{"id":"https://openalex.org/W3092431471","doi":"https://doi.org/10.1109/sped53181.2021.9587408","title":"Mispronunciation Detection and Diagnosis for Mandarin Accented English Speech","display_name":"Mispronunciation Detection and Diagnosis for Mandarin Accented English Speech","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3092431471","doi":"https://doi.org/10.1109/sped53181.2021.9587408","mag":"3092431471"},"language":"en","primary_location":{"id":"doi:10.1109/sped53181.2021.9587408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://uknowledge.uky.edu/cgi/viewcontent.cgi?article=1164&context=ece_etds","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021784176","display_name":"Subash Khanal","orcid":"https://orcid.org/0000-0001-7666-8603"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Subash Khanal","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015797517","display_name":"Michael T. Johnson","orcid":"https://orcid.org/0000-0001-5424-4877"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael T. Johnson","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064273942","display_name":"Mohammad Soleymanpour","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Soleymanpour","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033165110","display_name":"Narjes Bozorg","orcid":null},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narjes Bozorg","raw_affiliation_strings":["University of Kentucky, Lexington, KY, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021784176"],"corresponding_institution_ids":["https://openalex.org/I143302722"],"apc_list":null,"apc_paid":null,"fwci":0.8399,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77537472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"62","last_page":"67"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9962000250816345,"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":0.9947999715805054,"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":0.8697864413261414},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8494352102279663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7615275979042053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7536041140556335},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5833220481872559},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5146142244338989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4957524240016937},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40937715768814087},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13776597380638123}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8697864413261414},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8494352102279663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7615275979042053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536041140556335},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5833220481872559},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5146142244338989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4957524240016937},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40937715768814087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13776597380638123},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/sped53181.2021.9587408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped53181.2021.9587408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"},{"id":"pmh:oai:uknowledge.uky.edu:ece_etds-1164","is_oa":true,"landing_page_url":"https://uknowledge.uky.edu/ece_etds/156","pdf_url":"https://uknowledge.uky.edu/cgi/viewcontent.cgi?article=1164&context=ece_etds","source":{"id":"https://openalex.org/S4306402623","display_name":"UKnowledge (University of Kentucky)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143302722","host_organization_name":"University of Kentucky","host_organization_lineage":["https://openalex.org/I143302722"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses and Dissertations--Electrical and Computer Engineering","raw_type":"text"},{"id":"doi:10.13023/etd.2020.340","is_oa":true,"landing_page_url":"https://doi.org/10.13023/etd.2020.340","pdf_url":null,"source":{"id":"https://openalex.org/S4306402623","display_name":"UKnowledge (University of Kentucky)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143302722","host_organization_name":"University of Kentucky","host_organization_lineage":["https://openalex.org/I143302722"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:uknowledge.uky.edu:ece_etds-1164","is_oa":true,"landing_page_url":"https://uknowledge.uky.edu/ece_etds/156","pdf_url":"https://uknowledge.uky.edu/cgi/viewcontent.cgi?article=1164&context=ece_etds","source":{"id":"https://openalex.org/S4306402623","display_name":"UKnowledge (University of Kentucky)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I143302722","host_organization_name":"University of Kentucky","host_organization_lineage":["https://openalex.org/I143302722"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Theses and Dissertations--Electrical and Computer Engineering","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092431471.pdf","grobid_xml":"https://content.openalex.org/works/W3092431471.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W290344559","https://openalex.org/W1006203101","https://openalex.org/W1524333225","https://openalex.org/W1647671624","https://openalex.org/W1974747584","https://openalex.org/W1981706894","https://openalex.org/W1993166555","https://openalex.org/W2049905800","https://openalex.org/W2073006259","https://openalex.org/W2129755070","https://openalex.org/W2139008940","https://openalex.org/W2159693968","https://openalex.org/W2370418772","https://openalex.org/W2400818677","https://openalex.org/W2401896499","https://openalex.org/W2516863679","https://openalex.org/W2550928100","https://openalex.org/W2552635739","https://openalex.org/W2576146788","https://openalex.org/W2770494505","https://openalex.org/W2794209590","https://openalex.org/W2890962360","https://openalex.org/W2895930397","https://openalex.org/W2938359332","https://openalex.org/W2964227577","https://openalex.org/W3092431471","https://openalex.org/W3104896896","https://openalex.org/W3140836199","https://openalex.org/W6610357026","https://openalex.org/W6631362777","https://openalex.org/W6713037690","https://openalex.org/W6784002887"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"This":[0,112],"paper":[1],"presents":[2],"a":[3,12,168,185],"Mispronunciation":[4],"Detection":[5],"and":[6,20,39,52,84,129,172,184],"Diagnosis":[7],"(MDD)":[8],"system":[9,166],"based":[10,131],"on":[11],"range":[13],"of":[14,25,33,50,57,70,78,91,120,146,160,170,178,182,189],"Automatic":[15],"Speech":[16],"Recognition":[17],"(ASR)":[18],"models":[19,97],"feature":[21],"types.":[22],"The":[23,163],"goals":[24],"this":[26],"research":[27],"are":[28],"to":[29,37,53,82,156],"assess":[30,54],"the":[31,41,55,58,68,76,79,88,95,108,116,121,135,142,158],"ability":[32,77],"speech":[34],"recognition":[35],"systems":[36,81],"detect":[38,83],"diagnose":[40,85],"common":[42],"pronunciation":[43,86],"errors":[44],"seen":[45],"in":[46,66],"non-native":[47],"speakers":[48],"(L2)":[49],"English":[51,148],"contribution":[56],"information":[59],"offered":[60],"by":[61,94],"Electromagnetic":[62,143],"Articulography":[63,144],"(EMA)":[64],"data":[65],"improving":[67],"performance":[69,159],"such":[71],"MDD":[72,117,136,161],"systems.":[73,162],"To":[74],"evaluate":[75],"ASR":[80,96,122,132],"errors,":[87],"recognized":[89],"sequence":[90],"phonemes":[92],"generated":[93],"were":[98,150],"aligned":[99],"with":[100,107,153],"human-labeled":[101],"phonetic":[102,110],"transcripts":[103],"as":[104,106],"well":[105],"original":[109],"prompts.":[111],"three-way":[113],"alignment":[114],"determined":[115],"related":[118],"metrics":[119],"system.":[123,137],"System":[124],"architectures":[125],"included":[126],"GMM-HMM,":[127],"DNN,":[128],"RNN":[130],"engines":[133],"for":[134],"Articulatory":[138],"features":[139,155,174],"derived":[140],"from":[141],"corpus":[145],"Mandarin-Accented":[147],"(EMA-MAE)":[149],"utilized":[151],"along":[152],"acoustic":[154,171],"compare":[157],"best":[164],"performing":[165],"using":[167],"combination":[169],"articulatory":[173],"had":[175],"an":[176],"accuracy":[177,181],"82.4%,":[179],"diagnostic":[180],"75.8%":[183],"false":[186],"rejection":[187],"rate":[188],"17.2%.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}