{"id":"https://openalex.org/W3015430779","doi":"https://doi.org/10.1109/icassp40776.2020.9053797","title":"End-To-End Accent Conversion Without Using Native Utterances","display_name":"End-To-End Accent Conversion Without Using Native Utterances","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015430779","doi":"https://doi.org/10.1109/icassp40776.2020.9053797","mag":"3015430779"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Disong Wang","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013296368","display_name":"Yuewen Cao","orcid":"https://orcid.org/0000-0002-1432-161X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Cao","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019219958","display_name":"Lifa Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifa Sun","raw_affiliation_strings":["SpeechX Limited, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"SpeechX Limited, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5102778496"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.7838,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.92124685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6289","last_page":"6293"},"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":0.9990000128746033,"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8429450988769531},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7082517743110657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7034851908683777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6115337610244751},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5650315284729004},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4668937921524048},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4528924822807312},{"id":"https://openalex.org/keywords/native-american","display_name":"Native american","score":0.44328856468200684},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4214090406894684},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3955545723438263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3529086112976074},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.09899088740348816},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0761549174785614}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8429450988769531},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7082517743110657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034851908683777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6115337610244751},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5650315284729004},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4668937921524048},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4528924822807312},{"id":"https://openalex.org/C2992135444","wikidata":"https://www.wikidata.org/wiki/Q4232928","display_name":"Native american","level":2,"score":0.44328856468200684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4214090406894684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3955545723438263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3529086112976074},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09899088740348816},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0761549174785614},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2549261","wikidata":"https://www.wikidata.org/wiki/Q43455","display_name":"Ethnology","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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1855892484","https://openalex.org/W1991682319","https://openalex.org/W2017742648","https://openalex.org/W2120605154","https://openalex.org/W2124331435","https://openalex.org/W2143076222","https://openalex.org/W2157259375","https://openalex.org/W2518172956","https://openalex.org/W2526425061","https://openalex.org/W2527729766","https://openalex.org/W2726515241","https://openalex.org/W2805038428","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2888922217","https://openalex.org/W2890402938","https://openalex.org/W2955237921","https://openalex.org/W2962788625","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2973094925","https://openalex.org/W2973108288","https://openalex.org/W3101689408","https://openalex.org/W3127686677","https://openalex.org/W4298580827","https://openalex.org/W6623517193","https://openalex.org/W6678683371","https://openalex.org/W6726528559","https://openalex.org/W6752888775","https://openalex.org/W6785457655","https://openalex.org/W6789826613","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2108985546","https://openalex.org/W2077992636","https://openalex.org/W2279374969","https://openalex.org/W1537411440","https://openalex.org/W290673751","https://openalex.org/W2017702615","https://openalex.org/W2024201202","https://openalex.org/W2370805772","https://openalex.org/W2547993968"],"abstract_inverted_index":{"Techniques":[0],"for":[1],"accent":[2],"conversion":[3,57],"(AC)":[4],"aim":[5],"to":[6,9,17,28,70,107],"convert":[7,18,122],"non-native":[8,32,95],"native":[10,25,127],"accented":[11,33,96],"speech.":[12,110],"Conventional":[13],"AC":[14,72],"methods":[15],"try":[16],"only":[19],"the":[20,31,37,118],"speaker":[21,92],"identity":[22],"of":[23,30,142],"a":[24,100],"speaker's":[26],"voice":[27],"that":[29,117],"target":[34],"speaker,":[35],"leaving":[36],"underlying":[38],"content":[39],"and":[40,91,98],"pronunciations":[41],"unchanged.":[42],"This":[43],"hinders":[44],"their":[45],"practical":[46],"use":[47],"in":[48,140],"real-world":[49],"applications,":[50],"because":[51],"native-accented":[52,79,109,138],"utterances":[53,75,80],"are":[54],"required":[55],"at":[56],"stage.":[58],"In":[59],"this":[60,86],"paper,":[61],"we":[62],"present":[63],"an":[64],"end-to-end":[65],"framework,":[66],"which":[67,134],"is":[68,135],"able":[69],"conduct":[71],"from":[73,94,137],"non-native-accented":[74],"without":[76],"using":[77],"any":[78],"during":[81],"online":[82],"conversion.":[83],"We":[84],"achieve":[85],"by":[87],"independently":[88],"extracting":[89],"linguistic":[90],"representations":[93,106],"speech":[97,101,125,130],"condition":[99],"synthesis":[102],"model":[103],"on":[104,112],"these":[105],"generate":[108],"Experiments":[111],"open-source":[113],"data":[114],"corpora":[115],"show":[116],"proposed":[119],"system":[120],"can":[121],"Hindi-accented":[123],"English":[124,129],"into":[126],"American":[128],"with":[131],"high":[132],"naturalness,":[133],"indistinguishable":[136],"recordings":[139],"terms":[141],"accent.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
