{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:31:51Z","timestamp":1763202711631,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10038137","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"101-104","source":"Crossref","is-referenced-by-count":1,"title":["A New Spoken Language Teaching Tech: Combining Multi-attention and AdaIN for One-shot Cross Language Voice Conversion"],"prefix":"10.1109","author":[{"given":"Dengfeng","family":"Ke","sequence":"first","affiliation":[{"name":"Beijing Language and Culture University"}]},{"given":"Wenhan","family":"Yao","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}]},{"given":"Ruixin","family":"Hu","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}]},{"given":"Liangjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}]},{"given":"Wentao","family":"Shu","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/09588221.2017.1297836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAST.2008.4747690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref8","article-title":"Efficient non-autoregressive gan voice conversion using vqwav2vec features and dynamic convolution","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv:2203.17172"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2086"},{"key":"ref10","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref20","article-title":"Cycletransgan-evc: A cyclegan-based emotional voice conversion model with transformer","author":"Fu","year":"2021","journal-title":"arXiv preprint arXiv:2111.15159"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"Aishell-3: A multispeaker mandarin tts corpus and the baselines","author":"Shi","year":"2020","journal-title":"arXiv preprint arXiv:2010.11567"},{"key":"ref23","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Christophe","year":"2016","journal-title":"The Centre for Speech Technology Research (CSTR)"},{"key":"ref24","first-page":"17 022","article-title":"Hifi-gan: 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":"ref25","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413959"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10038137.pdf?arnumber=10038137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T14:01:00Z","timestamp":1707832860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10038137","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}