{"id":"https://openalex.org/W2991202348","doi":"https://doi.org/10.1109/access.2019.2955978","title":"Voice Conversion With CycleRNN-Based Spectral Mapping and Finely Tuned WaveNet Vocoder","display_name":"Voice Conversion With CycleRNN-Based Spectral Mapping and Finely Tuned WaveNet Vocoder","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2991202348","doi":"https://doi.org/10.1109/access.2019.2955978","mag":"2991202348"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2955978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955978","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08913551.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08913551.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2792-8418","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8471,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80969728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"171114","last_page":"171125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991999864578247,"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":0.9976000189781189,"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/naturalness","display_name":"Naturalness","score":0.916008710861206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7418886423110962},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6964656114578247},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6798324584960938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6646104454994202},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.49105262756347656},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4429228603839874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38749611377716064},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37182268500328064},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16768160462379456},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.07933908700942993},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07739415764808655}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.916008710861206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418886423110962},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6964656114578247},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6798324584960938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6646104454994202},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.49105262756347656},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4429228603839874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38749611377716064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37182268500328064},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16768160462379456},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.07933908700942993},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07739415764808655},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2955978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955978","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08913551.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e7bfa6675bd5419cb69615d083e9b1db","is_oa":true,"landing_page_url":"https://doaj.org/article/e7bfa6675bd5419cb69615d083e9b1db","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":"IEEE Access, Vol 7, Pp 171114-171125 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2955978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2955978","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08913551.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1628655565","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"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"},{"id":"https://openalex.org/G200199876","display_name":"\u30e6\u30fc\u30b6\u306e\u9069\u5fdc\u80fd\u529b\u3092\u6d3b\u7528\u3059\u308b\u5171\u5275\u578b\u97f3\u58f0\u751f\u6210\u6a5f\u80fd\u62e1\u5f35\u6280\u8853\u306e\u69cb\u7bc9","funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2521286739","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2664191106","display_name":"\u97f3\u30e1\u30c7\u30a3\u30a2\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u304a\u3051\u308b\u5171\u5275\u578b\u6a5f\u80fd\u62e1\u5f35\u6280\u8853\u306e\u5275\u51fa","funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G3497787681","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991202348.pdf","grobid_xml":"https://content.openalex.org/works/W2991202348.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W773905565","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1558306184","https://openalex.org/W1590808459","https://openalex.org/W1963637322","https://openalex.org/W2012086895","https://openalex.org/W2013996527","https://openalex.org/W2017742648","https://openalex.org/W2048646122","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2095705004","https://openalex.org/W2100819376","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2156142001","https://openalex.org/W2157331557","https://openalex.org/W2161727827","https://openalex.org/W2187234408","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2524251915","https://openalex.org/W2584032004","https://openalex.org/W2745644908","https://openalex.org/W2747070883","https://openalex.org/W2749651610","https://openalex.org/W2770751809","https://openalex.org/W2786868129","https://openalex.org/W2794725088","https://openalex.org/W2797310469","https://openalex.org/W2800289214","https://openalex.org/W2802455234","https://openalex.org/W2883586237","https://openalex.org/W2889329491","https://openalex.org/W2911540263","https://openalex.org/W2936002583","https://openalex.org/W2963035245","https://openalex.org/W2963631950","https://openalex.org/W2964243274","https://openalex.org/W4245284779","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6732429163","https://openalex.org/W6743434412","https://openalex.org/W6748409065"],"related_works":["https://openalex.org/W2371805284","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148"],"abstract_inverted_index":{"In":[0],"this":[1,69,116],"paper,":[2],"we":[3,118],"present":[4],"a":[5,9,16,23,62,78,83,91,111,123,133,139,165,182,238],"novel":[6],"framework":[7],"for":[8,94,197],"voice":[10],"conversion":[11,126,134,156,184,226],"(VC)":[12],"system":[13],"based":[14],"on":[15],"cyclic":[17,124,140,159],"recurrent":[18],"neural":[19],"network":[20],"(CycleRNN)":[21],"and":[22,138,157,217],"finely":[24,162],"tuned":[25],"WaveNet":[26,30,79,95,168,198,244],"vocoder.":[27],"Even":[28],"though":[29],"is":[31,71,97,152,170,237],"capable":[32,130],"of":[33,90,110,122,131,176,181,204,215,234],"producing":[34],"natural":[35,41,247],"speech":[36,42,48,207],"waveforms":[37],"when":[38,51],"fed":[39,52],"with":[40,53,242],"features,":[43,55],"it":[44],"still":[45],"suffers":[46],"from":[47,61,108],"quality":[49],"degradation":[50],"oversmoothed":[54,74,87],"such":[56],"as":[57],"spectral":[58,88,125,150,195],"parameters":[59],"estimated":[60],"statistical":[63],"model.":[64,80],"One":[65],"way":[66],"to":[67,72,101,143],"address":[68],"problem":[70],"introduce":[73],"features":[75,89,175],"while":[76],"developing":[77],"However,":[81],"in":[82,104],"VC":[84],"framework,":[85],"providing":[86],"target":[92,146,179,248],"speaker":[93,180,183,225,231],"modeling":[96],"not":[98],"straightforward":[99],"owing":[100],"the":[102,105,120,173,177,192,202,205,219,223],"difference":[103],"time-sequence":[106],"alignment":[107],"that":[109,190],"source":[112],"speaker.":[113],"To":[114,161],"overcome":[115],"problem,":[117],"propose":[119],"use":[121],"network,":[127],"i.e.,":[128,136,142],"CycleRNN,":[129],"performing":[132],"flow,":[135,141],"source-to-target,":[137],"generate":[144],"self-predicted":[145,174],"spectra.":[147],"The":[148,186],"CycleRNN":[149],"model":[151,169,196,221],"trained":[153],"using":[154,172,246],"both":[155],"weighted":[158],"losses.":[160],"tune":[163],"WaveNet,":[164],"pretrained":[166],"multispeaker":[167],"optimized":[171],"corresponding":[178],"pair.":[185],"experimental":[187],"results":[188],"demonstrate":[189],"1)":[191],"proposed":[193,220],"CycleRNN-based":[194],"fine-tuning":[199,245],"significantly":[200],"improves":[201],"naturalness":[203],"converted":[206],"waveforms,":[208],"giving":[209,228],"an":[210,229],"overall":[211,230],"mean":[212],"opinion":[213],"score":[214,233],"3.50;":[216],"2)":[218],"yields":[222],"highest":[224],"accuracy,":[227],"similarity":[232],"78.33%,":[235],"which":[236],"significant":[239],"improvement":[240],"compared":[241],"conventional":[243],"features.":[249]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}