{"id":"https://openalex.org/W4392944304","doi":"https://doi.org/10.1109/iceic61013.2024.10457193","title":"Contextual Learning for Missing Speech Automatic Speech Recognition","display_name":"Contextual Learning for Missing Speech Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-01-28","ids":{"openalex":"https://openalex.org/W4392944304","doi":"https://doi.org/10.1109/iceic61013.2024.10457193"},"language":"en","primary_location":{"id":"doi:10.1109/iceic61013.2024.10457193","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5057917723","display_name":"Yeona Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yeona Hong","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066878875","display_name":"Miseul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Miseul Kim","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101214578","display_name":"Woo-Jin Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo-Jin Chung","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Yonsei University,dept. of electrical and electronic engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"dept. of electrical and electronic engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057917723"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02708391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2303.08774","issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.980400025844574,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.980400025844574,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9435999989509583,"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/computer-science","display_name":"Computer science","score":0.7738960981369019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6795887351036072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4607471227645874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4483104646205902},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4193834364414215},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.41503891348838806}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738960981369019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6795887351036072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4607471227645874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4483104646205902},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4193834364414215},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.41503891348838806}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic61013.2024.10457193","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1992475611","https://openalex.org/W2007151545","https://openalex.org/W2013426435","https://openalex.org/W2062164080","https://openalex.org/W2127141656","https://openalex.org/W2908510526","https://openalex.org/W2965373594","https://openalex.org/W3015678833","https://openalex.org/W3036601975","https://openalex.org/W3095319910","https://openalex.org/W4221156109","https://openalex.org/W4226399820","https://openalex.org/W4296740048","https://openalex.org/W4375869189","https://openalex.org/W4385245566","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6811129797"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,42],"present":[4],"an":[5],"automatic":[6],"speech":[7,19,36,61,119],"recognition":[8],"(ASR)":[9],"system":[10,105],"that":[11,37],"is":[12],"capable":[13],"of":[14,71,82,121,131],"decoding":[15],"complete":[16,33],"transcriptions":[17,34],"from":[18,35,125],"even":[20],"in":[21,28,55],"cases":[22],"where":[23],"there":[24],"are":[25],"missing":[26,40,118],"segments":[27,62,120,136],"the":[29,66,80,103],"audio.":[30],"To":[31],"predict":[32],"may":[38],"have":[39],"segments,":[41],"utilize":[43],"a":[44,74,86,126],"contextual":[45,75],"learning":[46],"approach":[47],"inspired":[48],"by":[49],"recent":[50],"language":[51],"model":[52,58,69,96],"training":[53,97],"approaches,":[54],"which":[56],"our":[57],"leverages":[59],"surrounding":[60],"as":[63,99],"cues":[64],"for":[65,95],"prediction.":[67],"Our":[68,110],"consists":[70],"two":[72],"modules:":[73],"feature":[76],"extractor":[77],"designed":[78],"with":[79],"structure":[81],"wav2vec":[83],"2.0,":[84],"and":[85],"projection":[87],"layer.":[88],"We":[89],"further":[90],"explore":[91],"various":[92,122],"masking":[93],"lengths":[94],"so":[98],"to":[100,137],"optimally":[101],"benefit":[102],"ASR":[104,115],"without":[106],"compromising":[107],"its":[108],"performance.":[109],"proposed":[111],"methodology":[112],"demonstrates":[113],"high-quality":[114],"performance":[116],"on":[117,133,139],"lengths,":[123],"ranging":[124],"word":[127],"error":[128],"rate":[129],"(WER)":[130],"4.7%":[132],"0.25":[134],"seconds":[135],"18.5%":[138],"1":[140],"second":[141],"segments.":[142]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}