{"id":"https://openalex.org/W3034420534","doi":"https://doi.org/10.1109/taslp.2020.3001456","title":"ConvS2S-VC: Fully Convolutional Sequence-to-Sequence Voice Conversion","display_name":"ConvS2S-VC: Fully Convolutional Sequence-to-Sequence Voice Conversion","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3034420534","doi":"https://doi.org/10.1109/taslp.2020.3001456","mag":"3034420534"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3001456","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3001456","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09113442.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09113442.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3102-0162","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048328334","display_name":"Damian Kwa\u015bny","orcid":"https://orcid.org/0000-0002-2276-5288"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Damian Kwasny","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2276-5288","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020693766","display_name":"Takuhiro Kaneko","orcid":"https://orcid.org/0009-0000-8016-5144"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuhiro Kaneko","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Atsugi, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001243214"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":6.2511,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.97130001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1849","last_page":"1863"},"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":0.9994999766349792,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8323347568511963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129150867462158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5970529913902283},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4485059976577759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3979633152484894},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35977327823638916},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19632136821746826}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8323347568511963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129150867462158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5970529913902283},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4485059976577759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3979633152484894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35977327823638916},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19632136821746826},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3001456","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3001456","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09113442.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2020.3001456","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3001456","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/8938144/09113442.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6466568207","display_name":"Development of fundamental technology for speech and sound event processing based on complementary use of air- and body-conducted sound signals","funder_award_id":"17H01763","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/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034420534.pdf","grobid_xml":"https://content.openalex.org/works/W3034420534.grobid-xml"},"referenced_works_count":94,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W854541894","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1902237438","https://openalex.org/W2017742648","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2076258817","https://openalex.org/W2093450784","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2130942839","https://openalex.org/W2142300631","https://openalex.org/W2148846882","https://openalex.org/W2156142001","https://openalex.org/W2157412983","https://openalex.org/W2161727827","https://openalex.org/W2284050935","https://openalex.org/W2471520273","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2545656684","https://openalex.org/W2567070169","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2613904329","https://openalex.org/W2619368999","https://openalex.org/W2739735615","https://openalex.org/W2747744257","https://openalex.org/W2749651610","https://openalex.org/W2767052532","https://openalex.org/W2800289214","https://openalex.org/W2890983311","https://openalex.org/W2897353073","https://openalex.org/W2898654681","https://openalex.org/W2899877258","https://openalex.org/W2901997113","https://openalex.org/W2902070858","https://openalex.org/W2911708970","https://openalex.org/W2946555236","https://openalex.org/W2949382160","https://openalex.org/W2962882868","https://openalex.org/W2962896155","https://openalex.org/W2963011080","https://openalex.org/W2963035245","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963403868","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963685250","https://openalex.org/W2963691546","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963808252","https://openalex.org/W2963970792","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964265128","https://openalex.org/W2964281804","https://openalex.org/W2964307104","https://openalex.org/W2972667718","https://openalex.org/W2972970915","https://openalex.org/W2972999331","https://openalex.org/W3099078140","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6603838645","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6679436768","https://openalex.org/W6695676441","https://openalex.org/W6724804524","https://openalex.org/W6729110096","https://openalex.org/W6731370813","https://openalex.org/W6732429163","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6756102363","https://openalex.org/W6756159577","https://openalex.org/W6756197946","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W4321441197","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"This":[0,51,120,190],"article":[1],"proposes":[2],"a":[3,44,47,104,117,172],"voice":[4,20],"conversion":[5,94,167,203,209],"(VC)":[6],"method":[7],"using":[8,63,102,116],"sequence-to-sequence":[9],"(seq2seq":[10],"or":[11],"S2S)":[12],"learning,":[13],"which":[14],"flexibly":[15],"converts":[16],"not":[17],"only":[18,103],"the":[19,24,84,88,122,175,187],"characteristics":[21],"but":[22],"also":[23,67,226],"pitch":[25],"contour":[26],"and":[27,211,219,246],"duration":[28],"of":[29,108],"input":[30],"speech.":[31],"The":[32],"proposed":[33],"method,":[34],"called":[35,174],"ConvS2S-VC,":[36],"has":[37,193],"three":[38],"key":[39],"features.":[40],"First,":[41],"it":[42,57,70,91,162,232],"uses":[43],"model":[45,106,123,151],"with":[46,186],"fully":[48,125],"convolutional":[49],"architecture.":[50],"is":[52,58,66],"particularly":[53],"advantageous":[54],"in":[55,87,184,236],"that":[56,139,179,213,231],"suitable":[59],"for":[60,82,200],"parallel":[61],"computations":[62],"GPUs.":[64],"It":[65],"beneficial":[68],"since":[69],"enables":[71,121],"effective":[72,199],"normalization":[73,78,178,182],"techniques":[74],"such":[75],"as":[76],"batch":[77,177,181],"to":[79,124,147,164,196],"be":[80,141,197],"used":[81],"all":[83],"hidden":[85],"layers":[86,183],"networks.":[89],"Second,":[90],"achieves":[92],"many-to-many":[93,202],"by":[95,134],"simultaneously":[96],"learning":[97,110],"mappings":[98,111],"among":[99],"multiple":[100,132],"speakers":[101,133],"single":[105],"instead":[107],"separately":[109],"between":[112],"each":[113],"speaker":[114,158,207,220],"pair":[115],"different":[118,144],"model.":[119,204],"utilize":[126],"available":[127],"training":[128],"data":[129],"collected":[130],"from":[131,228],"capturing":[135],"common":[136],"latent":[137],"features":[138],"can":[140],"shared":[142],"across":[143],"speakers.":[145],"Owing":[146],"this":[148],"structure,":[149],"our":[150,201],"works":[152],"reasonably":[153],"well":[154,235],"even":[155],"without":[156],"source":[157],"information,":[159],"thus":[160],"making":[161],"able":[163],"handle":[165],"any-to-many":[166],"tasks.":[168],"Third,":[169],"we":[170],"introduce":[171],"mechanism,":[173],"conditional":[176],"switches":[180],"accordance":[185],"target":[188],"speaker.":[189],"particular":[191],"mechanism":[192],"been":[194],"found":[195,212,227],"extremely":[198],"We":[205,225],"conducted":[206],"identity":[208],"experiments":[210],"ConvS2S-VC":[214],"obtained":[215],"higher":[216],"sound":[217],"quality":[218],"similarity":[221],"than":[222],"baseline":[223],"methods.":[224],"audio":[229],"examples":[230],"could":[233],"perform":[234],"various":[237],"tasks":[238],"including":[239],"emotional":[240],"expression":[241],"conversion,":[242],"electrolaryngeal":[243],"speech":[244],"enhancement,":[245],"English":[247],"accent":[248],"conversion.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}