{"id":"https://openalex.org/W4312259157","doi":"https://doi.org/10.1109/access.2022.3212417","title":"Self-Supervised Pre-Trained Speech Representation Based End-to-End Mispronunciation Detection and Diagnosis of Mandarin","display_name":"Self-Supervised Pre-Trained Speech Representation Based End-to-End Mispronunciation Detection and Diagnosis of Mandarin","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312259157","doi":"https://doi.org/10.1109/access.2022.3212417"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3212417","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3212417","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2022.3212417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089251855","display_name":"Yunfei Shen","orcid":"https://orcid.org/0000-0002-2085-0163"},"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":"Yunfei Shen","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China","Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0002-2085-0163","affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100740336","display_name":"Qingqing Liu","orcid":"https://orcid.org/0000-0003-1084-6459"},"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":"Qingqing Liu","raw_affiliation_strings":["Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","institution_ids":[]},{"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/A5070689452","display_name":"Zhixing Fan","orcid":"https://orcid.org/0000-0002-1379-8299"},"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":"Zhixing Fan","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China","Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050347","display_name":"Jiajun Liu","orcid":"https://orcid.org/0000-0002-5301-8314"},"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":"Jiajun Liu","raw_affiliation_strings":["School of Software, Xinjiang University, Urumqi, China","Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077794475","display_name":"Aishan Wumaier","orcid":"https://orcid.org/0000-0003-1681-1089"},"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":"Aishan Wumaier","raw_affiliation_strings":["Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0003-1681-1089","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multilingual Information Technology in Xinjiang Uyghur Autonomous Region, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1102,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8197674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"106451","last_page":"106462"},"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":0.9972000122070312,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9905999898910522,"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":0.8405728340148926},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6846672892570496},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6516811847686768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547390341758728},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5403369665145874},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42015692591667175},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4158251881599426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3532153367996216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405728340148926},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6846672892570496},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6516811847686768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547390341758728},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5403369665145874},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42015692591667175},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4158251881599426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3532153367996216},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3212417","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3212417","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:87db50831ae14b0ab1a448c5073525f8","is_oa":true,"landing_page_url":"https://doaj.org/article/87db50831ae14b0ab1a448c5073525f8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 106451-106462 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3212417","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3212417","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6956434356","display_name":null,"funder_award_id":"BNR2021KF02005","funder_id":"https://openalex.org/F4320329777","funder_display_name":"Beijing National Research Center For Information Science And Technology"}],"funders":[{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W275138538","https://openalex.org/W343636949","https://openalex.org/W1828163288","https://openalex.org/W1875231349","https://openalex.org/W1922655562","https://openalex.org/W1970870811","https://openalex.org/W2067517679","https://openalex.org/W2074231493","https://openalex.org/W2091856355","https://openalex.org/W2125534887","https://openalex.org/W2127141656","https://openalex.org/W2139008940","https://openalex.org/W2284628133","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2402640444","https://openalex.org/W2407533274","https://openalex.org/W2696967604","https://openalex.org/W2766219058","https://openalex.org/W2768986418","https://openalex.org/W2842511635","https://openalex.org/W2888954148","https://openalex.org/W2892009249","https://openalex.org/W2894835365","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2938359332","https://openalex.org/W2963403664","https://openalex.org/W2972818416","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981991061","https://openalex.org/W3007328579","https://openalex.org/W3013336802","https://openalex.org/W3015231007","https://openalex.org/W3016010032","https://openalex.org/W3035725276","https://openalex.org/W3036601975","https://openalex.org/W3081817774","https://openalex.org/W3097777922","https://openalex.org/W3134482008","https://openalex.org/W3146505093","https://openalex.org/W3156081754","https://openalex.org/W3160255128","https://openalex.org/W3163527543","https://openalex.org/W3167533889","https://openalex.org/W3197742413","https://openalex.org/W3198712976","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6639350448","https://openalex.org/W6640090968","https://openalex.org/W6695553435","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6780218876","https://openalex.org/W6794778313","https://openalex.org/W6803164887"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Mispronunciation":[0],"Detection":[1],"and":[2,15,50,99,115,124,126],"Diagnosis":[3],"(MDD)":[4],"is":[5,24,35],"an":[6],"essential":[7],"basic":[8],"technology":[9],"in":[10,22,55],"Computer-Assisted":[11,16],"Pronunciation":[12],"Training":[13],"(CAPT)":[14],"Language":[17],"Learning":[18],"(CALL).":[19],"MDD":[20,67,74,92],"research":[21],"Mandarin":[23,73],"faced":[25],"with":[26,138],"the":[27,79,90,130,139,151],"problem":[28],"of":[29,31],"lack":[30],"relevant":[32],"data,":[33],"which":[34],"a":[36,72],"typical":[37],"low-resource":[38,56],"scenario.":[39],"In":[40],"recent":[41],"years,":[42],"self-supervised":[43,106],"pre-trained":[44],"speech":[45,57,108,120],"representation":[46,109],"has":[47],"developed":[48],"rapidly":[49],"achieved":[51],"significant":[52],"performance":[53],"improvement":[54,149],"recognition":[58],"scenarios,":[59],"making":[60],"it":[61],"necessary":[62],"to":[63,66,117],"be":[64],"applied":[65],"tasks.":[68],"First,":[69],"we":[70,88],"build":[71],"dataset":[75],"called":[76],"PSC-Reading":[77,131],"for":[78],"Putonghua":[80],"Proficiency":[81],"Test":[82],"(PSC)":[83],"passage":[84],"reading":[85],"section.":[86],"Then":[87],"extended":[89],"end-to-end":[91],"system":[93],"based":[94],"on":[95,129,150],"CTC/Attention":[96],"hybrid":[97],"architecture":[98],"Transformer":[100],"architecture,":[101],"using":[102],"features":[103,121],"extracted":[104],"from":[105],"pre-training":[107],"models":[110],"such":[111],"as":[112],"Wav2Vec":[113],"2.0":[114],"WavLM":[116],"replace":[118],"conventional":[119],"like":[122],"MFCC":[123],"Fbank,":[125],"conduct":[127],"experiments":[128],"dataset.":[132],"Experimental":[133],"results":[134],"show":[135],"that,":[136],"compared":[137],"baseline":[140],"model":[141,145],"CNN-RNN-CTC,":[142],"our":[143],"WavLM-based":[144],"obtains":[146],"20.5%":[147],"relative":[148],"F1":[152],"score":[153],"metric.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}