{"id":"https://openalex.org/W3213544594","doi":"https://doi.org/10.1109/taslp.2022.3167258","title":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","display_name":"Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3213544594","doi":"https://doi.org/10.1109/taslp.2022.3167258","mag":"3213544594"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3167258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3167258","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.04040","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-9720-811X","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069664539","display_name":"Chyi-Jiunn Lin","orcid":"https://orcid.org/0000-0002-2447-9330"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chyi-Jiunn Lin","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-2447-9330","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084868332","display_name":"Da-Rong Liu","orcid":"https://orcid.org/0009-0005-0090-7408"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Rong Liu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015249499","display_name":"Y.-Y. Chen","orcid":"https://orcid.org/0000-0003-4062-0821"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chen Chen","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-4062-0821","affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-9654-5747","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0753,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97391808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1558","last_page":"1571"},"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/T11309","display_name":"Music and Audio Processing","score":0.9926000237464905,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9912999868392944,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929166555404663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7422956824302673},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.663284182548523},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5909246802330017},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5847510695457458},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5605735778808594},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5474796891212463},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4370032846927643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39068853855133057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05780762434005737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929166555404663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7422956824302673},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.663284182548523},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5909246802330017},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5847510695457458},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5605735778808594},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5474796891212463},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4370032846927643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39068853855133057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05780762434005737},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3167258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3167258","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"},{"id":"pmh:oai:arXiv.org:2111.04040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.04040","pdf_url":"https://arxiv.org/pdf/2111.04040","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:2111.04040","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.04040","pdf_url":"https://arxiv.org/pdf/2111.04040","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2471925828","display_name":null,"funder_award_id":"110-2223-E-002 -007-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G4828869825","display_name":null,"funder_award_id":"111-2628-E-002-013","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2046056978","https://openalex.org/W2114925438","https://openalex.org/W2519091744","https://openalex.org/W2604763608","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2842511635","https://openalex.org/W2949382160","https://openalex.org/W2962788625","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963534259","https://openalex.org/W2963609956","https://openalex.org/W2963912924","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2995049146","https://openalex.org/W3003387229","https://openalex.org/W3015826515","https://openalex.org/W3041561163","https://openalex.org/W3095035471","https://openalex.org/W3095199334","https://openalex.org/W3096086473","https://openalex.org/W3097531247","https://openalex.org/W3099782249","https://openalex.org/W3128910262","https://openalex.org/W3130016944","https://openalex.org/W3161558238","https://openalex.org/W3161704465","https://openalex.org/W3161959914","https://openalex.org/W3198270377","https://openalex.org/W4297808394","https://openalex.org/W6736057607","https://openalex.org/W6745569068","https://openalex.org/W6745697700","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6765987481","https://openalex.org/W6767111847","https://openalex.org/W6768532476","https://openalex.org/W6772879244","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6790220310","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Personalizing":[0],"a":[1,6,32,50,90,129,150,158,195,201],"speech":[2,15,101,216],"synthesis":[3],"system":[4,12,33],"is":[5,248],"highly":[7],"desired":[8],"application,":[9],"where":[10],"the":[11,17,43,80,99,104,109,114,118,133,146,163,177,188,226,232,237,242,246,260],"can":[13,97,174,212,257],"generate":[14],"with":[16,20,56,192,221,250],"user\u2019s":[18,100],"voice":[19],"rare":[21],"enrolled":[22,58],"recordings.":[23],"There":[24],"are":[25],"two":[26,193],"main":[27],"approaches":[28],"to":[29,75,132,156,161,165,181],"build":[30],"such":[31],"in":[34],"recent":[35],"works:":[36],"speaker":[37,40,46,83,91,106,110,134,168,196,202,227,233,243],"adaptation":[38,47,135,169,197,223,228],"and":[39,120,200,230,265],"encoding.":[41],"On":[42,79],"one":[44],"hand,":[45,82],"methods":[48,85],"fine-tune":[49],"trained":[51,94],"multi-speaker":[52,151],"text-to-speech":[53],"(TTS)":[54],"model":[55,96,164,180],"few":[57,218],"samples.":[59],"However,":[60],"they":[61],"require":[62],"at":[63],"least":[64],"thousands":[65],"of":[66,149,245,254],"fine-tuning":[67],"steps":[68,224],"for":[69],"high-quality":[70],"adaptation,":[71],"making":[72],"it":[73],"hard":[74],"apply":[76],"on":[77,103,262,269],"devices.":[78],"other":[81],"encoding":[84,203,234],"encode":[86],"enrollment":[87,219],"utterances":[88],"into":[89],"embedding.":[92,107],"The":[93,206],"TTS":[95,152,179],"synthesize":[98,213],"conditioned":[102],"corresponding":[105],"Nevertheless,":[108],"encoder":[111,244],"suffers":[112],"from":[113,217],"generalization":[115],"gap":[116],"between":[117],"seen":[119],"unseen":[121,182],"speakers.":[122],"In":[123],"this":[124],"paper,":[125],"we":[126,139,173],"propose":[127],"applying":[128],"meta-learning":[130],"algorithm":[131,148],"method.":[136],"More":[137],"specifically,":[138],"use":[140],"Model":[141],"Agnostic":[142],"Meta-Learning":[143],"(MAML)":[144],"as":[145],"training":[147,239],"model,":[153],"which":[154],"aims":[155],"find":[157],"great":[159],"meta-initialization":[160],"adapt":[162,176],"any":[166],"few-shot":[167],"tasks":[170],"quickly.":[171],"Therefore,":[172],"also":[175],"meta-trained":[178],"speakers":[183,253],"efficiently.":[184],"Our":[185],"experiments":[186],"compare":[187],"proposed":[189],"method":[190,198,204],"(Meta-TTS)":[191],"baselines:":[194],"baseline":[199,229,235,247,261],"baseline.":[205],"evaluation":[207],"results":[208,268],"show":[209],"that":[210],"Meta-TTS":[211,256],"high":[214],"speaker-similarity":[215],"samples":[220],"fewer":[222],"than":[225],"outperforms":[231],"under":[236],"same":[238],"scheme.":[240],"When":[241],"pre-trained":[249],"extra":[251],"8371":[252],"data,":[255],"still":[258],"outperform":[259],"LibriTTS":[263],"dataset":[264],"achieve":[266],"comparable":[267],"VCTK":[270],"dataset.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}