{"id":"https://openalex.org/W4406858885","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849099","title":"Generating Phonetic Transcriptions for Korean English L2 Learners Using Multiple Self-Supervised-Model-Based ASR Systems and Rover Method","display_name":"Generating Phonetic Transcriptions for Korean English L2 Learners Using Multiple Self-Supervised-Model-Based ASR Systems and Rover Method","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858885","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849099"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5089506248","display_name":"Jong\u2010In Kim","orcid":"https://orcid.org/0000-0002-6907-6703"},"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":"Jong In Kim","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Cognitive Science,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Cognitive Science,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417561","display_name":"Sun\u2010Hee Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunhee Kim","raw_affiliation_strings":["Seoul National University,Department of French Language Education,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of French Language Education,Republic of Korea","institution_ids":["https://openalex.org/I158743462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105294860","display_name":"Minhwa Chung","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":"Minhwa Chung","raw_affiliation_strings":["Seoul National University,Interdisciplinary Program in Cognitive Science,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University,Interdisciplinary Program in Cognitive Science,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089506248"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24324974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9552000164985657,"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":0.9552000164985657,"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":0.8033163547515869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6007106900215149},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.567680835723877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5412350296974182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033163547515869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6007106900215149},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.567680835723877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5412350296974182}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1904457459","https://openalex.org/W2061114942","https://openalex.org/W2888954148","https://openalex.org/W3095350795","https://openalex.org/W3197742413","https://openalex.org/W3198098585","https://openalex.org/W3209059054","https://openalex.org/W3209976096","https://openalex.org/W4296068419","https://openalex.org/W4296068424","https://openalex.org/W4386025763","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"Computer-Assisted":[1],"Pronunciation":[2],"Training":[3],"(CAPT),":[4],"accurate":[5,41],"phonetic":[6,42],"transcriptions":[7,28],"are":[8],"essential":[9],"for":[10,20],"identifying":[11],"mispronunciations":[12],"in":[13,93],"non-native":[14],"speech":[15],"corpora.":[16],"Publicly":[17],"available":[18],"corpora":[19],"Korean":[21,110,120],"English":[22,112,121],"L2":[23],"learners":[24],"often":[25],"lack":[26],"these":[27],"due":[29],"to":[30,81,97],"their":[31],"limited":[32],"size":[33],"and":[34,75,78],"availability.":[35],"To":[36],"address":[37],"the":[38,73,83,109],"shortage":[39],"of":[40,104],"transcriptions,":[43],"we":[44,89],"propose":[45],"a":[46],"method":[47],"that":[48],"combines":[49],"multiple":[50],"Self-Supervised":[51],"Learning":[52],"(SSL)-based":[53],"phone":[54,67,94],"recognition":[55],"systems":[56],"with":[57],"Recognizer":[58],"Output":[59],"Voting":[60],"Error":[61],"Reduction":[62],"(ROVER).":[63],"We":[64],"trained":[65],"SSL-based":[66],"recognizers":[68],"(Data2vec,":[69],"Hubert,":[70],"Wav2vec)":[71],"on":[72],"Librispeech":[74],"CommonVoice":[76],"datasets":[77],"used":[79],"them":[80],"decode":[82],"L2arctic":[84],"corpus.":[85],"By":[86],"applying":[87],"ROVER,":[88],"achieved":[90],"85.5%":[91],"accuracy":[92],"transcription":[95],"compared":[96],"manual":[98],"tagging.":[99],"Additionally,":[100],"an":[101],"error":[102],"analysis":[103],"140":[105],"beginner-level":[106],"sentences":[107],"from":[108],"Spoken":[111],"Corpus":[113],"(NIA144)":[114],"identified":[115],"common":[116],"pronunciation":[117],"errors":[118],"among":[119],"speakers.":[122]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}