{"id":"https://openalex.org/W3166077906","doi":"https://doi.org/10.21437/interspeech.2021-38","title":"Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech","display_name":"Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3166077906","doi":"https://doi.org/10.21437/interspeech.2021-38","mag":"3166077906"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2106.03494","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":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054373836","display_name":"Shira Calamaro","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shira Calamaro","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"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":["Gda\u0144sk University of Technology, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gda\u0144sk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9976000189781189,"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":0.8071107864379883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392248511314392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7102721929550171},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5847654342651367},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5697411298751831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5148352980613708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5131638646125793},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4801078140735626},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.4671606123447418},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4575760066509247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2602139711380005}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8071107864379883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392248511314392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7102721929550171},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5847654342651367},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5697411298751831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5148352980613708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5131638646125793},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4801078140735626},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4671606123447418},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4575760066509247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2602139711380005},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-38","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-38","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.03494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.03494","pdf_url":"https://arxiv.org/pdf/2106.03494","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:3166077906","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.03494","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.2106.03494","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.03494","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.03494","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.03494","pdf_url":"https://arxiv.org/pdf/2106.03494","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":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3166077906.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W11805017","https://openalex.org/W108866686","https://openalex.org/W854541894","https://openalex.org/W1505400583","https://openalex.org/W1515154287","https://openalex.org/W1586532344","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/W2164810574","https://openalex.org/W2186615578","https://openalex.org/W2295721380","https://openalex.org/W2400751463","https://openalex.org/W2400818677","https://openalex.org/W2552635739","https://openalex.org/W2889480449","https://openalex.org/W2962826786","https://openalex.org/W2963403868","https://openalex.org/W2963799213","https://openalex.org/W2972347929","https://openalex.org/W2972359262","https://openalex.org/W2972812366","https://openalex.org/W2974489302","https://openalex.org/W3008371301","https://openalex.org/W3008618223","https://openalex.org/W3011307848","https://openalex.org/W3081817774","https://openalex.org/W3100647618","https://openalex.org/W3114586309","https://openalex.org/W3124560983","https://openalex.org/W3125709657"],"related_works":["https://openalex.org/W3196676570","https://openalex.org/W2017743450","https://openalex.org/W3205234329","https://openalex.org/W2810104656","https://openalex.org/W1894018451","https://openalex.org/W2071162251","https://openalex.org/W2230441926","https://openalex.org/W1579089397","https://openalex.org/W2168911071","https://openalex.org/W2795003080","https://openalex.org/W141348503","https://openalex.org/W143242639","https://openalex.org/W2620301616","https://openalex.org/W2073211979","https://openalex.org/W1513016810","https://openalex.org/W654092675","https://openalex.org/W1990856848","https://openalex.org/W2167161853","https://openalex.org/W2400818677","https://openalex.org/W2157075408"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,50,84,104],"weakly-supervised":[3],"model":[4,44,70],"for":[5,38],"word-level":[6,54,96,132],"mispronunciation":[7],"detection":[8],"in":[9,83,135],"non-native":[10],"(L2)":[11],"English":[12],"speech.":[13],"To":[14,76],"train":[15,81],"this":[16,78],"model,":[17],"phonetically":[18,109],"transcribed":[19,110],"L2":[20,39,67,146,157],"speech":[21,40,112],"is":[22,71,114],"not":[23],"required":[24],"and":[25,59,117,149,159],"we":[26,80,91,102,126],"only":[27,48],"need":[28],"to":[29,46,61,74,123],"mark":[30],"mispronounced":[31,66],"words.":[32],"The":[33],"lack":[34],"of":[35,53,57,65,95,130,145,156],"phonetic":[36],"transcriptions":[37],"means":[41],"that":[42,58,113],"the":[43,62,69,88,93,99,128,141,153],"has":[45],"learn":[47],"from":[49],"weak":[51],"signal":[52],"mispronunciations.":[55],"Because":[56],"due":[60],"limited":[63],"amount":[64],"speech,":[68],"more":[72],"likely":[73],"overfit.":[75],"limit":[77],"risk,":[79],"it":[82],"multi-task":[85],"setup.":[86],"In":[87],"first":[89],"task,":[90,101],"estimate":[92],"probabilities":[94],"mispronunciation.":[97],"For":[98],"second":[100],"use":[103],"phoneme":[105],"recognizer":[106],"trained":[107],"on":[108,140,152],"L1":[111],"easily":[115],"accessible":[116],"can":[118],"be":[119],"automatically":[120],"annotated.":[121],"Compared":[122],"state-of-the-art":[124],"approaches,":[125],"improve":[127],"accuracy":[129],"detecting":[131],"pronunciation":[133],"errors":[134],"AUC":[136],"metric":[137],"by":[138,150],"30%":[139],"GUT":[142],"Isle":[143,154],"Corpus":[144,155],"Polish":[147],"speakers,":[148],"21.5%":[151],"German":[158],"Italian":[160],"speakers.":[161]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}