{"id":"https://openalex.org/W4221166168","doi":"https://doi.org/10.21437/interspeech.2022-225","title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","display_name":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221166168","doi":"https://doi.org/10.21437/interspeech.2022-225"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-225","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103176510","display_name":"Sunghwan Ahn","orcid":"https://orcid.org/0009-0001-6799-6821"},"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sunghwan Ahn","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"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":"Joun Yeop Lee","raw_affiliation_strings":["Samsung Research, Samsung Electronics, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Samsung Electronics, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027616639"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":2.5034,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90937997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"788","last_page":"792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9729999899864197,"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":0.9703999757766724,"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/naturalness","display_name":"Naturalness","score":0.8211052417755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8076673746109009},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7072122097015381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6397677063941956},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5500919222831726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49726083874702454},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46100279688835144},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4283275008201599},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41411399841308594},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33244457840919495},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06543236970901489}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8211052417755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076673746109009},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7072122097015381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6397677063941956},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5500919222831726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49726083874702454},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46100279688835144},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4283275008201599},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41411399841308594},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33244457840919495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06543236970901489},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-225","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"},{"id":"pmh:oai:arXiv.org:2203.15447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15447","pdf_url":"https://arxiv.org/pdf/2203.15447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.15447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15447","pdf_url":"https://arxiv.org/pdf/2203.15447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2060277733","https://openalex.org/W2194775991","https://openalex.org/W2788357188","https://openalex.org/W2896457183","https://openalex.org/W2940703732","https://openalex.org/W2946200149","https://openalex.org/W2955425717","https://openalex.org/W2964243274","https://openalex.org/W2965373594","https://openalex.org/W2970597249","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3090254849","https://openalex.org/W3092028330","https://openalex.org/W3094502228","https://openalex.org/W3095883095","https://openalex.org/W3140429000","https://openalex.org/W3150572638","https://openalex.org/W3167533889","https://openalex.org/W3168527213","https://openalex.org/W3169320628","https://openalex.org/W3196584150","https://openalex.org/W3198213150","https://openalex.org/W3213873715","https://openalex.org/W4239072543","https://openalex.org/W4287121924","https://openalex.org/W4287173589","https://openalex.org/W4287248095","https://openalex.org/W4297808394","https://openalex.org/W4301371414"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4391272374","https://openalex.org/W2549308614","https://openalex.org/W2023694213","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Training":[0],"a":[1,6,23,31],"text-to-speech":[2],"(TTS)":[3],"model":[4,93,110],"requires":[5],"large":[7,32],"scale":[8],"text":[9],"labeled":[10,55,101],"speech":[11,36,45,134],"corpus,":[12],"which":[13],"is":[14],"troublesome":[15],"to":[16,63],"collect.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"transfer":[24],"learning":[25],"framework":[26],"for":[27,38],"TTS":[28,66,92],"that":[29,88],"utilizes":[30],"amount":[33],"of":[34,54,74,80,100,117,125],"unlabeled":[35,44,132],"dataset":[37,102,120],"pre-training.":[39],"By":[40],"leveraging":[41],"wav2vec2.0":[42],"representation,":[43],"can":[46,121],"highly":[47],"improve":[48],"performance,":[49],"especially":[50],"in":[51,78],"the":[52,60,72,75,89,96,104,108,113,123,126],"lack":[53],"speech.":[56],"We":[57,86],"also":[58],"extend":[59],"proposed":[61,76],"method":[62,77],"zero-shot":[64],"multi-speaker":[65,133],"(ZS-TTS).":[67],"The":[68],"experimental":[69],"results":[70],"verify":[71],"effectiveness":[73],"terms":[79],"naturalness,":[81],"intelligibility,":[82],"and":[83,107],"speaker":[84,91,119],"generalization.":[85],"highlight":[87],"single":[90,118],"fine-tuned":[94,111],"on":[95,112,131],"only":[97,114],"10":[98],"minutes":[99,116],"outperforms":[103],"other":[105],"baselines,":[106],"ZS-TTS":[109],"30":[115],"generate":[122],"voice":[124],"arbitrary":[127],"speaker,":[128],"by":[129],"pre-training":[130],"corpus.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":6}],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2022-04-03T00:00:00"}