{"id":"https://openalex.org/W1999114171","doi":"https://doi.org/10.1109/taslp.2015.2409733","title":"Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection","display_name":"Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation Detection","publication_year":2015,"publication_date":"2015-03-06","ids":{"openalex":"https://openalex.org/W1999114171","doi":"https://doi.org/10.1109/taslp.2015.2409733","mag":"1999114171"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2409733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2409733","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/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","School of Information Science and Engineering, Xinjiang University Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["Temasek laboratories, Nanyang Technological University, Singapore","Temasek Laboratories, \u00a0Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Temasek laboratories, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Temasek Laboratories, \u00a0Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianhui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianhui Wang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","School of Information Science and Engineering, Xinjiang University Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063120015","display_name":"Wushour Silamu","orcid":"https://orcid.org/0000-0003-4592-7806"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wushour Silamu","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","School of Information Science and Engineering, Xinjiang University Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3224,"has_fulltext":false,"cited_by_count":142,"citation_normalized_percentile":{"value":0.96258592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"23","issue":"4","first_page":"787","last_page":"797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9909999966621399,"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":0.9909999966621399,"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/T10320","display_name":"Neural Networks and Applications","score":0.9901999831199646,"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":0.9847999811172485,"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":0.8683574199676514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5190197229385376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48434507846832275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47642073035240173},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.454026997089386},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4517969787120819},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35029661655426025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3490263819694519},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.051446765661239624}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8683574199676514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5190197229385376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48434507846832275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47642073035240173},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.454026997089386},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4517969787120819},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35029661655426025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3490263819694519},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.051446765661239624},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2015.2409733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2409733","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":[],"awards":[{"id":"https://openalex.org/G2476734129","display_name":"\u9762\u5411\u65b0\u7586\u5c11\u6570\u6c11\u65cf\u6c49\u8bed\u8bed\u8a00\u5b66\u4e60\u7684\u81ea\u52a8\u53d1\u97f3\u9519\u8bef\u68c0\u6d4b\u65b9\u6cd5\u7684\u7814\u7a76","funder_award_id":"60965002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G546115561","display_name":"\u53e3\u8bed\u5bf9\u8bdd\u7cfb\u7edf\u6280\u672f\u5728\u81ea\u7531\u8868\u8ff0\u8bed\u8a00\u5b66\u4e60\u4e2d\u7684\u5e94\u7528\u7814\u7a76-\u4ee5\u65b0\u7586\u5c11\u6570\u6c11\u65cf\u5b66\u751f\u7684\u666e\u901a\u8bdd\u5b66\u4e60\u4e3a\u4f8b","funder_award_id":"61365005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W21911835","https://openalex.org/W149618481","https://openalex.org/W290344559","https://openalex.org/W1877570817","https://openalex.org/W1950777589","https://openalex.org/W1965370992","https://openalex.org/W1970870811","https://openalex.org/W1999494183","https://openalex.org/W2008834750","https://openalex.org/W2045459610","https://openalex.org/W2049905800","https://openalex.org/W2063541597","https://openalex.org/W2097427452","https://openalex.org/W2104448323","https://openalex.org/W2124629003","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2130179707","https://openalex.org/W2131342762","https://openalex.org/W2134218976","https://openalex.org/W2137469438","https://openalex.org/W2139008940","https://openalex.org/W2164115090","https://openalex.org/W2398741870","https://openalex.org/W2401656258","https://openalex.org/W2402640444","https://openalex.org/W2402676007","https://openalex.org/W2404722202","https://openalex.org/W4293775970","https://openalex.org/W6603374476","https://openalex.org/W6672317430","https://openalex.org/W6678976218","https://openalex.org/W6682398751","https://openalex.org/W6712626004","https://openalex.org/W6713490435","https://openalex.org/W6738693003"],"related_works":["https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W74886973","https://openalex.org/W2024160000","https://openalex.org/W82679236","https://openalex.org/W2773500201","https://openalex.org/W1990254706","https://openalex.org/W4287995534","https://openalex.org/W2743258233","https://openalex.org/W2998168123"],"abstract_inverted_index":{"We":[0,63,85,93],"carry":[1],"out":[2],"an":[3],"in-depth":[4],"investigation":[5],"on":[6,79],"a":[7,56,95,103],"newly":[8],"proposed":[9],"Maximum":[10],"F1-score":[11,48,53,132,213],"Criterion":[12],"(MFC)":[13],"discriminative":[14,91],"training":[15,66,124,127,144,154,157,191,219],"objective":[16,58],"function":[17,54,59,83],"for":[18],"Goodness":[19],"of":[20,30,42,100,173,186,217],"Pronunciation":[21],"(GOP)":[22],"based":[23,78,89,122],"automatic":[24],"mispronunciation":[25,180],"detection":[26,118,181],"that":[27,193],"makes":[28],"use":[29,185],"Gaussian":[31],"Mixture":[32],"Model-hidden":[33],"Markov":[34],"model":[35],"(GMM-HMM)":[36],"as":[37],"acoustic":[38],"models.":[39],"The":[40,201],"formulation":[41],"MFC":[43,70,88,121,143,187],"seeks":[44],"to":[45,60,69,102,113],"directly":[46],"optimize":[47],"by":[49],"converting":[50],"the":[51,80,110,147,165,184,210],"non-differentiable":[52],"into":[55,209],"continuous":[57],"facilitate":[61],"optimization.":[62],"present":[64,87],"model-space":[65,123,150,153],"algorithm":[67],"according":[68],"using":[71],"extended":[72],"Baum\u2013Welch":[73],"form":[74],"like":[75],"update":[76],"equations":[77],"weak-sense":[81],"auxiliary":[82],"method.":[84],"then":[86],"feature-space":[90,126,148,156],"training.":[92],"train":[94],"matrix":[96],"projecting":[97],"from":[98],"posteriors":[99],"Gaussians":[101],"normal":[104],"size":[105],"feature":[106],"space,":[107],"and":[108,125,133,149,159,178,188,204,215],"add":[109],"projected":[111],"features":[112],"traditional":[114,190],"spectral":[115],"features.":[116],"Mispronunciation":[117],"experiments":[119],"show":[120],"are":[128],"effective":[129],"in":[130,145,171,198],"improving":[131],"other":[134],"commonly":[135],"used":[136],"evaluation":[137],"metrics.":[138],"It":[139],"is":[140,160],"also":[141],"shown":[142],"both":[146],"outperforms":[151],"either":[152],"or":[155],"alone,":[158],"about":[161],"11.6%":[162],"better":[163],"than":[164],"maximum":[166],"likelihood":[167],"(ML)":[168],"trained":[169],"baseline":[170],"terms":[172],"F1-score.":[174],"Further,":[175],"we":[176],"review":[177],"compare":[179],"results":[182],"with":[183],"some":[189],"criteria":[192],"minimize":[194],"word":[195],"error":[196],"rate":[197],"speech":[199],"recognition.":[200],"experimental":[202],"analysis":[203],"comparison":[205],"provide":[206],"useful":[207],"insight":[208],"correlations":[211],"between":[212],"maximization":[214],"optimization":[216],"these":[218],"criteria.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}