{"id":"https://openalex.org/W2370418772","doi":"https://doi.org/10.1109/taslp.2016.2526782","title":"A Two-Pass Framework of Mispronunciation Detection and Diagnosis for Computer-Aided Pronunciation Training","display_name":"A Two-Pass Framework of Mispronunciation Detection and Diagnosis for Computer-Aided Pronunciation Training","publication_year":2016,"publication_date":"2016-02-08","ids":{"openalex":"https://openalex.org/W2370418772","doi":"https://doi.org/10.1109/taslp.2016.2526782","mag":"2370418772"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2526782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2526782","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"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":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"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":6.6654,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96762503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"24","issue":"6","first_page":"1020","last_page":"1028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9857000112533569,"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/discriminative-model","display_name":"Discriminative model","score":0.8955113887786865},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7556646466255188},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7506086230278015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6980544924736023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6591050028800964},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6428185701370239},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37084686756134033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33036404848098755},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09177163243293762}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8955113887786865},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7556646466255188},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7506086230278015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6980544924736023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591050028800964},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6428185701370239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37084686756134033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33036404848098755},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09177163243293762},{"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:10.1109/taslp.2016.2526782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2526782","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329815","display_name":"Hong Kong Government","ror":"https://ror.org/034179816"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W67753814","https://openalex.org/W70727784","https://openalex.org/W103312509","https://openalex.org/W290344559","https://openalex.org/W323265179","https://openalex.org/W1496430420","https://openalex.org/W1506404588","https://openalex.org/W1535086474","https://openalex.org/W1842528305","https://openalex.org/W1884048561","https://openalex.org/W1931766939","https://openalex.org/W1965044932","https://openalex.org/W1999845150","https://openalex.org/W2008834750","https://openalex.org/W2026501739","https://openalex.org/W2027993708","https://openalex.org/W2034537249","https://openalex.org/W2049905800","https://openalex.org/W2051811941","https://openalex.org/W2062516439","https://openalex.org/W2063915318","https://openalex.org/W2067517679","https://openalex.org/W2071650246","https://openalex.org/W2093826182","https://openalex.org/W2137268753","https://openalex.org/W2139008940","https://openalex.org/W2156178627","https://openalex.org/W2400751463","https://openalex.org/W2403848074","https://openalex.org/W2405178423","https://openalex.org/W3105803047","https://openalex.org/W4234400994","https://openalex.org/W4254960454","https://openalex.org/W4390912981","https://openalex.org/W6602686748","https://openalex.org/W6602874765","https://openalex.org/W6611059293","https://openalex.org/W6629639235","https://openalex.org/W6650297668","https://openalex.org/W6683243209","https://openalex.org/W6713148202","https://openalex.org/W6713543713","https://openalex.org/W6713547206","https://openalex.org/W6860681269","https://openalex.org/W7075740705"],"related_works":["https://openalex.org/W2162582511","https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"presents":[2],"a":[3,33,38,208],"two-pass":[4],"framework":[5,31],"with":[6,172,188,212],"discriminative":[7],"acoustic":[8,146,162],"modeling":[9],"for":[10,47],"mispronunciation":[11,20,112,136,150,155],"detection":[12,21,151],"and":[13,37,85,118,123,153,168,216],"diagnoses":[14],"(MD&D).":[15],"The":[16,30,71,79,108],"first":[17],"pass":[18,110,126,152],"of":[19,35,55,111,133,148,164,177,198,207],"does":[22],"not":[23],"require":[24],"explicit":[25],"phonetic":[26,64,131],"error":[27,58,103,180,196],"pattern":[28],"modeling.":[29],"instantiates":[32],"set":[34],"antiphones":[36,72],"filler":[39,80],"model":[40,46,81],"to":[41,76,90,128,144],"augment":[42],"the":[43,63,68,101,115,130,134,145,149,154,161,165,169,179,189,195,199],"original":[44],"phone":[45,86,121],"each":[48],"canonical":[49,166],"phone.":[50],"guarantees":[52],"full":[53],"coverage":[54],"all":[56],"possible":[57,102],"patterns":[59,104],"while":[60],"maximally":[61],"exploiting":[62],"information":[65],"derived":[66],"from":[67],"text":[69],"prompt.":[70],"can":[73,82,106],"be":[74],"used":[75],"detect":[77,83,91],"substitutions.":[78],"insertions,":[84],"skips":[87],"are":[88,202,220],"allowed":[89],"deletions.":[92],"As":[93],"such,":[94],"there":[95],"is":[96,141,182],"no":[97],"prior":[98],"assumption":[99],"on":[100],"that":[105],"occur.":[107],"second":[109],"diagnosis":[113,156],"expands":[114],"detected":[116,135],"insertions":[117],"substitutions":[119],"into":[120],"networks,":[122],"another":[124],"recognition":[125],"attempts":[127],"reveal":[129],"identities":[132],"errors.":[137],"Discriminative":[138],"training":[139],"(DT)":[140],"applied":[142],"respectively":[143],"models":[147,163],"pass.":[157],"DT":[158,173,213],"effectively":[159],"separates":[160],"phones":[167],"antiphones.":[170],"Overall,":[171],"in":[174],"both":[175],"passes":[176,201],"MD&D,":[178],"rate":[181],"reduced":[183],"by":[184,214],"40.4%":[185],"relative,":[186],"compared":[187],"maximum":[190],"likelihood":[191],"baseline.":[192],"After":[193],"DT,":[194],"rates":[197],"respective":[200],"also":[203],"lower":[204],"than":[205],"those":[206],"strong":[209],"single-pass":[210],"baseline":[211],"1.3%":[215],"5.1%":[217],"relative":[218],"which":[219],"statistically":[221],"significant.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}