{"id":"https://openalex.org/W4416922871","doi":"https://doi.org/10.1109/iccais67508.2025.11262073","title":"Korean Speech Recognition via Retrieval-Augmented Generation-Based Intent-Aware Keyword Correction","display_name":"Korean Speech Recognition via Retrieval-Augmented Generation-Based Intent-Aware Keyword Correction","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4416922871","doi":"https://doi.org/10.1109/iccais67508.2025.11262073"},"language":null,"primary_location":{"id":"doi:10.1109/iccais67508.2025.11262073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais67508.2025.11262073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5054678894","display_name":"Chaerin Kim","orcid":"https://orcid.org/0009-0002-9665-4342"},"institutions":[{"id":"https://openalex.org/I4210159093","display_name":"Jeil Pharmaceutical (South Korea)","ror":"https://ror.org/04z9hzj86","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210159093"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chaerin Kim","raw_affiliation_strings":["R&D Center, Jenti AI,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"R&D Center, Jenti AI,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210159093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027240674","display_name":"Yeonghun Chae","orcid":null},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeonghun Chae","raw_affiliation_strings":["SEASON Co. Ltd.,Sejong,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SEASON Co. Ltd.,Sejong,Republic of Korea","institution_ids":["https://openalex.org/I28777354"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyoungki Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126996","display_name":"Sejong Institute","ror":"https://ror.org/03qs3qx17","country_code":"KR","type":"nonprofit","lineage":["https://openalex.org/I4210126996"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyoungki Ahn","raw_affiliation_strings":["Digital Convergence Center Korean Institute for Archaeology and Environment,Sejong,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Convergence Center Korean Institute for Archaeology and Environment,Sejong,Republic of Korea","institution_ids":["https://openalex.org/I4210126996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072873685","display_name":"Changbeom Shim","orcid":"https://orcid.org/0000-0003-1735-6655"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Changbeom Shim","raw_affiliation_strings":["School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University,Perth,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University,Perth,Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35397241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7005000114440918,"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":0.7005000114440918,"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/T12031","display_name":"Speech and dialogue systems","score":0.06279999762773514,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.04969999939203262,"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/visualization","display_name":"Visualization","score":0.6459000110626221},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5616999864578247},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.4307999908924103},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4056999981403351},{"id":"https://openalex.org/keywords/cultural-heritage","display_name":"Cultural heritage","score":0.3993000090122223},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.36809998750686646},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.3490000069141388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144999742507935},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6459000110626221},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6333000063896179},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.4307999908924103},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C60671577","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural heritage","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais67508.2025.11262073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais67508.2025.11262073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 14th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1937349937","https://openalex.org/W2041670430","https://openalex.org/W2137561086","https://openalex.org/W2797303992","https://openalex.org/W3035164836","https://openalex.org/W3095878927","https://openalex.org/W3164712988","https://openalex.org/W3182801966","https://openalex.org/W3200692557","https://openalex.org/W4320494062","https://openalex.org/W4361290451","https://openalex.org/W4367671122","https://openalex.org/W4402112288","https://openalex.org/W4403334466"],"related_works":[],"abstract_inverted_index":{"This":[0,142],"study":[1],"proposes":[2],"a":[3,64,70],"novel":[4],"Korean":[5,148],"speech":[6,26,82,101,116,149],"recognition":[7,27,117,150],"system":[8,62,85,129],"in":[9,51,156],"Kiosks":[10],"that":[11,68,110],"integrates":[12],"domain-specific":[13],"keyword":[14,65,72,112],"correction":[15,66,113],"and":[16,37,134,151,160],"visualization":[17,90,127],"report":[18,128],"generation":[19],"based":[20,92],"on":[21,93],"Retrieval-Augmented":[22],"Generation":[23],"(RAG).":[24],"Conventional":[25],"for":[28],"Korean,":[29],"characterized":[30],"by":[31],"its":[32,153],"agglutinative":[33],"structure,":[34],"numerous":[35],"homophones,":[36],"significant":[38],"pronunciation":[39],"variations,":[40],"often":[41],"exhibits":[42],"high":[43],"error":[44],"rates,":[45],"especially":[46],"when":[47],"recognizing":[48],"specialized":[49],"terminology":[50],"the":[52,60,80,94,111,126],"cultural":[53,106,157],"heritage":[54,107,158],"domain.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"proposed":[61],"utilizes":[63],"mechanism":[67],"combines":[69],"topic-specific":[71],"dictionary":[73],"with":[74],"semantic":[75],"similarity":[76],"analysis,":[77],"thereby":[78],"refining":[79],"recognized":[81],"input.":[83],"The":[84],"automatically":[86],"generates":[87],"structured":[88],"HTML":[89],"reports":[91],"corrected":[95],"queries.":[96],"Experimental":[97],"results":[98],"using":[99],"70":[100],"data":[102],"samples":[103],"across":[104],"seven":[105],"topics":[108],"demonstrate":[109],"method":[114],"improved":[115],"accuracy":[118],"from":[119],"45.71":[120],"%":[121],"to":[122,138],"91.43":[123],"%,":[124],"while":[125],"significantly":[130],"enhanced":[131],"user":[132],"satisfaction":[133],"learning":[135],"effectiveness":[136],"compared":[137],"traditional":[139],"text-based":[140],"responses.":[141],"work":[143],"overcomes":[144],"structural":[145],"limitations":[146],"of":[147],"demonstrates":[152],"practical":[154],"applicability":[155],"education":[159],"guidance":[161],"scenarios.":[162]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-02T00:00:00"}