{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:37:40Z","timestamp":1776883060715,"version":"3.51.2"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447809","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11471-11475","source":"Crossref","is-referenced-by-count":9,"title":["Noise-Robust Zero-Shot Text-to-Speech Synthesis Conditioned on Self-Supervised Speech-Representation Model with Adapters"],"prefix":"10.1109","author":[{"given":"Kenichi","family":"Fujita","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Sato","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanori","family":"Ashihara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroki","family":"Kanagawa","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Ijima","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref5","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193459"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-826"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2002-168"},{"key":"ref12","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413934"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-645"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref21","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"ICML","author":"Houlsby"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193427"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1575"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461299"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/SLT54892.2023.10023274","article-title":"Exploring efficient-tuning methods in self-supervised speech models","volume-title":"SLT","author":"Chen"},{"key":"ref29","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref31","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR","author":"Kingma"},{"key":"ref33","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref35","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICLR","author":"Kim"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447809.pdf?arnumber=10447809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:12:53Z","timestamp":1722579173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447809","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}