{"id":"https://openalex.org/W4224928150","doi":"https://doi.org/10.1109/icassp43922.2022.9747414","title":"Masked Acoustic Unit for Mispronunciation Detection and Correction","display_name":"Masked Acoustic Unit for Mispronunciation Detection and Correction","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224928150","doi":"https://doi.org/10.1109/icassp43922.2022.9747414"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747414","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5100393417","display_name":"Zhan Zhang","orcid":"https://orcid.org/0000-0002-5367-3052"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Zhang","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064952252","display_name":"Yuehai Wang","orcid":"https://orcid.org/0000-0002-5084-0572"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuehai Wang","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103081371","display_name":"Jianyi Yang","orcid":"https://orcid.org/0000-0002-3142-5015"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyi Yang","raw_affiliation_strings":["Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.8435,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73333849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"6832","last_page":"6836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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":0.9916999936103821,"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/pronunciation","display_name":"Pronunciation","score":0.9163996577262878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8024538159370422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7202205061912537},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6713516712188721},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.602440357208252},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49158796668052673},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4480573832988739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41626960039138794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4162408709526062},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4124825596809387},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11266574263572693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08503508567810059}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9163996577262878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024538159370422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7202205061912537},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6713516712188721},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.602440357208252},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49158796668052673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4480573832988739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41626960039138794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4162408709526062},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4124825596809387},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11266574263572693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08503508567810059},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747414","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747414","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067517679","https://openalex.org/W2139008940","https://openalex.org/W2144374888","https://openalex.org/W2547875792","https://openalex.org/W2888954148","https://openalex.org/W2938359332","https://openalex.org/W2963448630","https://openalex.org/W2973028772","https://openalex.org/W3013336802","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3081817774","https://openalex.org/W3095361818","https://openalex.org/W3097515180","https://openalex.org/W3097777922","https://openalex.org/W3160799772","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6681666576","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6761144201","https://openalex.org/W6769767169","https://openalex.org/W6775056728","https://openalex.org/W6777380884","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6795346631"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2361861616","https://openalex.org/W2776838583","https://openalex.org/W4205510397"],"abstract_inverted_index":{"Computer-Assisted":[0],"Pronunciation":[1],"Training":[2],"(CAPT)":[3],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8],"language":[9],"learning.":[10],"Conventional":[11],"ASR-based":[12,50],"CAPT":[13,51,127],"methods":[14,52],"require":[15],"expensive":[16],"annotation":[17,41],"of":[18],"the":[19,24,40,47,55,60,65,70,81,86,99,104,109,120],"ground":[20],"truth":[21],"pronunciation":[22],"for":[23,89,129],"supervised":[25],"training.":[26],"Mean-while,":[27],"certain":[28],"undefined":[29],"non-native":[30],"phonemes":[31,106],"cannot":[32,63],"be":[33],"correctly":[34],"classified":[35],"into":[36],"standard":[37],"phonemes,":[38],"making":[39,125],"process":[42],"challenging":[43],"and":[44,93,103,112],"subjective.":[45],"On":[46],"other":[48],"hand,":[49],"only":[53],"give":[54,119],"learner":[56,66,121],"text-based":[57],"feedback":[58],"about":[59],"mispronunciation,":[61],"but":[62],"teach":[64],"how":[67],"to":[68,79,107],"pronounce":[69],"sentence":[71],"correctly.":[72],"To":[73],"solve":[74],"these":[75],"limitations,":[76],"we":[77],"propose":[78],"use":[80],"acoustic":[82],"unit":[83],"(AU)":[84],"as":[85],"intermediary":[87],"feature":[88],"both":[90],"mispronunciation":[91],"detection":[92],"correction.":[94],"The":[95],"proposed":[96],"method":[97,117],"uses":[98],"masked":[100],"AU":[101,111],"sequence":[102],"target":[105],"detect":[108],"error":[110],"then":[113],"corrects":[114],"it.":[115],"This":[116],"can":[118],"speech-based":[122],"self-imitating":[123],"feedback,":[124],"our":[126],"powerful":[128],"education.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
