{"id":"https://openalex.org/W3207547029","doi":"https://doi.org/10.21437/interspeech.2022-547","title":"K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables","display_name":"K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W3207547029","doi":"https://doi.org/10.21437/interspeech.2022-547","mag":"3207547029"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-547","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-547","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5074958622","display_name":"Jounghee Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jounghee Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059650940","display_name":"Pilsung Kang","orcid":"https://orcid.org/0000-0001-7663-3937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pilsung Kang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074958622"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8315,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72689076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4945","last_page":"4949"},"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":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.7649229764938354},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7221239805221558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7214025259017944},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6945292949676514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43228408694267273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37539270520210266},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06304579973220825},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06232038140296936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649229764938354},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7221239805221558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7214025259017944},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6945292949676514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43228408694267273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37539270520210266},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06304579973220825},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06232038140296936},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-547","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-547","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2739883972","https://openalex.org/W2769205094","https://openalex.org/W2787663903","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2890197052","https://openalex.org/W2962780374","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2964172053","https://openalex.org/W2965373594","https://openalex.org/W2973049979","https://openalex.org/W2992095114","https://openalex.org/W3000083466","https://openalex.org/W3005680577","https://openalex.org/W3016181583","https://openalex.org/W3037057938","https://openalex.org/W3083353586","https://openalex.org/W3091427154","https://openalex.org/W3096899423","https://openalex.org/W3099782249","https://openalex.org/W3124030384","https://openalex.org/W3163702140"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W2351061015","https://openalex.org/W2017509870","https://openalex.org/W4360952157","https://openalex.org/W4220731478","https://openalex.org/W2153647085","https://openalex.org/W4251141768","https://openalex.org/W2383083288","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Wav2vec":[0,79,96,145],"2.0":[1,80,146],"is":[2,13,38,44,74,116,185],"an":[3],"end-to-end":[4],"framework":[5,43],"of":[6,22,78,93,122,126,136],"self-supervised":[7,42],"learning":[8],"for":[9,82],"speech":[10,17,85,175],"representation":[11],"that":[12,158],"successful":[14],"in":[15,46,188],"automatic":[16,84],"recognition":[18,86],"(ASR),":[19],"but":[20],"most":[21],"the":[23,26,41,59,94,108,120,127,133,137,143,159,163],"work":[24],"on":[25,147,166],"topic":[27],"has":[28],"been":[29],"developed":[30],"with":[31,50],"a":[32,62,75,102,113,148],"single":[33],"language:":[34],"English.":[35],"Therefore,":[36],"it":[37],"unclear":[39],"whether":[40],"effective":[45,187],"recognizing":[47],"other":[48],"languages":[49],"different":[51],"writing":[52,64,110],"systems,":[53],"such":[54],"as":[55],"Korean":[56,83,109,149,168,174],"which":[57,73],"uses":[58],"Hangul":[60],"having":[61],"unique":[63],"system.":[65],"In":[66,98,129],"this":[67],"paper,":[68],"we":[69,100,131],"present":[70],"K-Wav2Vec":[71],"2.0,":[72],"modified":[76],"version":[77],"designed":[81],"by":[87,140],"exploring":[88],"and":[89,177],"optimizing":[90],"various":[91],"factors":[92],"original":[95],"2.0.":[97],"fine-tuning,":[99],"propose":[101],"multi-task":[103],"hierarchical":[104],"architecture":[105],"to":[106,118,192],"reflect":[107],"structure.":[111],"Moreover,":[112],"joint":[114],"decoder":[115],"applied":[117],"alleviate":[119],"problem":[121],"words":[123],"existing":[124],"outside":[125],"vocabulary.":[128],"pre-training,":[130],"attempted":[132],"cross-lingual":[134],"transfer":[135],"pre-trained":[138],"model":[139],"further":[141],"pre-training":[142,184],"English":[144],"dataset,":[150],"considering":[151],"limited":[152],"resources.":[153],"Our":[154],"experimental":[155],"results":[156],"demonstrate":[157],"proposed":[160],"method":[161],"yields":[162],"best":[164],"performance":[165],"both":[167],"ASR":[169],"datasets:":[170],"Ksponspeech":[171],"(a":[172,179],"large-scale":[173],"corpus)":[176],"Clovacall":[178],"call-based":[180],"dialog":[181],"corpus).":[182],"Further":[183],"also":[186],"language":[189],"adaptation,":[190],"leading":[191],"large":[193],"improvements":[194],"without":[195],"additional":[196],"data.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}