{"id":"https://openalex.org/W2990413709","doi":"https://doi.org/10.1109/taslp.2019.2955858","title":"Cross-Lingual Transfer Learning of Non-Native Acoustic Modeling for Pronunciation Error Detection and Diagnosis","display_name":"Cross-Lingual Transfer Learning of Non-Native Acoustic Modeling for Pronunciation Error Detection and Diagnosis","publication_year":2019,"publication_date":"2019-11-25","ids":{"openalex":"https://openalex.org/W2990413709","doi":"https://doi.org/10.1109/taslp.2019.2955858","mag":"2990413709"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2955858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955858","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/246413/1/TASLP.2019.2955858.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062004816","display_name":"Richeng Duan","orcid":"https://orcid.org/0000-0001-7927-2444"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Richeng Duan","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7927-2444","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2686-2296","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086753922","display_name":"Masatake Dantsuji","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatake Dantsuji","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103737191","display_name":"Hiroaki Nanjo","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Nanjo","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1178,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90494195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"391","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9908999800682068,"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":0.9884999990463257,"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/pronunciation","display_name":"Pronunciation","score":0.8964025974273682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8428395986557007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.604188859462738},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5608850717544556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49516430497169495},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49372395873069763},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4720286428928375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4290006458759308},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.41826337575912476},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.257965087890625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14323976635932922}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8964025974273682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8428395986557007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.604188859462738},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5608850717544556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49516430497169495},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49372395873069763},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4720286428928375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4290006458759308},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.41826337575912476},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.257965087890625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14323976635932922},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2019.2955858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2955858","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/246413","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/246413","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/246413/1/TASLP.2019.2955858.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:repository.kulib.kyoto-u.ac.jp:2433/246413","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/246413","pdf_url":"https://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/246413/1/TASLP.2019.2955858.pdf","source":{"id":"https://openalex.org/S4306401454","display_name":"Kyoto University Research Information Repository (Kyoto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I22299242","host_organization_name":"Kyoto