{"id":"https://openalex.org/W3096767609","doi":"https://doi.org/10.21437/interspeech.2020-2440","title":"Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition","display_name":"Exploring Lexicon-Free Modeling Units for End-to-End Korean and Korean-English Code-Switching Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096767609","doi":"https://doi.org/10.21437/interspeech.2020-2440","mag":"3096767609"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2440","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5063405483","display_name":"Jisung Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jisung Wang","raw_affiliation_strings":["VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul"],"affiliations":[{"raw_affiliation_string":"VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451538","display_name":"Ji\u2010Hwan Kim","orcid":"https://orcid.org/0000-0001-9054-2994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihwan Kim","raw_affiliation_strings":["VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul"],"affiliations":[{"raw_affiliation_string":"VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042058165","display_name":"Sangki Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sangki Kim","raw_affiliation_strings":["VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul"],"affiliations":[{"raw_affiliation_string":"VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047510119","display_name":"Yeha Lee","orcid":"https://orcid.org/0000-0002-6248-7729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeha Lee","raw_affiliation_strings":["VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul"],"affiliations":[{"raw_affiliation_string":"VUNO Inc. 507, Gangnam-daero, Seocho-gu, Seoul","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063405483"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64089987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9455999732017517,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9417999982833862,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.7950171232223511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748146057128906},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7427576780319214},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7002207636833191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5917568802833557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5143085718154907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.447887122631073},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.424269437789917},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.25401222705841064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.141218364238739}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7950171232223511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748146057128906},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7427576780319214},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7002207636833191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5917568802833557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5143085718154907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447887122631073},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.424269437789917},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.25401222705841064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.141218364238739},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2440","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W309335912","https://openalex.org/W1524333225","https://openalex.org/W2085628288","https://openalex.org/W2121879602","https://openalex.org/W2327501763","https://openalex.org/W2627092829","https://openalex.org/W2803399609","https://openalex.org/W2962778134","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963382687","https://openalex.org/W2963939538","https://openalex.org/W2964002616"],"related_works":["https://openalex.org/W2432897346","https://openalex.org/W2771594921","https://openalex.org/W3138119129","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W2140536630","https://openalex.org/W2391730868","https://openalex.org/W2759814045","https://openalex.org/W2940588741","https://openalex.org/W2293063924"],"abstract_inverted_index":{"As":[0],"the":[1,10,142],"character-based":[2],"end-to-end":[3,42],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"models":[8],"evolve,":[9],"choice":[11],"of":[12],"acoustic":[13],"modeling":[14,38,51],"units":[15,39,52,65],"becomes":[16],"important.Since":[17],"Korean":[18,33,43,69,78,123,135],"is":[19,105],"a":[20,26,59,75,106],"fairly":[21],"phonetic":[22],"language":[23,152],"and":[24,55,100,115,124,149],"has":[25],"unique":[27],"writing":[28],"system":[29],"with":[30,131],"its":[31],"own":[32],"alphabet,":[34],"it's":[35],"worth":[36],"investigating":[37],"for":[40,74,122,144],"an":[41,150],"ASR":[44,127],"task.In":[45],"this":[46],"work,":[47],"we":[48],"introduce":[49],"lexicon-free":[50,64],"in":[53,90,98,139],"Korean,":[54],"explore":[56],"them":[57],"using":[58],"hybrid":[60],"CTC/Attention-based":[61],"encoder-decoder":[62],"model.Five":[63],"are":[66,120],"investigated:":[67],"Syllable-based":[68],"character":[70,73,80,87,95],"(with":[71,81,88,96],"English":[72,82],"code-switching":[76],"task),":[77],"Jamo":[79,94],"character),":[83],"subword":[84],"on":[85,93,111,134],"syllable-based":[86],"sub-word":[89,92],"English),":[91,99],"sub-words":[97,132],"finally":[101],"byte":[102],"unit,":[103],"which":[104],"universal":[107],"one":[108],"across":[109],"language.Experiments":[110],"Zeroth-Korean":[112],"(51.6":[113],"hrs)":[114,119],"Medical":[116],"Record":[117],"(2530":[118],"done":[121],"Korean-English":[125],"codeswitching":[126],"tasks,":[128],"respectively.Sequence-to-sequence":[129],"learning":[130],"based":[133],"syllables":[136],"(and":[137],"subwords":[138],"English)":[140],"performs":[141],"best":[143],"both":[145],"tasks":[146],"without":[147],"lexicon":[148],"extra":[151],"model":[153],"integration.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}