{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:50:50Z","timestamp":1778604650911,"version":"3.51.4"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["111-2628-E-002-013"],"award-info":[{"award-number":["111-2628-E-002-013"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["110-2223-E-002 -007-MY3"],"award-info":[{"award-number":["110-2223-E-002 -007-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3167258","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T19:36:21Z","timestamp":1649878581000},"page":"1558-1571","source":"Crossref","is-referenced-by-count":50,"title":["Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9720-811X","authenticated-orcid":false,"given":"Sung-Feng","family":"Huang","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2447-9330","authenticated-orcid":false,"given":"Chyi-Jiunn","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da-Rong","family":"Liu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4062-0821","authenticated-orcid":false,"given":"Yi-Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-5747","authenticated-orcid":false,"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","author":"Oord"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","article-title":"FastSpeech 2: Fast and high-quality end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref4","first-page":"2966","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gibiansky","year":"2017"},{"key":"ref5","first-page":"214","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref6","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref8","first-page":"10040","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Arik","year":"2018"},{"key":"ref9","article-title":"Sample efficient adaptive text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1745"},{"key":"ref11","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414727"},{"key":"ref13","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Taigman","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1737"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref18","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref19","article-title":"Revisiting meta-learning as supervised learning","author":"Chao","year":"2020"},{"key":"ref20","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of MAML","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Raghu","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref30","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref32","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref34","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","volume-title":"version 0.92), [Sound","author":"Yamagishi","year":"2019"},{"key":"ref35","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09756900.pdf?arnumber=9756900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:20:37Z","timestamp":1705958437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9756900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3167258","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}