{"id":"https://openalex.org/W3124560983","doi":"https://doi.org/10.1109/icassp39728.2021.9413953","title":"Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling","display_name":"Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3124560983","doi":"https://doi.org/10.1109/icassp39728.2021.9413953","mag":"3124560983"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.06396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":["Amazon Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022629545","display_name":"Szymon Zaporowski","orcid":"https://orcid.org/0000-0003-0814-1097"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Szymon Zaporowski","raw_affiliation_strings":["Gdansk University of Technology, Faculty of ETI,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gdansk University of Technology, Faculty of ETI,Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054373836","display_name":"Shira Calamaro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shira Calamaro","raw_affiliation_strings":["Amazon Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon Speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033154448","display_name":"Bo\u017cena Kostek","orcid":"https://orcid.org/0000-0001-6288-2908"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bozena Kostek","raw_affiliation_strings":["Gdansk University of Technology, Faculty of ETI,Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gdansk University of Technology, Faculty of ETI,Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7738","last_page":"7742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9979000091552734,"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":0.9969000220298767,"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/pronunciation","display_name":"Pronunciation","score":0.7775049805641174},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619749903678894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6768370866775513},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6425989270210266},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5853587985038757},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.507396399974823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810200333595276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24691230058670044}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7775049805641174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619749903678894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768370866775513},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6425989270210266},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5853587985038757},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.507396399974823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810200333595276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24691230058670044},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.06396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06396","pdf_url":"https://arxiv.org/pdf/2101.06396","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3124560983","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.06396.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.06396","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.06396","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"},{"id":"doi:10.17023/bv0z-7p29","is_oa":true,"landing_page_url":"https://doi.org/10.17023/bv0z-7p29","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.06396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.06396","pdf_url":"https://arxiv.org/pdf/2101.06396","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3124560983.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1493077065","https://openalex.org/W1505400583","https://openalex.org/W1515154287","https://openalex.org/W1635512741","https://openalex.org/W2054441760","https://openalex.org/W2070233361","https://openalex.org/W2074231493","https://openalex.org/W2130942839","https://openalex.org/W2139008940","https://openalex.org/W2143612262","https://openalex.org/W2186615578","https://openalex.org/W2400818677","https://openalex.org/W2552635739","https://openalex.org/W2889480449","https://openalex.org/W2938359332","https://openalex.org/W2972347929","https://openalex.org/W2972359262","https://openalex.org/W2972812366","https://openalex.org/W3012416849","https://openalex.org/W3027912465","https://openalex.org/W3096270392","https://openalex.org/W3100647618","https://openalex.org/W6623517193","https://openalex.org/W6679436768","https://openalex.org/W6686509673","https://openalex.org/W6713037690","https://openalex.org/W6785174819"],"related_works":["https://openalex.org/W3160255128","https://openalex.org/W3205234329","https://openalex.org/W2400818677","https://openalex.org/W2396796398","https://openalex.org/W2805034849","https://openalex.org/W2069678305","https://openalex.org/W1992662153","https://openalex.org/W3196676570","https://openalex.org/W2230441926","https://openalex.org/W3096674206","https://openalex.org/W2485759381","https://openalex.org/W654092675","https://openalex.org/W45930974","https://openalex.org/W2389881542","https://openalex.org/W2810104656","https://openalex.org/W2130689396","https://openalex.org/W1564062815","https://openalex.org/W2274685338","https://openalex.org/W179346709","https://openalex.org/W275138538"],"abstract_inverted_index":{"A":[0],"common":[1,148],"approach":[2,33,82],"to":[3,13,24,58,83,133,142,146],"the":[4,15,25,97,105,116,135,147],"automatic":[5,98],"detection":[6],"of":[7,28,74,123,137],"mispronunciation":[8,76],"in":[9,70,96],"language":[10],"learning":[11],"is":[12,50,131],"recognize":[14],"phonemes":[16,39],"produced":[17],"by":[18,140],"a":[19,29,51,56,71,80],"student":[20],"and":[21,126],"compare":[22],"it":[23,130],"expected":[26],"pronunciation":[27],"native":[30],"speaker.":[31],"This":[32],"makes":[34],"two":[35,89],"simplifying":[36],"assumptions:":[37],"a)":[38,91],"can":[40,68],"be":[41,59,110],"recognized":[42],"from":[43],"speech":[44,122],"with":[45],"high":[46],"accuracy,":[47],"b)":[48,102],"there":[49,108],"single":[52],"correct":[53],"way":[54],"for":[55,104],"sentence":[57],"pronounced.":[60],"These":[61],"assumptions":[62],"do":[63],"not":[64],"always":[65],"hold,":[66],"which":[67],"result":[69],"significant":[72],"amount":[73],"false":[75],"alarms.":[77],"We":[78,114],"propose":[79],"novel":[81],"overcome":[84],"this":[85],"problem":[86],"based":[87],"on":[88,118],"principles:":[90],"taking":[92],"into":[93],"account":[94],"uncertainty":[95],"phoneme":[99],"recognition":[100],"step,":[101],"accounting":[103],"fact":[106],"that":[107],"may":[109],"multiple":[111],"valid":[112],"pronunciations.":[113],"evaluate":[115],"model":[117],"non-native":[119],"(L2)":[120],"English":[121],"German,":[124],"Italian":[125],"Polish":[127],"speakers,":[128],"where":[129],"shown":[132],"increase":[134],"precision":[136],"detecting":[138],"mispronunciations":[139],"up":[141],"18%":[143],"(relative)":[144],"compared":[145],"approach.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
