{"id":"https://openalex.org/W2990215159","doi":"https://doi.org/10.1145/3364908.3365302","title":"The Use of SDAE in Noisy English Mispronunciation Detection and Diagnosis towards Application in Mobile Learning","display_name":"The Use of SDAE in Noisy English Mispronunciation Detection and Diagnosis towards Application in Mobile Learning","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2990215159","doi":"https://doi.org/10.1145/3364908.3365302","mag":"2990215159"},"language":"en","primary_location":{"id":"doi:10.1145/3364908.3365302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3364908.3365302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Symposium on Signal Processing Systems","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/A5100301343","display_name":"Yizhi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhi Wu","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China, Shanghai","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343044","display_name":"Junjie Zhang","orcid":"https://orcid.org/0000-0002-0033-0494"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zhang","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China, Shanghai","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053353345","display_name":"Quanfeng Dong","orcid":"https://orcid.org/0000-0002-4886-3361"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Dong","raw_affiliation_strings":["College of Information Science and Technology, Donghua University, China, Shanghai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Donghua University, China, Shanghai","institution_ids":["https://openalex.org/I181326427"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976000189781189,"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":0.9797000288963318,"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":0.7369807362556458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6550552845001221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5514267683029175},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.47443047165870667},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4512544870376587},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4352670907974243},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.430658221244812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3782182037830353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7369807362556458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6550552845001221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514267683029175},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.47443047165870667},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4512544870376587},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4352670907974243},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.430658221244812},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3782182037830353},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3364908.3365302","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3364908.3365302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Symposium on Signal Processing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W290344559","https://openalex.org/W296713244","https://openalex.org/W1496430420","https://openalex.org/W1496979626","https://openalex.org/W1563276533","https://openalex.org/W1997900929","https://openalex.org/W2105961775","https://openalex.org/W2118163005","https://openalex.org/W2145094598","https://openalex.org/W2401896499","https://openalex.org/W2404637451","https://openalex.org/W2405774341","https://openalex.org/W2751911807","https://openalex.org/W4239638394","https://openalex.org/W6629639235","https://openalex.org/W6681096077","https://openalex.org/W6743838540"],"related_works":["https://openalex.org/W2092619848","https://openalex.org/W3108403339","https://openalex.org/W383418545","https://openalex.org/W2020163257","https://openalex.org/W4367628250","https://openalex.org/W2023005931","https://openalex.org/W3005783148","https://openalex.org/W3190667789","https://openalex.org/W4287867034","https://openalex.org/W2076268407"],"abstract_inverted_index":{"The":[0,77,95,126,160],"problem":[1,29],"of":[2,13,83,92,97,119,143,158,177],"noise":[3,28],"in":[4,10,23,30,62,73,171],"the":[5,11,27,81,84,98,116,141,146,156,175],"environment":[6],"is":[7,46,66,86],"a":[8,33,54,135,168],"bottleneck":[9],"application":[12],"computer":[14],"assisted":[15],"pronunciation":[16,150],"training":[17],"(CAPT)":[18],"system.":[19],"In":[20],"this":[21],"paper,":[22],"order":[24],"to":[25,59,68,88,121,133],"solve":[26],"mobile":[31,179],"learning,":[32],"mispronunciation":[34,61,137,172],"detection":[35,138,173],"and":[36,106,145],"diagnosis":[37],"(MD-D)":[38],"model":[39,132],"based":[40,56],"on":[41],"stack":[42],"denoising":[43],"autoencoder":[44],"(SDAE)":[45],"proposed":[47],"for":[48],"noisy":[49,63,75,178],"English":[50],"phonemes.":[51],"We":[52,109],"built":[53],"SDAE":[55,65,99,120],"recognition":[57],"network":[58,85,100],"detect":[60],"speech.":[64],"used":[67,87,110,129],"obtain":[69,134],"robust":[70],"data":[71],"features":[72],"different":[74],"environments.":[76],"classifier":[78],"layer":[79],"at":[80],"top":[82],"generate":[89],"posterior":[90],"probability":[91],"error":[93],"types.":[94],"parameters":[96],"are":[101],"obtained":[102],"through":[103],"unsupervised":[104],"pretraining":[105],"supervised":[107],"fine-tuning.":[108],"rectified":[111],"linear":[112],"unit":[113],"(ReLU)":[114],"as":[115],"activation":[117],"function":[118],"get":[122],"more":[123],"advanced":[124],"features.":[125],"verification":[127],"experiment":[128],"SDAE-based":[130],"MDD":[131],"better":[136],"performance":[139,157],"using":[140],"dataset":[142],"NOISE-92":[144],"Speech":[147],"Accent":[148],"Archive":[149],"corpus":[151],"with":[152],"varied":[153],"SNR":[154],"than":[155],"SVM.":[159],"experimental":[161],"results":[162],"showed":[163],"that":[164],"our":[165],"work":[166],"provided":[167],"new":[169],"example":[170],"under":[174],"situation":[176],"learning.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}