{"id":"https://openalex.org/W3114453927","doi":"https://doi.org/10.1109/gcce50665.2020.9291952","title":"CycleGAN-Based High-Quality Non-Parallel Voice Conversion with Spectrogram and WaveRNN","display_name":"CycleGAN-Based High-Quality Non-Parallel Voice Conversion with Spectrogram and WaveRNN","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3114453927","doi":"https://doi.org/10.1109/gcce50665.2020.9291952","mag":"3114453927"},"language":"en","primary_location":{"id":"doi:10.1109/gcce50665.2020.9291952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049188373","display_name":"Aoi Kanagaki","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Aoi Kanagaki","raw_affiliation_strings":["Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009707727","display_name":"Masaya Tanaka","orcid":"https://orcid.org/0000-0002-7873-1749"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaya Tanaka","raw_affiliation_strings":["Tokyo University of Agriculture and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology, Japan","institution_ids":["https://openalex.org/I92614990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102781482","display_name":"Ryohei Shimizu","orcid":"https://orcid.org/0000-0001-9711-3121"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryohei Shimizu","raw_affiliation_strings":["The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004043077","display_name":"A. S. Ito","orcid":"https://orcid.org/0000-0002-4602-7570"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Ito","raw_affiliation_strings":["Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.17026468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"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":0.9994000196456909,"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":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/spectrogram","display_name":"Spectrogram","score":0.9515508413314819},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8890581130981445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692406177520752},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7379980683326721},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.525954008102417},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5079715847969055},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5026366710662842},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5006678104400635},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.41743195056915283},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3725631833076477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3493534326553345},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.056127071380615234}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9515508413314819},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8890581130981445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692406177520752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7379980683326721},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.525954008102417},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5079715847969055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5026366710662842},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5006678104400635},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.41743195056915283},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3725631833076477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3493534326553345},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.056127071380615234},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce50665.2020.9291952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6814346892","display_name":"Research and development of multi-modal interactive English learning system based on deep learning","funder_award_id":"17H00823","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2785678896","https://openalex.org/W2937579788","https://openalex.org/W2963836885","https://openalex.org/W2964307104","https://openalex.org/W2972789651","https://openalex.org/W4298580827","https://openalex.org/W6748409065","https://openalex.org/W6748582592"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W2626699140","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W2111961547"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"Scyclone,":[3,36],"a":[4,31,37],"high-quality":[5],"voice":[6],"conversion":[7,29,44],"(VC)":[8],"technique":[9],"without":[10],"parallel":[11],"data":[12],"training.":[13],"Scyclone":[14,59],"improves":[15],"speech":[16,24],"naturalness":[17],"and":[18],"speaker":[19],"similarity":[20],"of":[21,66],"the":[22,43,67],"converted":[23],"by":[25],"introducing":[26],"CycleGAN-based":[27],"spectrogram":[28,39],"with":[30],"simplified":[32],"WaveRNN-based":[33],"vocoder.":[34],"In":[35],"linear":[38],"is":[40,60],"used":[41],"as":[42],"feature,":[45],"which":[46],"avoids":[47],"quality":[48],"degradation":[49],"due":[50],"to":[51],"extraction":[52],"errors.":[53],"The":[54],"subjective":[55],"experiments":[56],"show":[57],"that":[58],"significantly":[61],"better":[62],"than":[63],"CycleGAN-VC2,":[64],"one":[65],"existing":[68],"state-of-the-art":[69],"parallel-data-free":[70],"VC":[71],"techniques.":[72]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}