{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T20:52:25Z","timestamp":1725742345034},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T00:00:00Z","timestamp":1703289600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T00:00:00Z","timestamp":1703289600000},"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":[[2023,12,23]]},"DOI":"10.1109\/rivf60135.2023.10471830","type":"proceedings-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T17:56:58Z","timestamp":1711130218000},"page":"585-589","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Voice Conversion Based on Speaker Embedding Domain Generalization"],"prefix":"10.1109","author":[{"given":"Yi-Xing","family":"Lin","sequence":"first","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Chun-Hsiang","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Phuong Thi","family":"Le","sequence":"additional","affiliation":[{"name":"Fu Jen Catholic University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Bing-Jhih","family":"Huang","sequence":"additional","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Liao","family":"Chu-Xin","sequence":"additional","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Chien-Lin","family":"Huang","sequence":"additional","affiliation":[{"name":"National Cheng Kung University,Department of Computer Science and Information Engineering,Taiwan"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"National Central University,Department of Computer Science and Information Engineering,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1265"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref3","article-title":"Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion","volume-title":"Proc. NeurIPS","author":"Serr\u00e1","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref6","article-title":"Generative Adversarial Networks","volume-title":"Proc. NeurIPS","author":"Goodfellow","year":"2014"},{"key":"ref7","article-title":"Auto-Encoding Variational Bayes","volume-title":"Proc. ICLR","author":"Kingma","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref12","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"Proc. MLR","author":"Qian","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1416"},{"key":"ref14","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume-title":"Proc. NeurIPS","author":"Baevski","year":"2020"},{"volume-title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","year":"2020","author":"Chen","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2562"},{"key":"ref18","article-title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","volume-title":"Proc. NeurIPS","author":"Dou","year":"2019"},{"issue":"33","key":"ref19","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6707304"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref22","article-title":"Visualizing Data using t-SNE","author":"Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2023 RIVF International Conference on Computing and Communication Technologies (RIVF)","start":{"date-parts":[[2023,12,23]]},"location":"Hanoi, Vietnam","end":{"date-parts":[[2023,12,25]]}},"container-title":["2023 RIVF International Conference on Computing and Communication Technologies (RIVF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10471760\/10471767\/10471830.pdf?arnumber=10471830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T21:25:05Z","timestamp":1711488305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10471830\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/rivf60135.2023.10471830","relation":{},"subject":[],"published":{"date-parts":[[2023,12,23]]}}}