{"id":"https://openalex.org/W4226046739","doi":"https://doi.org/10.1109/asru51503.2021.9688291","title":"Towards Robust Mispronunciation Detection and Diagnosis for L2 English Learners with Accent-Modulating Methods","display_name":"Towards Robust Mispronunciation Detection and Diagnosis for L2 English Learners with Accent-Modulating Methods","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226046739","doi":"https://doi.org/10.1109/asru51503.2021.9688291"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688291","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5041458249","display_name":"Shaowei Jiang","orcid":"https://orcid.org/0000-0003-1260-4699"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Shao-Wei Fan Jiang","raw_affiliation_strings":["National Taiwan Normal University"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081032657","display_name":"Bicheng Yan","orcid":"https://orcid.org/0000-0002-3356-7594"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bi-Cheng Yan","raw_affiliation_strings":["National Taiwan Normal University"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110596981","display_name":"Tien-Hong Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tien-Hong Lo","raw_affiliation_strings":["National Taiwan Normal University"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000134905","display_name":"Fu-An Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Fu-An Chao","raw_affiliation_strings":["National Taiwan Normal University"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041458249"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":1.7592,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8817536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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/pronunciation","display_name":"Pronunciation","score":0.8346607685089111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774463891983032},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7253774404525757},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6423121690750122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6134400963783264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5421190857887268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45200955867767334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42241808772087097},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23767635226249695}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8346607685089111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774463891983032},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7253774404525757},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6423121690750122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6134400963783264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5421190857887268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45200955867767334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42241808772087097},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23767635226249695},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688291","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688291","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5467972186","display_name":null,"funder_award_id":"TL-110-D301","funder_id":"https://openalex.org/F4320321559","funder_display_name":"Chunghwa Telecom Laboratories"},{"id":"https://openalex.org/G58338184","display_name":null,"funder_award_id":"MOST 110-2634-F-008-004,MOST 108-2221-E-003-005-MY3,MOST 109-2221-E-003-020-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320321559","display_name":"Chunghwa Telecom Laboratories","ror":"https://ror.org/04f786589"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W143647774","https://openalex.org/W290344559","https://openalex.org/W2127141656","https://openalex.org/W2139008940","https://openalex.org/W2164810574","https://openalex.org/W2398423749","https://openalex.org/W2401896499","https://openalex.org/W2408752745","https://openalex.org/W2552635739","https://openalex.org/W2766219058","https://openalex.org/W2886319145","https://openalex.org/W2888954148","https://openalex.org/W2889494795","https://openalex.org/W2891816510","https://openalex.org/W2938359332","https://openalex.org/W2964099675","https://openalex.org/W2972347929","https://openalex.org/W2972539100","https://openalex.org/W3015231007","https://openalex.org/W3015439711","https://openalex.org/W3096032230","https://openalex.org/W3097515180","https://openalex.org/W3134482008","https://openalex.org/W3196525293","https://openalex.org/W3197816268","https://openalex.org/W3205351443","https://openalex.org/W4226339160","https://openalex.org/W4287726212","https://openalex.org/W6713615836","https://openalex.org/W6780612146","https://openalex.org/W6783036611","https://openalex.org/W6803132568"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497"],"abstract_inverted_index":{"With":[0],"the":[1,20,59,98,128,132,142,147,162],"acceleration":[2],"of":[3,19,49,62,117,131,138,149],"globalization,":[4],"more":[5,7,100],"and":[6,27,108,161],"people":[8],"are":[9],"willing":[10],"or":[11],"required":[12],"to":[13,39,57,113,126,155],"learn":[14],"second":[15],"languages":[16],"(L2).":[17],"One":[18],"major":[21],"remaining":[22],"challenges":[23],"facing":[24],"current":[25],"mispronunciation":[26],"diagnosis":[28],"(MDD)":[29],"models":[30],"for":[31],"use":[32],"in":[33,65,120,153],"computer-assisted":[34],"pronunciation":[35,164],"training":[36],"(CAPT)":[37],"is":[38],"handle":[40],"speech":[41],"from":[42],"L2":[43,68],"learners":[44],"with":[45,72],"a":[46,103,121],"diverse":[47],"set":[48,55],"accents.":[50],"In":[51],"this":[52,78],"paper,":[53],"we":[54,80,106],"out":[56],"mitigate":[58],"adverse":[60],"effects":[61],"accent":[63,89],"variety":[64],"building":[66],"an":[67,83,92],"English":[69],"MDD":[70,94,134,151],"system":[71],"end-to-end":[73],"(E2E)":[74],"neural":[75],"models.":[76],"To":[77],"end,":[79],"first":[81],"propose":[82],"effective":[84],"modeling":[85],"framework":[86],"that":[87],"infuses":[88],"features":[90,119],"into":[91],"E2E":[93],"model,":[95,152],"thereby":[96],"making":[97],"model":[99],"accent-aware.":[101],"Going":[102],"step":[104],"further,":[105],"design":[107],"present":[109],"disparate":[110],"accent-aware":[111,115],"modules":[112],"perform":[114],"modulation":[116],"acoustic":[118],"finer-grained":[122],"manner,":[123],"so":[124],"as":[125],"enhance":[127],"discriminating":[129],"capability":[130],"resulting":[133],"model.":[135],"Extensive":[136],"sets":[137],"experiments":[139],"conducted":[140],"on":[141],"L2-ARCTIC":[143],"benchmark":[144],"dataset":[145],"show":[146],"merits":[148],"our":[150],"comparison":[154],"some":[156],"existing":[157],"E2E-based":[158],"strong":[159],"baselines":[160],"celebrated":[163],"scoring":[165],"based":[166],"method.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}