{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:47:16Z","timestamp":1776880036863,"version":"3.51.2"},"reference-count":20,"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\/icassp48485.2024.10447205","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12501-12505","source":"Crossref","is-referenced-by-count":7,"title":["Transfer the Linguistic Representations from TTS to Accent Conversion with Non-Parallel Data"],"prefix":"10.1109","author":[{"given":"Xi","family":"Chen","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiakun","family":"Pei","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liumeng","family":"Xue","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen(CUHK-Shenzhen),China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-121"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-137"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1778"},{"key":"ref6","article-title":"Improving accent conversion with reference encoder and end-to-end text-to-speech","author":"Li","year":"2020","journal-title":"Cornell University - arXiv,Cornell University - arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101302"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3060813"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10729"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053797"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094737"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3270079"},{"key":"ref14","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1110"},{"key":"ref16","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2441"},{"key":"ref19","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"}],"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\/10447205.pdf?arnumber=10447205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:32:11Z","timestamp":1722576731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447205","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}