{"id":"https://openalex.org/W2977330202","doi":"https://doi.org/10.1109/ijcnn.2019.8851963","title":"Detection of Typical Pronunciation Errors in Non-native English Speech Using Convolutional Recurrent Neural Networks","display_name":"Detection of Typical Pronunciation Errors in Non-native English Speech Using Convolutional Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977330202","doi":"https://doi.org/10.1109/ijcnn.2019.8851963","mag":"2977330202"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8851963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5013473819","display_name":"Aleksandr Diment","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Aleksandr Diment","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079667068","display_name":"Eemi Fagerlund","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eemi Fagerlund","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049650295","display_name":"Adrian Benfield","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Adrian Benfield","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013473819"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.8401,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80598174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8029273748397827},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6963696479797363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6603783965110779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6115179061889648},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5612875819206238},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5326839089393616},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4828508496284485},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.43238356709480286},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.41823437809944153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3785461485385895},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1055578887462616},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07235139608383179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029273748397827},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6963696479797363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6603783965110779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115179061889648},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5612875819206238},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5326839089393616},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4828508496284485},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.43238356709480286},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.41823437809944153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3785461485385895},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1055578887462616},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07235139608383179},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8851963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8851963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1560013842","https://openalex.org/W1585763212","https://openalex.org/W1600744878","https://openalex.org/W1836465849","https://openalex.org/W1979364015","https://openalex.org/W1984541135","https://openalex.org/W2011301426","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2106411961","https://openalex.org/W2113207845","https://openalex.org/W2128389066","https://openalex.org/W2130689396","https://openalex.org/W2131774270","https://openalex.org/W2148154194","https://openalex.org/W2212703438","https://openalex.org/W2291868800","https://openalex.org/W2340233583","https://openalex.org/W2342249984","https://openalex.org/W2403588201","https://openalex.org/W2591013610","https://openalex.org/W2963266340","https://openalex.org/W2963414797","https://openalex.org/W2963451564","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W6631190155","https://openalex.org/W6635132915","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6675354045","https://openalex.org/W6676179485","https://openalex.org/W6677088747","https://openalex.org/W6688167117","https://openalex.org/W6703928569","https://openalex.org/W6713665620","https://openalex.org/W6743611570","https://openalex.org/W6992206719"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W4206951940","https://openalex.org/W4382602594","https://openalex.org/W4387850423"],"abstract_inverted_index":{"A":[0,110],"machine":[1],"learning":[2],"method":[3],"for":[4,38],"the":[5,46,52,91,125,134,148,158],"automatic":[6],"detection":[7],"of":[8,15,21,30,60,67,71,90,112,124,133,141,147],"pronunciation":[9,35,143],"errors":[10,144],"made":[11],"by":[12,117],"non-native":[13],"speakers":[14,119],"English":[16],"is":[17,49,120,139],"proposed.":[18],"It":[19],"consists":[20],"training":[22],"word-specific":[23],"binary":[24],"classifiers":[25,43],"on":[26,58,129],"a":[27,72,79,83,88,101,106,130],"collected":[28],"dataset":[29,111],"isolated":[31],"words":[32,114,149],"with":[33,151],"possible":[34],"errors,":[36],"typical":[37,47],"Finnish":[39],"native":[40],"speakers.":[41],"The":[42,75,93,122],"predict":[44],"whether":[45],"error":[48],"present":[50],"in":[51,100,145],"given":[53],"word":[54,73],"utterance.":[55,74],"They":[56],"operate":[57],"sequences":[59],"acoustic":[61],"features,":[62],"extracted":[63],"from":[64],"consecutive":[65],"frames":[66],"an":[68],"audio":[69],"recording":[70],"proposed":[76,126],"architecture":[77],"includes":[78],"convolutional":[80],"neural":[81,85],"network,":[82,86],"recurrent":[84],"or":[87],"combination":[89],"two.":[92],"optimal":[94],"topology":[95],"and":[96],"hyperparameters":[97],"are":[98],"obtained":[99],"Bayesian":[102],"optimisation":[103],"setting":[104],"using":[105],"tree-structured":[107],"Parzen":[108],"estimator.":[109],"80":[113],"uttered":[115],"naturally":[116],"120":[118],"collected.":[121],"performance":[123],"system,":[127],"evaluated":[128],"well-represented":[131],"subset":[132],"dataset,":[135],"shows":[136],"that":[137],"it":[138],"capable":[140],"detecting":[142],"most":[146],"(46/49)":[150],"high":[152],"accuracy":[153,155],"(mean":[154],"gain":[156],"over":[157],"zero":[159],"rule":[160],"12.21":[161],"percent":[162],"points).":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}