{"id":"https://openalex.org/W3135339411","doi":"https://doi.org/10.1186/s13636-021-00199-3","title":"Accent modification for speech recognition of non-native speakers using neural style transfer","display_name":"Accent modification for speech recognition of non-native speakers using neural style transfer","publication_year":2021,"publication_date":"2021-02-18","ids":{"openalex":"https://openalex.org/W3135339411","doi":"https://doi.org/10.1186/s13636-021-00199-3","mag":"3135339411"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00199-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00199-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00199-3","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"],"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/s13636-021-00199-3","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"]},{"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","PL"],"is_corresponding":true,"raw_author_name":"Kacper Radzikowski","raw_affiliation_strings":["Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland","Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]},{"raw_affiliation_string":"Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"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":["Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","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":["Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Graduate School of Information, Production and Systems, Kitakyushu, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Warsaw University of Technology, Institute of Computer Science, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487","https://openalex.org/I4210087266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016413734"],"corresponding_institution_ids":["https://openalex.org/I108403487","https://openalex.org/I150744194","https://openalex.org/I4210087266"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":4.1924,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.94904584,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"2021","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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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":0.7652640342712402},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7265608906745911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6979419589042664},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5738363265991211},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.5097091197967529},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.47015026211738586},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.4365031123161316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41060903668403625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39097464084625244},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.2417302131652832},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2072908580303192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7652640342712402},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7265608906745911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6979419589042664},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5738363265991211},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.5097091197967529},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.47015026211738586},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.4365031123161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41060903668403625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39097464084625244},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.2417302131652832},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2072908580303192},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-021-00199-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00199-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00199-3","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"],"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:174c06be62af462f804e5b6b5d57e44f","is_oa":true,"landing_page_url":"https://doaj.org/article/174c06be62af462f804e5b6b5d57e44f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"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 2021, Iss 1, Pp 1-10 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00199-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00199-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-021-00199-3","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"],"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":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327550","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135339411.pdf","grobid_xml":"https://content.openalex.org/works/W3135339411.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W78415016","https://openalex.org/W1783786615","https://openalex.org/W1924619199","https://openalex.org/W1995562189","https://openalex.org/W1996601463","https://openalex.org/W2069508439","https://openalex.org/W2126829162","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2296237247","https://openalex.org/W2331128040","https://openalex.org/W2398423749","https://openalex.org/W2588574756","https://openalex.org/W2766465839","https://openalex.org/W2782490852","https://openalex.org/W2936055714","https://openalex.org/W2949640717","https://openalex.org/W2962835968","https://openalex.org/W6600805904","https://openalex.org/W6601052344","https://openalex.org/W6777574746"],"related_works":["https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W3031252497","https://openalex.org/W2764094668","https://openalex.org/W2334135487","https://openalex.org/W4298046075","https://openalex.org/W4207066001","https://openalex.org/W2381837697"],"abstract_inverted_index":{"Abstract":[0],"Nowadays":[1],"automatic":[2],"speech":[3,77,122,183,197,234],"recognition":[4,184,235],"(ASR)":[5],"systems":[6,91],"can":[7,208,221],"achieve":[8],"higher":[9,11],"and":[10,19,51,101,146,153,207],"accuracy":[12,106],"rates":[13],"depending":[14],"on":[15,104,159],"the":[16,27,38,56,64,67,85,99,105,111,121,133,182,189,200,204,233],"methodology":[17,187],"applied":[18],"datasets":[20,78],"used.":[21],"The":[22,43,155,169,219],"rate":[23],"decreases":[24],"significantly":[25],"when":[26],"ASR":[28,90,108,217],"system":[29,236],"is":[30,48,174,230],"being":[31],"used":[32,210],"with":[33],"a":[34,117,124,175,212,228],"non-native":[35,76,93,125,196],"speaker":[36,126],"of":[37,59,74,107,123,181,191],"language":[39,161],"to":[40,55,82,203],"be":[41,209,222],"recognized.":[42],"main":[44],"reason":[45],"for":[46,92,119,140,195,214],"this":[47,95],"specific":[49],"pronunciation":[50],"accent":[52,141],"features":[53],"related":[54,202],"mother":[57],"tongue":[58],"that":[60,128,172],"speaker,":[61],"which":[62],"influence":[63,103],"pronunciation.":[65],"At":[66],"same":[68],"time,":[69,226],"an":[70],"extremely":[71],"limited":[72],"volume":[73],"labeled":[75],"makes":[79],"it":[80,129],"difficult":[81],"train,":[83],"from":[84],"ground":[86],"up,":[87],"sufficiently":[88],"accurate":[89],"speakers.In":[94],"research,":[96],"we":[97],"address":[98],"problem":[100],"its":[102],"systems,":[109],"using":[110,143],"style":[112,151],"transfer":[113,152],"methodology.":[114],"We":[115],"designed":[116],"pipeline":[118],"modifying":[120],"so":[127],"more":[130],"closely":[131],"resembles":[132],"native":[134],"speech.":[135],"This":[136],"paper":[137],"covers":[138],"experiments":[139,156],"modification":[142,220],"different":[144,147],"setups":[145],"approaches,":[148],"including":[149],"neural":[150],"autoencoder.":[154],"were":[157],"conducted":[158],"English":[160],"pronounced":[162],"by":[163],"Japanese":[164],"speakers":[165],"(":[166],"UME-ERJ":[167],"dataset).":[168],"results":[170],"show":[171],"there":[173],"significant":[176],"relative":[177],"improvement":[178],"in":[179,224],"terms":[180],"accuracy.":[185],"Our":[186],"reduces":[188],"necessity":[190],"training":[192],"new":[193],"algorithms":[194],"(thus":[198],"overcoming":[199],"obstacle":[201],"data":[205],"scarcity)":[206],"as":[211],"wrapper":[213],"any":[215],"existing":[216],"system.":[218],"performed":[223],"real":[225],"before":[227],"sample":[229],"passed":[231],"into":[232],"itself.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
