{"id":"https://openalex.org/W4391640577","doi":"https://doi.org/10.1109/taslp.2024.3364085","title":"Transfer Learning for Low-Resource, Multi-Lingual, and Zero-Shot Multi-Speaker Text-to-Speech","display_name":"Transfer Learning for Low-Resource, Multi-Lingual, and Zero-Shot Multi-Speaker Text-to-Speech","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391640577","doi":"https://doi.org/10.1109/taslp.2024.3364085"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3364085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3364085","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Kakao Enterprise, Seongnam, Republic of Korea","Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4689-3110","affiliations":[{"raw_affiliation_string":"Kakao Enterprise, Seongnam, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210164379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8150-765X","affiliations":[{"raw_affiliation_string":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210164379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-1319-8215","affiliations":[{"raw_affiliation_string":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210164379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050154985","display_name":"Jaesam Yoon","orcid":"https://orcid.org/0000-0002-9978-0582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaesam Yoon","raw_affiliation_strings":["Kakao Enterprise, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9978-0582","affiliations":[{"raw_affiliation_string":"Kakao Enterprise, Seongnam, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103192158","display_name":"Won Jang","orcid":"https://orcid.org/0000-0002-4711-780X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Won Jang","raw_affiliation_strings":["Kakao Enterprise, Seongnam, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-4711-780X","affiliations":[{"raw_affiliation_string":"Kakao Enterprise, Seongnam, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Institute of New Media and Communications, Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210164379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":1.3942,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82779576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"1519","last_page":"1530"},"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/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"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/T11309","display_name":"Music and Audio Processing","score":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.7852178812026978},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7559829950332642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5655677318572998},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5424490571022034},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5407220721244812},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4986240863800049},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4694247841835022},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45111727714538574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4186609387397766},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0894637405872345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852178812026978},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7559829950332642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5655677318572998},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5424490571022034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407220721244812},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4986240863800049},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4694247841835022},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45111727714538574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4186609387397766},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0894637405872345},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3364085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3364085","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2060277733","https://openalex.org/W2187089797","https://openalex.org/W2884225676","https://openalex.org/W2936832667","https://openalex.org/W2962770929","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2972473628","https://openalex.org/W2973049979","https://openalex.org/W2973084242","https://openalex.org/W2990124956","https://openalex.org/W2998572311","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3081416955","https://openalex.org/W3090254849","https://openalex.org/W3095012670","https://openalex.org/W3095410713","https://openalex.org/W3097290232","https://openalex.org/W3140429000","https://openalex.org/W3167533889","https://openalex.org/W3181257032","https://openalex.org/W3196584150","https://openalex.org/W3198213150","https://openalex.org/W3198429080","https://openalex.org/W3198575134","https://openalex.org/W3209059054","https://openalex.org/W4206596421","https://openalex.org/W4221166168","https://openalex.org/W4225746985","https://openalex.org/W4283640572","https://openalex.org/W4296070453","https://openalex.org/W4297808394","https://openalex.org/W4297841354","https://openalex.org/W4297841714","https://openalex.org/W4312095868","https://openalex.org/W4313148337","https://openalex.org/W6752888775","https://openalex.org/W6762242920","https://openalex.org/W6770838157","https://openalex.org/W6772349387","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783527727","https://openalex.org/W6795807602","https://openalex.org/W6795952400","https://openalex.org/W6796464841","https://openalex.org/W6798575157","https://openalex.org/W6803547063","https://openalex.org/W6805710207","https://openalex.org/W6839738141","https://openalex.org/W6844194202","https://openalex.org/W6846288075","https://openalex.org/W6846936884","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2549308614","https://openalex.org/W2023694213"],"abstract_inverted_index":{"Though":[0],"neural":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4,31],"show":[5],"remarkable":[6],"performance,":[7],"they":[8],"still":[9],"require":[10],"a":[11,34,47,68,91,100,128],"large":[12],"amount":[13,102,130],"ofpaired":[14],"dataset,":[15],"which":[16,120],"is":[17],"expensive":[18],"to":[19,95],"collect.":[20],"The":[21,106,150],"heavy":[22],"demand":[23],"for":[24,51,124],"collecting":[25],"paired":[26,104],"datasets":[27],"makes":[28],"the":[29,75,96,112,136,159],"TTS":[30,97,148],"support":[32],"only":[33],"small":[35,101],"number":[36],"of":[37,103,131,138,163],"speakers":[38],"and":[39,55,145,166],"languages.":[40],"To":[41],"address":[42],"this":[43,84],"problem,":[44],"we":[45,59,88],"introduce":[46],"transfer":[48],"learning":[49,93,126],"framework":[50],"multi-lingual,":[52,144],"zero-shot":[53,146],"multi-speaker,":[54],"low-resource":[56],"TTS.":[57],"Firstly,":[58],"pretrain":[60],"our":[61,139,155],"model":[62,98,141],"in":[63,142,161],"an":[64],"unsupervised":[65],"manner":[66],"with":[67,99,127],"multi-lingual":[69],"multi-speaker":[70,147],"speech-only":[71,114],"dataset":[72,115],"by":[73],"leveraging":[74],"self-supervised":[76],"speech":[77],"representations":[78,109],"as":[79],"intermediate":[80],"linguistic":[81,86,108],"representations.":[82],"Given":[83],"pretrained":[85,107],"information,":[87],"then":[89],"apply":[90],"supervised":[92,125],"technique":[94],"dataset.":[105],"extracted":[110],"from":[111],"large-scale":[113],"facilitate":[116],"phoneme-to-linguistic":[117],"feature":[118],"matching,":[119],"provides":[121],"good":[122],"guidance":[123],"limited":[129],"labeled":[132],"data.":[133],"We":[134],"evaluate":[135],"performance":[137],"proposed":[140,156],"low-resource,":[143],"tasks.":[149],"experimental":[151],"results":[152],"demonstrate":[153],"that":[154],"method":[157],"outperforms":[158],"baseline":[160],"terms":[162],"naturalness,":[164],"intelligibility,":[165],"speaker":[167],"similarity.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
