{"id":"https://openalex.org/W4319862631","doi":"https://doi.org/10.1109/slt54892.2023.10023214","title":"ASBERT: ASR-Specific Self-Supervised Learning with Self-Training","display_name":"ASBERT: ASR-Specific Self-Supervised Learning with Self-Training","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862631","doi":"https://doi.org/10.1109/slt54892.2023.10023214"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023214","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023214","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5068972361","display_name":"Hyung Yong Kim","orcid":"https://orcid.org/0000-0001-6009-9530"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Yong Kim","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055878270","display_name":"Seung Woo Yoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung Woo Yoo","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059677906","display_name":"Youshin Lim","orcid":"https://orcid.org/0000-0003-3328-0064"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youshin Lim","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027173062","display_name":"Yunkyu Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunkyu Lim","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025565566","display_name":"Hanbin Lee","orcid":"https://orcid.org/0000-0002-4545-0027"},"institutions":[{"id":"https://openalex.org/I4210086063","display_name":"Handok (South Korea)","ror":"https://ror.org/00exehz38","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210086063"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanbin Lee","raw_affiliation_strings":["42dot Inc.,Seoul,Republic of Korea","42dot Inc., Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"42dot Inc.,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4210086063"]},{"raw_affiliation_string":"42dot Inc., Seoul, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20133883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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":0.8104450702667236},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6575819849967957},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6565636396408081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457318663597107},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6104654669761658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5316708087921143},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48716112971305847},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4870465099811554},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4228609502315521},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.41799911856651306},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38666802644729614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35929280519485474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08489182591438293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104450702667236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6575819849967957},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6565636396408081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457318663597107},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6104654669761658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5316708087921143},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48716112971305847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4870465099811554},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4228609502315521},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.41799911856651306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38666802644729614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35929280519485474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08489182591438293},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023214","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023214","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2127141656","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3026041220","https://openalex.org/W3163169798","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W4221145109","https://openalex.org/W4224934179","https://openalex.org/W4226033575","https://openalex.org/W4283324001","https://openalex.org/W4297841337","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6771812881","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6810673746","https://openalex.org/W6844194202","https://openalex.org/W6947929050"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2944691285","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Pre-training":[0],"of":[1],"self-supervised":[2],"learning":[3],"(SSL)":[4],"generally":[5],"shows":[6],"a":[7,22,27,40,102],"good":[8],"performance":[9,119],"on":[10,81],"various":[11],"speech":[12,33],"processing":[13],"tasks.":[14],"However,":[15],"this":[16],"pre-training":[17,77],"scheme":[18],"may":[19],"lead":[20],"to":[21,38,120],"sub-optimal":[23],"solution":[24],"for":[25,45],"fine-tuning":[26],"specific":[28],"task,":[29],"such":[30],"as":[31],"automatic":[32],"recognition":[34],"(ASR).":[35],"In":[36],"order":[37],"provide":[39],"more":[41],"optimal":[42],"pre-trained":[43],"model":[44,92],"ASR,":[46],"we":[47,60],"introduce":[48],"an":[49],"ASR-Specific":[50],"hidden-unit":[51],"BERT":[52],"with":[53],"self-training,":[54,59],"namely":[55],"ASBERT.":[56],"Motivated":[57],"by":[58],"extract":[61],"linguistic-related":[62],"pseudo":[63],"labels":[64,71],"from":[65],"the":[66,75,95,121],"fine-tuned":[67],"model,":[68,100],"and":[69,84,98,104],"these":[70],"are":[72],"used":[73],"in":[74],"next":[76],"procedure.":[78],"Experimental":[79],"results":[80],"LibriSpeech":[82],"test-clean":[83],"test-other":[85],"datasets":[86],"show":[87],"that":[88],"ASBERT":[89,116],"without":[90,113],"language":[91],"(LM)":[93],"outperforms":[94],"conventional":[96,122],"SSL":[97],"self-training":[99,123],"achieving":[101],"6.3/2.0%":[103],"15.4/13.2%":[105],"relatively":[106],"word":[107],"error":[108],"rate":[109],"reduction":[110],"(RERR).":[111],"Moreover,":[112],"using":[114],"pseudo-transcription,":[115],"yields":[117],"comparable":[118],"method.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}