{"id":"https://openalex.org/W4372260408","doi":"https://doi.org/10.1109/icassp49357.2023.10096854","title":"Self-Supervised Accent Learning for Under-Resourced Accents Using Native Language Data","display_name":"Self-Supervised Accent Learning for Under-Resourced Accents Using Native Language Data","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260408","doi":"https://doi.org/10.1109/icassp49357.2023.10096854"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5065995328","display_name":"Mehul Kumar","orcid":"https://orcid.org/0000-0001-7341-2362"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mehul Kumar","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396580","display_name":"Jiyeon Kim","orcid":"https://orcid.org/0000-0001-7964-5060"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiyeon Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113125574","display_name":"Dhananjaya Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhananjaya Gowda","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043920881","display_name":"Abhinav Garg","orcid":"https://orcid.org/0000-0001-5082-5500"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Garg","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research"],"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065995328"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":0.5245,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69742136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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/stress","display_name":"Stress (linguistics)","score":0.819029688835144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8037338256835938},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.652579665184021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749117732048035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5464476943016052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5078707337379456},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.45423880219459534},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4419749975204468},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4332050681114197},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4324563443660736},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3233901262283325},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06009373068809509}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.819029688835144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037338256835938},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.652579665184021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749117732048035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5464476943016052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5078707337379456},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.45423880219459534},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4419749975204468},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4332050681114197},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4324563443660736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3233901262283325},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06009373068809509},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096854","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096854","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2130942839","https://openalex.org/W2895676041","https://openalex.org/W2933138175","https://openalex.org/W2946417913","https://openalex.org/W2964099675","https://openalex.org/W2972798094","https://openalex.org/W2988736778","https://openalex.org/W2991213871","https://openalex.org/W3008587939","https://openalex.org/W3015356564","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3044481399","https://openalex.org/W3095173472","https://openalex.org/W3095410713","https://openalex.org/W3112702554","https://openalex.org/W3137832819","https://openalex.org/W3162061711","https://openalex.org/W3162812479","https://openalex.org/W3209059054","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6770506093","https://openalex.org/W6770514103","https://openalex.org/W6771467084","https://openalex.org/W6777781272","https://openalex.org/W6779192484","https://openalex.org/W6780218876","https://openalex.org/W6792224355"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2352261042","https://openalex.org/W4386784607"],"abstract_inverted_index":{"In":[0,111],"this":[1],"paper,":[2],"we":[3,115],"propose":[4,116],"a":[5,18,45,52,68,81],"novel":[6],"method":[7],"to":[8,35,62,88,117,123,151],"improve":[9],"the":[10,22,91,102,128,143],"accuracy":[11],"of":[12,33,54,93,104,113],"an":[13,37,153],"English":[14,34,43,56,96,140,154,162],"speech":[15,40,74],"recognizer":[16,41,155],"for":[17,30,42,58,76,142],"target":[19,144,160],"accent":[20,61],"using":[21,137,147,159],"corresponding":[23],"native":[24,78,109,120,148],"language":[25,79,121,149],"data.":[26],"Collecting":[27],"labeled":[28,139],"data":[29,65,75,122,141,150],"all":[31],"accents":[32,92,173],"train":[36],"end-to-end":[38],"neural":[39],"is":[44,80,86,134],"difficult":[46,69],"and":[47],"expensive":[48],"task.":[49,70,84],"Also,":[50],"finding":[51],"pool":[53],"representative":[55],"speakers":[57,97],"any":[59,77],"arbitrary":[60],"collect":[63],"unlabeled":[64,73,119],"can":[66],"be":[67],"However,":[71],"collecting":[72],"much":[82],"simpler":[83],"It":[85],"important":[87],"note":[89],"that":[90],"most":[94],"non-native":[95],"are":[98],"heavily":[99],"biased":[100],"by":[101,157],"co-articulation":[103],"sounds":[105],"in":[106,166],"their":[107],"own":[108],"language.":[110],"view":[112],"this,":[114],"use":[118],"learn":[124],"self-supervised":[125],"representations":[126],"during":[127],"pre-training":[129],"stage.":[130],"The":[131],"pre-trained":[132],"model":[133],"then":[135],"fine-tuned":[136],"limited":[138],"accent.":[145],"Experiments":[146],"pre-train":[152],"followed":[156],"fine-tuning":[158],"accented":[161],"show":[163],"significant":[164],"improvements":[165],"word":[167],"error":[168],"rates":[169],"on":[170],"four":[171],"different":[172],"(Great":[174],"Britain,":[175],"Korean,":[176],"Chinese,":[177],"Spanish).":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}