{"id":"https://openalex.org/W2095479218","doi":"https://doi.org/10.1109/icassp.2014.6855100","title":"Adaptive and discriminative modeling for improved mispronunciation detection","display_name":"Adaptive and discriminative modeling for improved mispronunciation detection","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2095479218","doi":"https://doi.org/10.1109/icassp.2014.6855100","mag":"2095479218"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6855100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5112857367","display_name":"Horacio Franco","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Horacio Franco","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051405063","display_name":"Harry Bratt","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Bratt","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7709","last_page":"7713"},"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":0.9958000183105469,"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":0.995199978351593,"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/discriminative-model","display_name":"Discriminative model","score":0.8003010153770447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.785995602607727},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7299920320510864},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7207640409469604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6017636060714722},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5658243298530579},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.560193657875061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5592512488365173},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5341725945472717},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4528034031391144},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4356302320957184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37675389647483826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37298527359962463},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09083613753318787}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8003010153770447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.785995602607727},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7299920320510864},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7207640409469604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6017636060714722},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5658243298530579},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.560193657875061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5592512488365173},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5341725945472717},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4528034031391144},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4356302320957184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37675389647483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37298527359962463},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09083613753318787},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6855100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6855100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.2356","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.2356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/Franco_Ferrer_Bratt_IS_ADEPT.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W42910856","https://openalex.org/W66698146","https://openalex.org/W70727784","https://openalex.org/W103312509","https://openalex.org/W322814586","https://openalex.org/W1576520375","https://openalex.org/W1585763212","https://openalex.org/W1842528305","https://openalex.org/W1868985557","https://openalex.org/W1931766939","https://openalex.org/W2002664886","https://openalex.org/W2041823554","https://openalex.org/W2086705963","https://openalex.org/W2098773974","https://openalex.org/W2100969003","https://openalex.org/W2139565824","https://openalex.org/W2144760012","https://openalex.org/W2164810574","https://openalex.org/W2402676007","https://openalex.org/W3144372880","https://openalex.org/W6601765995","https://openalex.org/W6602692065","https://openalex.org/W6602874765","https://openalex.org/W6634442568","https://openalex.org/W6635132915","https://openalex.org/W6639086485"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2146591867","https://openalex.org/W2113687551","https://openalex.org/W2112752961"],"abstract_inverted_index":{"In":[0,27,61],"the":[1,69,86],"context":[2],"of":[3,9,71,88,100,117,136],"computer-aided":[4],"language":[5],"learning,":[6],"automatic":[7],"detection":[8],"specific":[10,24],"phone":[11],"mispronunciations":[12,54],"by":[13,50,58,144],"nonnative":[14,59,146],"speakers":[15],"can":[16],"be":[17,36],"used":[18],"to":[19,39,47],"provide":[20],"detailed":[21],"feedback":[22],"about":[23],"pronunciation":[25],"problems.":[26],"previous":[28,153],"work":[29],"we":[30,64],"found":[31],"that":[32,42,81],"significant":[33,149],"improvements":[34,150],"could":[35],"achieved,":[37],"compared":[38],"standard":[40],"approaches":[41],"compute":[43],"posteriors":[44],"with":[45,68],"respect":[46],"native":[48],"models,":[49],"explicitly":[51],"modeling":[52,76],"both":[53],"and":[55,74,105,108,125],"correct":[56],"pronunciations":[57],"speakers.":[60],"this":[62],"work,":[63],"extend":[65],"our":[66,152],"approach":[67],"use":[70],"model":[72],"adaptation":[73,99],"discriminative":[75],"techniques,":[77],"inspired":[78],"on":[79,97,112],"methods":[80],"have":[82],"been":[83],"effective":[84],"in":[85,130,140],"area":[87],"speaker":[89],"identification.":[90],"Two":[91],"systems":[92],"were":[93,128],"developed,":[94],"one":[95,110],"based":[96,111],"Bayesian":[98],"Gaussian":[101],"Mixture":[102],"Models":[103],"(GMMs),":[104],"likelihood-ratio-based":[106],"detection,":[107],"another":[109],"Support":[113],"Vector":[114],"Machines":[115],"classification":[116],"supervectors":[118],"derived":[119],"from":[120,151],"adapted":[121],"GMMs.":[122],"Both":[123],"systems,":[124],"their":[126],"combination,":[127],"evaluated":[129],"a":[131],"phonetically":[132],"transcribed":[133],"Spanish":[134],"database":[135],"130,000":[137],"phones":[138],"uttered":[139],"continuous":[141],"speech":[142],"sentences":[143],"206":[145],"speakers,":[147],"showing":[148],"best":[154],"system.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}