{"id":"https://openalex.org/W4296069286","doi":"https://doi.org/10.21437/interspeech.2022-10856","title":"Self supervised learning for robust voice cloning","display_name":"Self supervised learning for robust voice cloning","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069286","doi":"https://doi.org/10.21437/interspeech.2022-10856"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10856","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10856","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5087573028","display_name":"Konstantinos Klapsas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Konstantinos Klapsas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052196585","display_name":"Nikolaos Ellinas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Ellinas","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056672858","display_name":"Karolos Nikitaras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karolos Nikitaras","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022310876","display_name":"Georgios Vamvoukakis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgios Vamvoukakis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Panagiotis Kakoulidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panagiotis Kakoulidis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050072052","display_name":"\u039a\u03c9\u03bd\u03c3\u03c4\u03b1\u03bd\u03c4\u03af\u03bd\u03bf\u03c2 \u039c\u03b1\u03c1\u03ba\u03cc\u03c0\u03bf\u03c5\u03bb\u03bf\u03c2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinos Markopoulos","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111393130","display_name":"Spyros Raptis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Spyros Raptis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041656238","display_name":"Gunu Jho","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunu Jho","raw_affiliation_strings":["Mobile Communications Business, Samsung Electronics, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Mobile Communications Business, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091595884","display_name":"Aimilios Chalamandaris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimilios Chalamandaris","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["Innoetics, Samsung Electronics, Greece"],"affiliations":[{"raw_affiliation_string":"Innoetics, Samsung Electronics, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5087573028"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6259,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67768945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4935","last_page":"4939"},"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":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/cloning","display_name":"Cloning (programming)","score":0.7194862365722656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6931266188621521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5139548182487488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4684871435165405},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3534986078739166}],"concepts":[{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.7194862365722656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6931266188621521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5139548182487488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684871435165405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3534986078739166},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10856","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10856","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2107860279","https://openalex.org/W2150769028","https://openalex.org/W2559260703","https://openalex.org/W2765407302","https://openalex.org/W2766812927","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2892620417","https://openalex.org/W2907262790","https://openalex.org/W2946200149","https://openalex.org/W2962788625","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2963864421","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2981087920","https://openalex.org/W3035060554","https://openalex.org/W3036601975","https://openalex.org/W3091928890","https://openalex.org/W3095389792","https://openalex.org/W3095545636","https://openalex.org/W3095990227","https://openalex.org/W3097728852","https://openalex.org/W3162794600","https://openalex.org/W3169212847","https://openalex.org/W3198032048","https://openalex.org/W3201143670","https://openalex.org/W4225528179","https://openalex.org/W4225680573","https://openalex.org/W4225713393","https://openalex.org/W4287592659","https://openalex.org/W4298857617","https://openalex.org/W4306247551"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Voice":[0],"cloning":[1],"is":[2,47],"a":[3,14,35,105,142],"difficult":[4],"task":[5],"which":[6,46],"requires":[7],"robust":[8,87],"and":[9,83,90,101,145],"informative":[10],"features":[11,32,77,94],"incorporated":[12],"in":[13,19,34,69,128],"high":[15,51],"quality":[16,52],"TTS":[17],"system":[18],"order":[20],"to":[21,49,61,73,78,84,88,104,111,124,140,150,160],"effectively":[22],"copy":[23,141],"an":[24,129],"unseen":[25,137],"speaker's":[26,143],"voice.In":[27],"our":[28,126],"work,":[29],"we":[30],"utilize":[31],"learned":[33,93],"self-supervised":[36],"framework":[37],"via":[38],"the":[39,62,67,70,75,80,152,158,161,165],"Bootstrap":[40],"Your":[41],"Own":[42],"Latent":[43],"(BYOL)":[44],"method,":[45],"shown":[48],"produce":[50],"speech":[53,114],"representations":[54],"when":[55],"specific":[56],"audio":[57],"augmentations":[58,68],"are":[59,95,148],"applied":[60],"vanilla":[63],"algorithm.We":[64],"further":[65],"extend":[66],"training":[71],"procedure":[72],"aid":[74],"resulting":[76],"capture":[79],"speaker":[81,119,138],"identity":[82],"make":[85],"them":[86],"noise":[89],"acoustic":[91,162],"conditions.The":[92],"used":[96,149],"as":[97,102,133,135,155,157],"pre-trained":[98],"utterance-level":[99],"embeddings":[100,139],"inputs":[103],"Non-Attentive":[106],"Tacotron":[107],"based":[108],"architecture,":[109],"aiming":[110],"achieve":[112],"multispeaker":[113,131],"synthesis":[115],"without":[116],"utilizing":[117],"additional":[118],"features.This":[120],"method":[121],"enables":[122],"us":[123],"train":[125],"model":[127],"unlabeled":[130],"dataset":[132],"well":[134,156],"use":[136],"voice.Subjective":[144],"objective":[146],"evaluations":[147],"validate":[151],"proposed":[153],"model,":[154],"robustness":[159],"conditions":[163],"of":[164],"target":[166],"utterance.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
