{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:50Z","timestamp":1776956450708,"version":"3.51.4"},"reference-count":29,"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\/icassp48485.2024.10446750","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11441-11445","source":"Crossref","is-referenced-by-count":3,"title":["An Experimental Comparison of Noise-Robust Text-To-Speech Synthesis Systems Based On Self-Supervised Representation"],"prefix":"10.1109","author":[{"given":"Xiaoying","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),Hefei,China"}]},{"given":"Qiushi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),Hefei,China"}]},{"given":"Yuchen","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref7","article-title":"Noise robust tts for low resource speakers using pre-trained model and speech enhancement","author":"Dai","year":"2020"},{"key":"ref8","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. ICLR","author":"Hsu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413934"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-294"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-645"},{"key":"ref13","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. ICML","author":"Baevski"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275033"},{"key":"ref23","article-title":"Rep2wav: Noise robust text-to-speech using self-supervised representations","author":"Zhu","year":"2023"},{"key":"ref24","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref25","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref26","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"}],"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\/10446750.pdf?arnumber=10446750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:54:14Z","timestamp":1722574454000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446750","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}