{"id":"https://openalex.org/W4392904750","doi":"https://doi.org/10.1109/icassp48485.2024.10448471","title":"Enhancing Multilingual TTS with Voice Conversion Based Data Augmentation and Posterior Embedding","display_name":"Enhancing Multilingual TTS with Voice Conversion Based Data Augmentation and Posterior Embedding","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904750","doi":"https://doi.org/10.1109/icassp48485.2024.10448471"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5032657615","display_name":"Hyun-Wook Yoon","orcid":"https://orcid.org/0000-0002-2849-4140"},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Wook Yoon","raw_affiliation_strings":["NAVER Cloud,Korea","NAVER Cloud, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud,Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]},{"raw_affiliation_string":"NAVER Cloud, Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033037115","display_name":"Jinseob Kim","orcid":"https://orcid.org/0000-0002-9403-605X"},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin-Seob Kim","raw_affiliation_strings":["NAVER Cloud,Korea","NAVER Cloud, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud,Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]},{"raw_affiliation_string":"NAVER Cloud, Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100556054","display_name":"Ryuichi Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I4210154963","display_name":"Lintec Corporation (Japan)","ror":"https://ror.org/04qrdn471","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210154963"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["LINE Corp.,Japan","LINE Corp., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corp.,Japan","institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I4210154963"]},{"raw_affiliation_string":"LINE Corp., Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064331370","display_name":"Ryo Terashima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I4210154963","display_name":"Lintec Corporation (Japan)","ror":"https://ror.org/04qrdn471","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210154963"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Terashima","raw_affiliation_strings":["LINE Corp.,Japan","LINE Corp., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corp.,Japan","institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I4210154963"]},{"raw_affiliation_string":"LINE Corp., Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103612604","display_name":"Chanho Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Ho Song","raw_affiliation_strings":["NAVER Cloud,Korea","NAVER Cloud, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud,Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]},{"raw_affiliation_string":"NAVER Cloud, Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480212","display_name":"Jae-Min Kim","orcid":"https://orcid.org/0000-0002-7705-6462"},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Min Kim","raw_affiliation_strings":["NAVER Cloud,Korea","NAVER Cloud, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud,Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]},{"raw_affiliation_string":"NAVER Cloud, Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":"https://orcid.org/0000-0003-0642-7083"},"institutions":[{"id":"https://openalex.org/I4405260609","display_name":"NAVER Cloud (South Korea)","ror":"https://ror.org/041051y78","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405260609","https://openalex.org/I60922564"]},{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":["NAVER Cloud,Korea","NAVER Cloud, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER Cloud,Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]},{"raw_affiliation_string":"NAVER Cloud, Korea","institution_ids":["https://openalex.org/I60922564","https://openalex.org/I4405260609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12186","last_page":"12190"},"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":0.9991000294685364,"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":0.9991000294685364,"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/polyglot","display_name":"Polyglot","score":0.9699599146842957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8246185183525085},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.791387140750885},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6736159920692444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6397237181663513},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5855101943016052},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5329628586769104},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5263843536376953},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5250163674354553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4637712836265564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40263456106185913},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.26468729972839355}],"concepts":[{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.9699599146842957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246185183525085},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.791387140750885},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6736159920692444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6397237181663513},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5855101943016052},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5329628586769104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5263843536376953},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5250163674354553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4637712836265564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40263456106185913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26468729972839355},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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:10.1109/icassp48485.2024.10448471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316108","display_name":"NAV","ror":"https://ror.org/00qghd717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1964940342","https://openalex.org/W2755348046","https://openalex.org/W2904459034","https://openalex.org/W2962691331","https://openalex.org/W2964243274","https://openalex.org/W2972789651","https://openalex.org/W2973034126","https://openalex.org/W3007859642","https://openalex.org/W3015959238","https://openalex.org/W3026874504","https://openalex.org/W3091928890","https://openalex.org/W3096514088","https://openalex.org/W3097297926","https://openalex.org/W3115632755","https://openalex.org/W4224301045","https://openalex.org/W4225276642","https://openalex.org/W4226424742","https://openalex.org/W4283771593","https://openalex.org/W4283777098","https://openalex.org/W4388400684","https://openalex.org/W6640963894","https://openalex.org/W6765987481","https://openalex.org/W6777694618","https://openalex.org/W6784545093","https://openalex.org/W6787860843","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6811227718"],"related_works":["https://openalex.org/W4243497717","https://openalex.org/W4393571790","https://openalex.org/W3021456553","https://openalex.org/W4393815655","https://openalex.org/W4287790127","https://openalex.org/W4250712637","https://openalex.org/W3034786336","https://openalex.org/W2772686614","https://openalex.org/W2482180524","https://openalex.org/W2902064555"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,11,41],"multilingual,":[4],"multi-speaker":[5,43],"(MM)":[6],"TTS":[7,97],"system":[8],"by":[9],"using":[10],"voice":[12],"conversion":[13],"(VC)-based":[14],"data":[15,31],"augmentation":[16],"method.":[17],"Creating":[18],"an":[19],"MM-TTS":[20,77],"model":[21,45,54,78,149],"is":[22,65,86,117],"challenging,":[23],"owing":[24],"to":[25,67,87,119],"the":[26,61,76,96,105,115,121,125,131,135,140,144,147,151],"difficulties":[27],"of":[28,134,153],"collecting":[29],"polyglot":[30,71,93],"from":[32,139],"multiple":[33,48],"speakers.":[34],"To":[35,111],"address":[36],"this":[37,53,113],"problem,":[38],"we":[39,74],"adopt":[40],"cross-lingual,":[42],"VC":[44],"trained":[46,118],"with":[47,79],"speakers\u2019":[49],"monolingual":[50],"databases.":[51],"As":[52],"effectively":[55],"transfers":[56],"acoustic":[57,122],"attributes":[58],"while":[59],"retaining":[60],"content":[62],"information,":[63],"it":[64],"possible":[66],"generate":[68],"each":[69],"speaker\u2019s":[70],"corpora.":[72],"Subsequently,":[73],"design":[75],"variational":[80],"autoencoder":[81],"(VAE)-based":[82],"posterior":[83,136],"embeddings.":[84],"It":[85],"be":[88],"noted":[89],"that":[90],"incorporating":[91],"VC-augmented":[92,128],"corpora":[94,106],"into":[95],"training":[98,145],"process":[99],"might":[100],"degrade":[101],"synthetic":[102],"quality,":[103],"since":[104],"sometimes":[107],"contain":[108],"unwanted":[109],"artifacts.":[110],"mitigate":[112],"issue,":[114],"VAE":[116],"capture":[120],"dissimilarity":[123],"between":[124],"recorded":[126],"and":[127],"datasets.":[129],"Through":[130],"selective":[132],"choice":[133],"embeddings":[137],"obtained":[138],"original":[141],"recordings":[142],"in":[143],"set,":[146],"proposed":[148],"enables":[150],"generation":[152],"acoustically":[154],"clearer":[155],"voices.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
