{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:28:08Z","timestamp":1762352888501},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053842","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7729-7733","source":"Crossref","is-referenced-by-count":16,"title":["One-Shot Voice Conversion Using Star-Gan"],"prefix":"10.1109","author":[{"given":"Ruobai","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yu","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Lincheng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"2016 IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref14","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"veaux","year":"2017","journal-title":"Centre for Speech Technology Research University of Edinburgh"},{"key":"ref16","article-title":"The cmu arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"article-title":"Thchs-30: A free chinese speech corpus","year":"2015","author":"wang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5326.983933"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref6","article-title":"Subband based voice conversion","author":"turk","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/002383099704000203"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","year":"2017","author":"kaneko","key":"ref9"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053842.pdf?arnumber=9053842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:19:33Z","timestamp":1656361173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053842","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}