{"id":"https://openalex.org/W3008371301","doi":"https://doi.org/10.1109/asru46091.2019.9003863","title":"Towards Real-Time Mispronunciation Detection in Kids' Speech","display_name":"Towards Real-Time Mispronunciation Detection in Kids' Speech","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008371301","doi":"https://doi.org/10.1109/asru46091.2019.9003863","mag":"3008371301"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003863","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5055583643","display_name":"Peter Plantinga","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Plantinga","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"690","last_page":"696"},"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":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.7675818204879761},{"id":"https://openalex.org/keywords/silence","display_name":"Silence","score":0.6611349582672119},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6606403589248657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5329305529594421},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.51947420835495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008308947086334},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15164390206336975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675818204879761},{"id":"https://openalex.org/C2781115785","wikidata":"https://www.wikidata.org/wiki/Q502261","display_name":"Silence","level":2,"score":0.6611349582672119},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6606403589248657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5329305529594421},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.51947420835495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008308947086334},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15164390206336975},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003863","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1970870811","https://openalex.org/W2067517679","https://openalex.org/W2070233361","https://openalex.org/W2127141656","https://openalex.org/W2134797427","https://openalex.org/W2291513470","https://openalex.org/W2400818677","https://openalex.org/W2406502879","https://openalex.org/W2552635739","https://openalex.org/W2745937416","https://openalex.org/W2892008152","https://openalex.org/W2913178639","https://openalex.org/W2936993002","https://openalex.org/W2938359332","https://openalex.org/W2963211739","https://openalex.org/W2963736842","https://openalex.org/W6638523607","https://openalex.org/W6679909955"],"related_works":["https://openalex.org/W2140535326","https://openalex.org/W1607271848","https://openalex.org/W2734809835","https://openalex.org/W2316014825","https://openalex.org/W2184961913","https://openalex.org/W1965764303","https://openalex.org/W2214987084","https://openalex.org/W1964726586","https://openalex.org/W3008391423","https://openalex.org/W1610198088"],"abstract_inverted_index":{"Modern":[0],"mispronunciation":[1],"detection":[2,167],"and":[3,164],"diagnosis":[4],"systems":[5,21],"have":[6,22],"seen":[7],"significant":[8],"gains":[9],"in":[10,32,37],"accuracy":[11],"due":[12],"to":[13,29,65,67,86,132],"the":[14,27,45,99,134,150,159,162,166],"introduction":[15],"of":[16,84,101,161],"deep":[17],"learning.":[18],"However,":[19],"these":[20,141,156,173],"not":[23,118],"been":[24],"evaluated":[25],"for":[26,97],"ability":[28],"be":[30,56],"run":[31],"real-time,":[33],"an":[34,107],"important":[35],"factor":[36],"applications":[38],"that":[39,111,155],"provide":[40],"rapid":[41],"feedback.":[42],"In":[43],"particular,":[44],"state-of-the-art":[46],"uses":[47,125,140],"bi-directional":[48,135,143],"recurrent":[49],"networks,":[50],"where":[51],"a":[52,62,69,75,126,170],"uni-directional":[53,70,127],"network":[54],"may":[55],"more":[57],"appropriate.":[58],"Teacher-student":[59],"learning":[60],"is":[61,79,106],"natural":[63],"approach":[64],"use":[66],"improve":[68,165],"model,":[71],"but":[72],"when":[73,115],"using":[74],"CTC":[76],"objective,":[77],"this":[78,90],"limited":[80],"by":[81,92],"poor":[82],"alignment":[83],"outputs":[85,113],"evidence.":[87],"We":[88],"address":[89],"limitation":[91],"trying":[93],"two":[94],"loss":[95,105,123],"terms":[96],"improving":[98],"alignments":[100],"our":[102],"models.":[103,147],"One":[104],"\u201calignment":[108],"loss\u201d":[109],"term":[110,124],"encourages":[112],"only":[114],"features":[116],"do":[117],"resemble":[119],"silence.":[120],"The":[121],"other":[122],"model":[128,131,139],"as":[129,145],"teacher":[130,146],"align":[133],"model.":[136],"Our":[137],"proposed":[138],"aligned":[142],"models":[144],"Experiments":[148],"on":[149],"CSLU":[151],"kids'":[152],"corpus":[153],"show":[154],"changes":[157],"decrease":[158],"latency":[160],"outputs,":[163],"rates,":[168],"with":[169],"trade-off":[171],"between":[172],"goals.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}