{"id":"https://openalex.org/W296713244","doi":"https://doi.org/10.21437/interspeech.2010-278","title":"Discriminative acoustic model for improving mispronunciation detection and diagnosis in computer-aided pronunciation training (CAPT)","display_name":"Discriminative acoustic model for improving mispronunciation detection and diagnosis in computer-aided pronunciation training (CAPT)","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W296713244","doi":"https://doi.org/10.21437/interspeech.2010-278","mag":"296713244"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-278","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5101881032","display_name":"Xiaojun Qian","orcid":"https://orcid.org/0000-0002-6026-8928"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojun Qian","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102225156","display_name":"Helen Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101881032"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.0717,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93593442,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"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":0.9998999834060669,"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":0.9973999857902527,"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":0.9965000152587891,"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":0.9216090440750122},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.886101245880127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251714468002319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6433653831481934},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5159855484962463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4307646155357361},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1725127398967743}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9216090440750122},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.886101245880127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251714468002319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6433653831481934},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5159855484962463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307646155357361},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1725127398967743},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":1,"locations":[{"id":"doi:10.21437/interspeech.2010-278","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W275138538","https://openalex.org/W1513168562","https://openalex.org/W2002342963","https://openalex.org/W2137268753","https://openalex.org/W2400818677"],"related_works":["https://openalex.org/W2158840414","https://openalex.org/W1970028996","https://openalex.org/W2112711188","https://openalex.org/W2362984804","https://openalex.org/W2375931456","https://openalex.org/W2043006378","https://openalex.org/W4384912414","https://openalex.org/W4384912146","https://openalex.org/W1585763212","https://openalex.org/W2578163670"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"propose":[4],"a":[5,134],"discriminative":[6,44,118],"training":[7,63,116,119,142],"algorithm":[8],"to":[9,39,48,55,133],"jointly":[10],"minimize":[11],"mispronunciation":[12],"detection":[13],"errors":[14,23,54],"(i.e.,":[15,24],"false":[16,19,122,128],"rejections":[17,123],"and":[18,21,77,124],"acceptances)":[20],"diagnosis":[22],"correctly":[25],"pinpointing":[26],"mispronunciations":[27],"but":[28],"incorrectly":[29],"stating":[30],"how":[31],"they":[32],"are":[33,58,102],"wrong).":[34],"An":[35],"optimization":[36],"procedure,":[37],"similar":[38],"Minimum":[40],"Word":[41],"Error":[42],"(MWE)":[43],"training,":[45],"is":[46,83],"developed":[47],"refine":[49],"the":[50,97,114,141],"ML-trained":[51],"HMMs.":[52],"The":[53,81],"be":[56,94],"minimized":[57],"obtained":[59],"by":[60,85],"comparing":[61],"transcribed":[62],"utterances":[64],"(including":[65],"mispronunciations)":[66],"with":[67,113],"Extended":[68],"Recognition":[69],"Networks":[70],"[3]":[71],"which":[72],"contain":[73],"both":[74],"canonical":[75],"pronunciations":[76],"explicitly":[78],"modeled":[79],"mispronunciations.":[80],"ERN":[82],"compiled":[84],"handcrafted":[86],"rules,":[87],"or":[88],"data-driven":[89,100],"rules.":[90],"Several":[91],"conclusions":[92],"can":[93,120],"drawn":[95],"from":[96],"experiments:":[98],"(1)":[99],"rules":[101],"more":[103],"effective":[104],"than":[105],"hand-crafted":[106],"ones":[107],"in":[108,140],"capturing":[109],"mispronunciations;":[110],"(2)":[111],"compared":[112],"ML":[115],"baseline,":[117],"reduce":[121],"diagnostic":[125],"errors,":[126],"though":[127],"acceptances":[129],"increase":[130],"slightly":[131],"due":[132],"small":[135],"number":[136],"of":[137],"false-acceptance":[138],"samples":[139],"set.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}