{"id":"https://openalex.org/W2936055714","doi":"https://doi.org/10.1186/s13636-018-0146-4","title":"Dual supervised learning for non-native speech recognition","display_name":"Dual supervised learning for non-native speech recognition","publication_year":2019,"publication_date":"2019-01-14","ids":{"openalex":"https://openalex.org/W2936055714","doi":"https://doi.org/10.1186/s13636-018-0146-4","mag":"2936055714"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-018-0146-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0146-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0146-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0146-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016413734","display_name":"Kacper Radzikowski","orcid":"https://orcid.org/0000-0003-0051-2762"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Kacper Radzikowski","raw_affiliation_strings":["Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland"],"raw_orcid":"https://orcid.org/0000-0003-0051-2762","affiliations":[{"raw_affiliation_string":"Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103202243","display_name":"Robert Nowak","orcid":"https://orcid.org/0000-0001-7248-6888"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]},{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Robert Nowak","raw_affiliation_strings":["Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350774","display_name":"Le Wang","orcid":"https://orcid.org/0000-0001-6636-6396"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Le Wang","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057487414","display_name":"Osamu Yoshie","orcid":"https://orcid.org/0000-0002-4192-554X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Yoshie","raw_affiliation_strings":["Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016413734"],"corresponding_institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":1.5975,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.86988924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2019","issue":"1","first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8143863081932068},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.7947546243667603},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5904529094696045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540673553943634},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5227975249290466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5030061602592468},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.468826025724411},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42814046144485474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37719425559043884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143863081932068},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.7947546243667603},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5904529094696045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540673553943634},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5227975249290466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5030061602592468},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.468826025724411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42814046144485474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37719425559043884},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-018-0146-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0146-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0146-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ddd1eef13dd14fd19a3339c9be5652e6","is_oa":true,"landing_page_url":"https://doaj.org/article/ddd1eef13dd14fd19a3339c9be5652e6","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":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2019, Iss 1, Pp 1-10 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-018-0146-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-018-0146-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-018-0146-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2936055714.pdf","grobid_xml":"https://content.openalex.org/works/W2936055714.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W78415016","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W1527535554","https://openalex.org/W1607753411","https://openalex.org/W1736701665","https://openalex.org/W1810943226","https://openalex.org/W1996601463","https://openalex.org/W2064675550","https://openalex.org/W2069508439","https://openalex.org/W2102113734","https://openalex.org/W2119000949","https://openalex.org/W2122598882","https://openalex.org/W2126829162","https://openalex.org/W2143612262","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2251443406","https://openalex.org/W2403787182","https://openalex.org/W2588574756","https://openalex.org/W2595741664","https://openalex.org/W2733239165","https://openalex.org/W2914386313","https://openalex.org/W2915722758","https://openalex.org/W2916979304","https://openalex.org/W2949382160","https://openalex.org/W2963211739","https://openalex.org/W6690408517","https://openalex.org/W6740590407"],"related_works":["https://openalex.org/W1622568043","https://openalex.org/W2055565857","https://openalex.org/W2056183469","https://openalex.org/W4230802329","https://openalex.org/W2164592990","https://openalex.org/W4299645117","https://openalex.org/W2197898492","https://openalex.org/W2087366038","https://openalex.org/W1498610659","https://openalex.org/W2810404362"],"abstract_inverted_index":{"Current":[0],"automatic":[1],"speech":[2,53],"recognition":[3],"(ASR)":[4],"systems":[5,80,171],"achieve":[6,175],"over":[7],"90\u201395%":[8],"accuracy,":[9],"depending":[10],"on":[11,153],"the":[12,19,26,37,43,46,63,145],"methodology":[13],"applied":[14],"and":[15,61,116,135,159,196],"datasets":[16,50],"used.":[17],"However,":[18],"level":[20],"of":[21,36,48,51,65,96,99,144,164,186],"accuracy":[22,177],"decreases":[23],"significantly":[24],"when":[25],"same":[27,44],"ASR":[28,79,170],"system":[29],"is":[30,55,191],"used":[31],"by":[32,110,157],"a":[33,89,127,137],"non-native":[34,52,83],"speaker":[35],"language":[38,155],"to":[39,73,179,194],"be":[40],"recognized.":[41],"At":[42],"time,":[45],"volume":[47],"labeled":[49],"samples":[54],"extremely":[56],"limited":[57],"both":[58],"in":[59,62,126,136,198],"size":[60],"number":[64],"existing":[66],"languages.":[67],"This":[68],"problem":[69],"makes":[70],"it":[71],"difficult":[72],"train":[74],"or":[75],"build":[76],"sufficiently":[77],"accurate":[78],"targeted":[81],"at":[82],"speakers,":[84],"which,":[85],"consequently,":[86],"calls":[87],"for":[88],"different":[90],"approach":[91,140],"that":[92,168],"would":[93],"make":[94],"use":[95,185],"vast":[97],"amounts":[98],"large":[100],"unlabeled":[101,187],"datasets.":[102],"In":[103],"this":[104,108],"paper,":[105],"we":[106],"address":[107],"issue":[109],"employing":[111],"dual":[112],"supervised":[113],"learning":[114,118],"(DSL)":[115],"reinforcement":[117],"with":[119,130,141,172],"policy":[120],"gradient":[121],"methodology.":[122],"We":[123],"tested":[124],"DSL":[125,173],"warm-start":[128,139],"approach,":[129],"two":[131,146],"models":[132,147],"trained":[133],"beforehand,":[134],"semi":[138],"only":[142],"one":[143],"pre-trained.":[148],"The":[149,162],"experiments":[150,166],"were":[151],"conducted":[152],"English":[154],"pronounced":[156],"Japanese":[158],"Polish":[160],"speakers.":[161],"results":[163],"our":[165],"show":[167],"creating":[169],"can":[174],"an":[176],"comparable":[178],"traditional":[180],"methods,":[181],"while":[182],"simultaneously":[183],"making":[184],"data,":[188],"which":[189],"obviously":[190],"much":[192],"cheaper":[193],"obtain":[195],"comes":[197],"larger":[199],"sizes.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}