{"id":"https://openalex.org/W2938359332","doi":"https://doi.org/10.1109/icassp.2019.8682654","title":"CNN-RNN-CTC Based End-to-end Mispronunciation Detection and Diagnosis","display_name":"CNN-RNN-CTC Based End-to-end Mispronunciation Detection and Diagnosis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938359332","doi":"https://doi.org/10.1109/icassp.2019.8682654","mag":"2938359332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5078785570","display_name":"Wai-Kim Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wai-Kim Leung","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong Big Data Decision Analytics (BDDA) Research Centre, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.2655,"has_fulltext":false,"cited_by_count":86,"citation_normalized_percentile":{"value":0.95763889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8132","last_page":"8136"},"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":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.7403357028961182},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7165755033493042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6552078127861023},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5909712314605713},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5795482397079468},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48047202825546265},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4539104402065277},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3878624141216278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3371202051639557},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06615987420082092}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7403357028961182},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7165755033493042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6552078127861023},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5909712314605713},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5795482397079468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48047202825546265},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4539104402065277},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3878624141216278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3371202051639557},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06615987420082092},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W290344559","https://openalex.org/W1554982972","https://openalex.org/W1666984270","https://openalex.org/W1978717898","https://openalex.org/W2022399114","https://openalex.org/W2054441760","https://openalex.org/W2091856355","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2137268753","https://openalex.org/W2155273149","https://openalex.org/W2400818677","https://openalex.org/W2401896499","https://openalex.org/W2552635739","https://openalex.org/W2597757402","https://openalex.org/W2963070863","https://openalex.org/W2963403664","https://openalex.org/W6603616073","https://openalex.org/W6610357026","https://openalex.org/W6637061625","https://openalex.org/W6675365184","https://openalex.org/W6713037690","https://openalex.org/W6725896364","https://openalex.org/W6735390525"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W2578422401"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3],"using":[4],"Convolutional":[5],"Neural":[6,10],"Network":[7,11,81],"(CNN),":[8],"Recurrent":[9],"(RNN)":[12],"and":[13,27,64,86,107,114],"Connection-ist":[14],"Temporal":[15],"Classification":[16],"(CTC)":[17],"to":[18],"build":[19],"an":[20],"end-to-end":[21,34],"speech":[22],"recognition":[23],"for":[24],"Mispronunciation":[25],"Detection":[26],"Diagnosis":[28],"(MDD)":[29,66],"task.":[30],"Our":[31],"approach":[32,59,72],"is":[33,73],"models,":[35],"while":[36],"phonemic":[37],"or":[38,41],"graphemic":[39],"information,":[40],"forced":[42],"alignment":[43],"between":[44],"different":[45],"linguistic":[46],"units,":[47],"are":[48,111],"not":[49],"required.":[50],"We":[51],"conduct":[52],"experiments":[53],"that":[54],"compare":[55],"the":[56,78],"proposed":[57],"CNN-RNN-CTC":[58],"with":[60],"alternative":[61],"mispronunciation":[62],"detection":[63],"diagnoses":[65],"approaches.":[67],"The":[68,94],"F-measure":[69,98],"of":[70],"our":[71],"74.65%,":[74],"which":[75],"significantly":[76],"outperforms":[77],"Extended":[79],"Recognition":[80],"(ERN)":[82],"(S-AM)":[83,90],"by":[84,91],"44.75%":[85],"State-level":[87],"Acoustic":[88],"Model":[89,102,105,109],"32.28%":[92],"relatively.":[93],"relative":[95],"improvement":[96],"in":[97],"when":[99],"over":[100],"Acoustic-Phonemic":[101],"(APM),":[103],"Acoustic-Graphemic":[104],"(AGM)":[106],"Acoustic-Phonemic-Graphemic":[108],"(APGM)":[110],"9.57%,":[112],"5.04%":[113],"2.77%":[115],"respectively.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}