University","host_organization_lineage":["https://openalex.org/I22299242"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2990413709.pdf"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W11987892","https://openalex.org/W32018921","https://openalex.org/W35168091","https://openalex.org/W70727784","https://openalex.org/W103312509","https://openalex.org/W215171336","https://openalex.org/W275138538","https://openalex.org/W290344559","https://openalex.org/W1494198834","https://openalex.org/W1499800345","https://openalex.org/W1501286448","https://openalex.org/W1580606264","https://openalex.org/W1585763212","https://openalex.org/W1594389310","https://openalex.org/W1761828760","https://openalex.org/W1945090009","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W1980850109","https://openalex.org/W1982957918","https://openalex.org/W1986614398","https://openalex.org/W2005522781","https://openalex.org/W2023389730","https://openalex.org/W2024490156","https://openalex.org/W2025198378","https://openalex.org/W2027993708","https://openalex.org/W2032069772","https://openalex.org/W2053638914","https://openalex.org/W2055115647","https://openalex.org/W2059376792","https://openalex.org/W2077155272","https://openalex.org/W2091856355","https://openalex.org/W2097381042","https://openalex.org/W2125711423","https://openalex.org/W2134124280","https://openalex.org/W2137268753","https://openalex.org/W2137469438","https://openalex.org/W2139008940","https://openalex.org/W2140372979","https://openalex.org/W2160815625","https://openalex.org/W2165698076","https://openalex.org/W2169883442","https://openalex.org/W2295582178","https://openalex.org/W2370418772","https://openalex.org/W2394589087","https://openalex.org/W2399792130","https://openalex.org/W2400818677","https://openalex.org/W2401896499","https://openalex.org/W2403033074","https://openalex.org/W2403588201","https://openalex.org/W2405178423","https://openalex.org/W2408387233","https://openalex.org/W2484174190","https://openalex.org/W2552635739","https://openalex.org/W2557978073","https://openalex.org/W2561373239","https://openalex.org/W2578750458","https://openalex.org/W2616180702","https://openalex.org/W2663878505","https://openalex.org/W2752899488","https://openalex.org/W2782999119","https://openalex.org/W2963540679","https://openalex.org/W4285719527","https://openalex.org/W6601290026","https://openalex.org/W6602874765","https://openalex.org/W6608671783","https://openalex.org/W6634953701","https://openalex.org/W6635132915","https://openalex.org/W6640608080","https://openalex.org/W6656299101","https://openalex.org/W6665119368","https://openalex.org/W6674600207","https://openalex.org/W6680263073","https://openalex.org/W6684803408","https://openalex.org/W6697274609","https://openalex.org/W6711883690","https://openalex.org/W6713033232","https://openalex.org/W6713037690","https://openalex.org/W6713505222","https://openalex.org/W6713547206","https://openalex.org/W6714114421","https://openalex.org/W6730816769","https://openalex.org/W7011707065"],"related_works":["https://openalex.org/W4383959480","https://openalex.org/W2901328199","https://openalex.org/W3081187864","https://openalex.org/W151018310","https://openalex.org/W4380605396","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2584084702","https://openalex.org/W2784059283","https://openalex.org/W3012383599"],"abstract_inverted_index":{"In":[0,61,79],"computer-assisted":[1],"pronunciation":[2,160,167,173],"training":[3],"(CAPT),":[4],"the":[5,44,142,159,175,187],"scarcity":[6],"of":[7,26,86,102,117,126,166,172],"large-scale":[8],"non-native":[9,20,34,54,66,87,127,153],"corpora":[10,35,101],"and":[11,51,72,107],"human":[12],"expert":[13],"annotations":[14],"are":[15,31,38,131],"two":[16,97],"fundamental":[17],"challenges":[18],"to":[19,49,81,95,111],"acoustic":[21,27,67,84],"modeling.":[22],"Most":[23],"existing":[24],"approaches":[25],"modeling":[28,68,178],"in":[29,43,152],"CAPT":[30],"based":[32,75,163],"on":[33,70,76,164],"while":[36],"there":[37],"so":[39],"many":[40],"living":[41],"languages":[42],"world.":[45],"It":[46,156],"is":[47,180],"impractical":[48],"collect":[50],"annotate":[52],"every":[53],"speech":[55,88,100,154],"corpus":[56],"considering":[57],"different":[58],"language":[59,105,109],"pairs.":[60],"this":[62],"work,":[63],"we":[64,93],"address":[65],"(both":[69],"phonetic":[71],"articulatory":[73],"level)":[74],"transfer":[77,118],"learning.":[78],"order":[80],"effectively":[82],"train":[83],"models":[85],"without":[89],"using":[90],"such":[91],"data,":[92],"propose":[94],"exploit":[96],"large":[98],"native":[99,104],"learner's":[103],"(L1)":[106],"target":[108],"(L2)":[110],"model":[112,145],"cross-lingual":[113],"phenomena.":[114],"This":[115],"kind":[116],"learning":[119,137],"can":[120],"provide":[121],"a":[122,147],"better":[123],"feature":[124],"representation":[125],"speech.":[128],"Experimental":[129],"evaluations":[130],"carried":[132],"out":[133],"for":[134,182],"Japanese":[135],"speakers":[136],"English.":[138],"We":[139],"first":[140],"demonstrate":[141],"proposed":[143,176],"acoustic-phone":[144],"achieves":[146],"lower":[148],"word":[149],"error":[150,161],"rate":[151],"recognition.":[155],"also":[157],"improves":[158],"detection":[162],"goodness":[165],"(GOP)":[168],"score.":[169],"For":[170],"diagnosis":[171],"errors,":[174],"acoustic-articulatory":[177],"method":[179],"effective":[181],"providing":[183],"detailed":[184],"feedback":[185],"at":[186],"articulation":[188],"level.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}