{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:22:49Z","timestamp":1783700569056,"version":"3.55.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022787","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"814-821","source":"Crossref","is-referenced-by-count":10,"title":["Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using \u00df-VAE"],"prefix":"10.1109","author":[{"given":"Hui","family":"Lu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Disong","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref3","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014","author":"Kingma","year":"2014"},{"key":"ref4","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"97","author":"Qian","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref7","article-title":"Improving zero-shot voice style transfer via disentangled representation learning","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","volume":"2021","author":"Yuan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref11","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Higgins"},{"key":"ref12","article-title":"Understanding disentangling in \u03b2-vae","volume":"abs\/1804.03599","author":"Burgess","year":"2018","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003798"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414788"},{"key":"ref16","first-page":"1878","article-title":"Unsu-pervised learning of disentangled and interpretable representations from sequential data","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Hsu","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2525"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref19","first-page":"4114","article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019","volume":"97","author":"Locatello","year":"2019"},{"key":"ref20","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"2654","article-title":"Disentangling by factorising","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","volume":"80","author":"Kim","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.29007\/l6qh"},{"issue":"1","key":"ref23","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfit-ting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","volume":"abs\/1412.6980","author":"Kingma","year":"2015","journal-title":"CoRR"},{"key":"ref27","volume-title":"Cstr vctk corpus: English multi-speaker cor-pus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref29","first-page":"5656","article-title":"Disentangled sequential autoencoder","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","volume":"80","author":"Li","year":"2018"},{"key":"ref30","first-page":"17022","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":"ref31","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022787.pdf?arnumber=10022787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T15:34:21Z","timestamp":1709393661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022787","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}