{"id":"https://openalex.org/W2800962324","doi":"https://doi.org/10.1109/icassp.2018.8462470","title":"Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody","display_name":"Cyborg Speech: Deep Multilingual Speech Synthesis for Generating Segmental Foreign Accent with Natural Prosody","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2800962324","doi":"https://doi.org/10.1109/icassp.2018.8462470","mag":"2800962324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082512344","display_name":"Mariko Kondo","orcid":"https://orcid.org/0000-0002-4808-6793"},"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":"Mariko Kondo","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"4799","last_page":"4803"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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/speech-synthesis","display_name":"Speech synthesis","score":0.7842351198196411},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7756443023681641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7233150005340576},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7065504193305969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.698195219039917},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5493375062942505},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5243332982063293},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.4705674350261688},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4695751368999481},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38459745049476624},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38270410895347595},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3094223737716675},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06729850172996521}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7842351198196411},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7756443023681641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233150005340576},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7065504193305969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.698195219039917},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5493375062942505},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5243332982063293},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.4705674350261688},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4695751368999481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38459745049476624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38270410895347595},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3094223737716675},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06729850172996521},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2018.8462470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/aa2b7aba-7307-4b82-a1c4-15ce9189eb9d","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W192649799","https://openalex.org/W304834817","https://openalex.org/W1576227399","https://openalex.org/W1630569004","https://openalex.org/W1783473872","https://openalex.org/W1999885698","https://openalex.org/W2002389722","https://openalex.org/W2066452495","https://openalex.org/W2089324793","https://openalex.org/W2102003408","https://openalex.org/W2102157173","https://openalex.org/W2103651905","https://openalex.org/W2131825398","https://openalex.org/W2141720691","https://openalex.org/W2146502635","https://openalex.org/W2154920538","https://openalex.org/W2157429465","https://openalex.org/W2168943479","https://openalex.org/W2172878967","https://openalex.org/W2185000091","https://openalex.org/W2188827208","https://openalex.org/W2294797155","https://openalex.org/W2400063444","https://openalex.org/W2402539796","https://openalex.org/W2471520273","https://openalex.org/W2494654097","https://openalex.org/W2549013258","https://openalex.org/W2595110011","https://openalex.org/W2745595539","https://openalex.org/W2747914378","https://openalex.org/W2759925408","https://openalex.org/W6686288375","https://openalex.org/W6696843773","https://openalex.org/W6729703263"],"related_works":["https://openalex.org/W4214652783","https://openalex.org/W2088008556","https://openalex.org/W2071315723","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W258725851","https://openalex.org/W2474947928","https://openalex.org/W2967415048","https://openalex.org/W4301230705","https://openalex.org/W1489682032"],"abstract_inverted_index":{"We":[0,55],"describe":[1],"a":[2,21,31,44],"new":[3],"application":[4],"of":[5,47],"deep-learning-based":[6],"speech":[7,11,28,67,71,95],"synthesis,":[8,103],"namely":[9],"multilingual":[10,27],"synthesis":[12,99],"for":[13],"generating":[14],"controllable":[15],"foreign":[16,123],"accent.":[17],"Specifically,":[18],"we":[19],"train":[20],"DBLSTM-based":[22],"acoustic":[23],"model":[24],"on":[25,91],"non-accented":[26,128],"recordings":[29],"from":[30,43,82],"speaker":[32],"native":[33],"in":[34],"several":[35],"languages.":[36],"By":[37],"copying":[38],"durations":[39],"and":[40,65,109],"pitch":[41,106],"contours":[42],"pre-recorded":[45],"utterance":[46],"the":[48,83],"desired":[49],"prompt,":[50],"natural":[51,105],"prosody":[52],"is":[53,72,107,117],"achieved.":[54],"call":[56],"this":[57],"paradigm":[58],"\u201ccyborg":[59],"speech\u201d":[60],"as":[61,119],"it":[62],"combines":[63],"human":[64],"machine":[66],"parameters.":[68],"Segmentally":[69],"accented":[70],"produced":[73],"by":[74],"interpolating":[75],"specific":[76],"quinphone":[77],"linguistic":[78],"features":[79],"towards":[80],"phones":[81],"other":[84],"language":[85],"that":[86,97,104,110,116],"represent":[87],"non-native":[88],"mispronunciations.":[89],"Experiments":[90],"synthetic":[92],"American-English-accented":[93],"Japanese":[94],"show":[96],"subjective":[98],"quality":[100],"matches":[101],"monolingual":[102],"maintained,":[108],"naturalistic":[111],"phone":[112],"substitutions":[113],"generate":[114],"output":[115],"perceived":[118],"having":[120],"an":[121],"American":[122],"accent,":[124],"even":[125],"though":[126],"only":[127],"training":[129],"data":[130],"was":[131],"used.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}