{"id":"https://openalex.org/W3212269487","doi":"https://doi.org/10.1109/icassp43922.2022.9747569","title":"Exploring Non-Autoregressive End-to-End Neural Modeling for English Mispronunciation Detection and Diagnosis","display_name":"Exploring Non-Autoregressive End-to-End Neural Modeling for English Mispronunciation Detection and Diagnosis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3212269487","doi":"https://doi.org/10.1109/icassp43922.2022.9747569","mag":"3212269487"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747569","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5036813887","display_name":"Hsin-Wei Wang","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":true,"raw_author_name":"Hsin-Wei Wang","raw_affiliation_strings":["National Taiwan Normal University,Taiwan","National Taiwan Normal University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"National Taiwan Normal University, Taiwan","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,Taiwan","National Taiwan Normal University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064576196","display_name":"Hsuan-Sheng Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-Sheng Chiu","raw_affiliation_strings":["Chunghwa Telecom Laboratories,Taiwan","Chunghwa Telecom Laboratories, Taiwan"],"affiliations":[{"raw_affiliation_string":"Chunghwa Telecom Laboratories,Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"Chunghwa Telecom Laboratories, Taiwan","institution_ids":["https://openalex.org/I92172085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112577687","display_name":"Yung-Chang Hsu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yung-Chang Hsu","raw_affiliation_strings":["EZAI,Taiwan","EZAI, Taiwan"],"affiliations":[{"raw_affiliation_string":"EZAI,Taiwan","institution_ids":[]},{"raw_affiliation_string":"EZAI, Taiwan","institution_ids":[]}]},{"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,Taiwan","National Taiwan Normal University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"National Taiwan Normal University, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036813887"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.831,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72705236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6817","last_page":"6821"},"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":0.998199999332428,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8269317746162415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000063896179199},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6632294058799744},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6155790686607361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5638965368270874},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5340152382850647},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5125882029533386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4687642753124237},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3493393659591675},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09349450469017029},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07062634825706482}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8269317746162415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000063896179199},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6632294058799744},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6155790686607361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5638965368270874},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5340152382850647},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5125882029533386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4687642753124237},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3493393659591675},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09349450469017029},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07062634825706482},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747569","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320321559","display_name":"Chunghwa Telecom Laboratories","ror":"https://ror.org/04f786589"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W11805017","https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W2127141656","https://openalex.org/W2295721380","https://openalex.org/W2398423749","https://openalex.org/W2400751463","https://openalex.org/W2408752745","https://openalex.org/W2526425061","https://openalex.org/W2552635739","https://openalex.org/W2888954148","https://openalex.org/W2938359332","https://openalex.org/W2962826786","https://openalex.org/W2972347929","https://openalex.org/W2988975212","https://openalex.org/W3015231007","https://openalex.org/W3015439711","https://openalex.org/W3036601975","https://openalex.org/W3096270392","https://openalex.org/W3097515180","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3097911750","https://openalex.org/W3156081754","https://openalex.org/W3169714379","https://openalex.org/W3205351443","https://openalex.org/W4226046739","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6697583303","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6783036611","https://openalex.org/W6794778313","https://openalex.org/W6803132568"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W2197967814"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"neural":[2,30,86,125,143],"modeling":[3,126,153],"has":[4],"emerged":[5],"as":[6],"one":[7,43],"predominant":[8],"school":[9],"of":[10,46,63,96,158,163,171,186],"thought":[11],"to":[12,22,59,70,127,166,182,191],"develop":[13,150],"computer-assisted":[14],"pronunciation":[15,152],"training":[16,98],"(CAPT)":[17],"systems,":[18],"showing":[19],"competitive":[20],"performance":[21,136],"conventional":[23,141],"pronunciation-scoring":[24,199],"based":[25,200],"methods.":[26,144],"However,":[27],"current":[28],"E2E":[29,48,85,124,142,161,194],"methods":[31,49,87],"for":[32],"CAPT":[33],"are":[34,88],"faced":[35],"with":[36,55,139],"at":[37],"least":[38],"two":[39],"pivotal":[40],"challenges.":[41],"On":[42,81],"hand,":[44,84],"most":[45],"the":[47,61,82,131,140,159,169,177,184],"operate":[50],"in":[51,137,189],"an":[52,64,93,197],"autoregressive":[53],"manner":[54],"left-to-right":[56],"beam":[57],"search":[58],"dictate":[60],"pronunciations":[62],"L2":[65],"learners.":[66],"This":[67],"however":[68],"leads":[69],"very":[71],"slow":[72],"inference":[73,132],"speed,":[74],"which":[75],"inevitably":[76],"hinders":[77],"their":[78,103],"practical":[79],"use.":[80],"other":[83],"normally":[89],"data-hungry":[90],"and":[91,108,149,196],"meanwhile":[92],"insufficient":[94],"amount":[95],"nonnative":[97],"data":[99],"would":[100],"often":[101],"reduce":[102],"efficacy":[104],"on":[105,156,176,203],"mispronunciation":[106],"detection":[107],"diagnosis":[109],"(MD&D).":[110],"In":[111,145],"response,":[112],"we":[113,147],"put":[114],"forward":[115],"a":[116,151,204],"novel":[117],"MD&D":[118],"method":[119,165,201],"that":[120],"leverages":[121],"non-autoregressive":[122],"(NAR)":[123],"dramatically":[128],"speed":[129],"up":[130],"time":[133],"while":[134],"maintaining":[135],"line":[138],"addition,":[146],"design":[148],"network":[154],"stacked":[155],"top":[157],"NAR":[160],"models":[162,195],"our":[164,187],"further":[167],"boost":[168],"effectiveness":[170],"MD&D.":[172],"Empirical":[173],"experiments":[174],"conducted":[175],"L2-ARCTIC":[178],"English":[179],"dataset":[180],"seems":[181],"validate":[183],"feasibility":[185],"method,":[188],"comparison":[190],"some":[192],"top-of-the-line":[193],"iconic":[198],"built":[202],"DNN-HMM":[205],"acoustic":[206],"model.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}