{"id":"https://openalex.org/W4323824369","doi":"https://doi.org/10.1109/iceic57457.2023.10049934","title":"Korean Tokenization for Beam Search Rescoring in Speech Recognition","display_name":"Korean Tokenization for Beam Search Rescoring in Speech Recognition","publication_year":2023,"publication_date":"2023-02-05","ids":{"openalex":"https://openalex.org/W4323824369","doi":"https://doi.org/10.1109/iceic57457.2023.10049934"},"language":"en","primary_location":{"id":"doi:10.1109/iceic57457.2023.10049934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic57457.2023.10049934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5064051041","display_name":"Kyuhong Shim","orcid":"https://orcid.org/0000-0002-0123-3100"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyuhong Shim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056442641","display_name":"Hyewon Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyewon Bae","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113491293","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064051041"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.1746,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51422285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9934999942779541,"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":0.989300012588501,"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":0.8378166556358337},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.8266123533248901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7701884508132935},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7127873301506042},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.583876371383667},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5680816769599915},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5192299485206604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48774272203445435},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4876796007156372},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.41650712490081787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3509180247783661},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.1356508731842041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378166556358337},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8266123533248901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7701884508132935},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7127873301506042},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.583876371383667},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5680816769599915},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5192299485206604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48774272203445435},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4876796007156372},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.41650712490081787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3509180247783661},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.1356508731842041},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic57457.2023.10049934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic57457.2023.10049934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1584080561","https://openalex.org/W2591804103","https://openalex.org/W2798955519","https://openalex.org/W2938348542","https://openalex.org/W2972357892","https://openalex.org/W2973122799","https://openalex.org/W3000083466","https://openalex.org/W3091427154","https://openalex.org/W3092366774","https://openalex.org/W3097777922","https://openalex.org/W3100129654","https://openalex.org/W3198270883","https://openalex.org/W4205807230","https://openalex.org/W6679855610","https://openalex.org/W6685327712","https://openalex.org/W6687566353","https://openalex.org/W6784261359"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W4361193986","https://openalex.org/W1847536016","https://openalex.org/W3149094754","https://openalex.org/W4298195702","https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3093768914","https://openalex.org/W2945402993","https://openalex.org/W1795026554"],"abstract_inverted_index":{"The":[0],"performance":[1,143],"of":[2],"automatic":[3],"speech":[4,30,151],"recognition":[5],"(ASR)":[6],"models":[7],"can":[8],"be":[9,84],"greatly":[10],"improved":[11],"by":[12],"proper":[13],"beam-search":[14],"decoding":[15,41],"with":[16],"an":[17,25],"external":[18,72],"language":[19],"model":[20,130],"(LM).":[21],"There":[22],"has":[23],"been":[24,37],"increasing":[26],"interest":[27],"in":[28,108],"Korean":[29,49,58,110,150],"recognition,":[31],"but":[32],"not":[33,83],"many":[34],"studies":[35],"have":[36],"focused":[38],"on":[39],"the":[40,61,67,75,85,116,127,137,141,145],"procedure.":[42],"In":[43,133],"this":[44],"paper,":[45],"we":[46,78,135],"propose":[47,91],"a":[48,92,98,109,120],"tokenization":[50,69,94],"method":[51,70,95],"for":[52,57,71,88,144],"neural":[53],"network-based":[54],"LM":[55,73,129],"used":[56],"ASR.":[59],"Although":[60],"common":[62],"approach":[63,118],"is":[64,104],"to":[65,126,139],"use":[66],"same":[68,128],"as":[74],"ASR":[76,142],"model,":[77],"show":[79,114],"that":[80,96,115],"it":[81],"may":[82],"best":[86],"choice":[87],"Korean.":[89],"We":[90],"new":[93],"inserts":[97],"special":[99],"token,":[100],"SkipTC,":[101],"when":[102],"there":[103],"no":[105],"trailing":[106],"consonant":[107],"syllable.":[111],"Our":[112],"experiments":[113],"proposed":[117],"achieves":[119],"lower":[121],"word":[122],"error":[123],"rate":[124],"compared":[125],"without":[131],"SkipTC.":[132],"addition,":[134],"are":[136],"first":[138],"report":[140],"recently":[146],"introduced":[147],"large-scale":[148],"7,600h":[149],"dataset.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}