{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:37:06Z","timestamp":1776886626361,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889831","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["CASC-XVC: Zero-Shot Cross-Lingual Voice Conversion with Content Accordant and Speaker Contrastive Losses"],"prefix":"10.1109","author":[{"given":"Han-Jie","family":"Guo","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Yan","family":"Sheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-687"},{"key":"ref4","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref5","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref6","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446160"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022787"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446264"},{"key":"ref10","article-title":"SelfVC: Voice conversion with iterative refinement using self transformations","author":"Neekhara","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-22"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747140"},{"key":"ref13","article-title":"AutoCycle-VC: Towards bottleneck-independent zero-shot cross-lingual voice conversion","author":"Choi","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref16","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref20","article-title":"Density estimation using Real NVP","volume-title":"International Conference on Learning Representations","author":"Dinh"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3193761"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271107"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"ref26","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":"ref27","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"11","key":"ref28","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889831.pdf?arnumber=10889831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:10Z","timestamp":1774416070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889831","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}