389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8458999991416931,"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":0.8458999991416931,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7767999768257141,"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/computer-science","display_name":"Computer science","score":0.8085482120513916},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6994711756706238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6501909494400024},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5850696563720703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40846776962280273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38711386919021606},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18054306507110596},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.060502052307128906},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06021338701248169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085482120513916},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6994711756706238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6501909494400024},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5850696563720703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40846776962280273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38711386919021606},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18054306507110596},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.060502052307128906},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06021338701248169}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":29,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1526392145","https://openalex.org/W1974387177","https://openalex.org/W2015143272","https://openalex.org/W2113814270","https://openalex.org/W2134867751","https://openalex.org/W2136155248","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2605246626","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2923794357","https://openalex.org/W2949662773","https://openalex.org/W3023905253","https://openalex.org/W3091427154","https://openalex.org/W3104792420","https://openalex.org/W3143803406","https://openalex.org/W3162293946","https://openalex.org/W4232282348","https://openalex.org/W4293363567","https://openalex.org/W4297841387","https://openalex.org/W4385245566","https://openalex.org/W6688069703","https://openalex.org/W6754420807","https://openalex.org/W6810740804","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"humans":[2],"comprehending":[3],"speech":[4,61,98],"in":[5,75,133],"a":[6,33,76],"multi-modal":[7,115,131],"manner,":[8],"various":[9,27,84],"audio-visual":[10,60],"datasets":[11,18],"have":[12,31],"been":[13],"constructed.":[14],"However,":[15],"most":[16],"existing":[17],"focus":[19],"on":[20,107],"English,":[21],"developed":[22],"from":[23,71],"pre-existing":[24],"videos":[25],"using":[26],"prediction":[28],"models,":[29],"and":[30,83,100,116,121],"only":[32],"small":[34],"number":[35],"of":[36,68,114],"multi-view":[37,117],"videos.":[38],"To":[39],"mitigate":[40],"the":[41,45,55,90,108,112,126],"limitations,":[42],"we":[43],"constructed":[44],"Open":[46],"Large-scale":[47],"Korean":[48,73],"Audio-Visual":[49],"Speech":[50],"(OLKAVS)":[51],"dataset,":[52],"which":[53],"is":[54],"largest":[56],"among":[57],"publicly":[58],"available":[59],"datasets.":[62],"The":[63],"dataset":[64,128],"contains":[65],"1,150":[66],"hours":[67],"transcribed":[69],"audio":[70],"1,107":[72],"speakers":[74],"studio":[77],"setup":[78],"with":[79],"nine":[80],"different":[81],"viewpoints":[82],"noise":[85],"situations.":[86],"We":[87,103,124],"also":[88],"provide":[89],"pre-trained":[91],"baseline":[92],"models":[93,109],"for":[94],"two":[95],"tasks:":[96],"audiovisual":[97],"recognition":[99],"lip":[101],"reading.":[102],"conducted":[104],"experiments":[105],"based":[106],"to":[110,129],"verify":[111],"effectiveness":[113],"training":[118],"over":[119],"uni-modal":[120],"frontal-view-only":[122],"training.":[123],"expect":[125],"OLKAVS":[127],"facilitate":[130],"research":[132],"broader":[134],"areas.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
