{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:55Z","timestamp":1774419595282,"version":"3.50.1"},"reference-count":25,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889083","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":0,"title":["Voice Conversion for Low-Resource Languages via Knowledge Transfer and Domain-Adversarial Training"],"prefix":"10.1109","author":[{"given":"Huu Tuong","family":"Tu","sequence":"first","affiliation":[{"name":"VNPT AI, VNPT Group,Hanoi,Vietnam"}]},{"given":"Luong","family":"Thanh Long","sequence":"additional","affiliation":[{"name":"VNPT AI, VNPT Group,Hanoi,Vietnam"}]},{"given":"Vu","family":"Huan","sequence":"additional","affiliation":[{"name":"National Economics University,Business AI Lab, College of Technology,Hanoi,Vietnam"}]},{"given":"Nguyen Thi","family":"Phuong Thao","sequence":"additional","affiliation":[{"name":"Hanoi University of Science and Technology,Hanoi,Vietnam"}]},{"given":"Nguyen","family":"Van Thang","sequence":"additional","affiliation":[{"name":"VNPT AI, VNPT Group,Hanoi,Vietnam"}]},{"given":"Nguyen Tien","family":"Cuong","sequence":"additional","affiliation":[{"name":"VNPT AI, VNPT Group,Hanoi,Vietnam"}]},{"given":"Nguyen","family":"Thi Thu Trang","sequence":"additional","affiliation":[{"name":"Hanoi University of Science and Technology,Hanoi,Vietnam"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094850"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref5","article-title":"Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref10","first-page":"189","volume-title":"Domain-Adversarial Training of Neural Networks","author":"Ganin","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683204"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00312-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414757"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref20","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"International conference on machine learning","author":"Larsen"},{"key":"ref21","first-page":"51","article-title":"A non-expert Kaldi recipe for Vietnamese speech recognition system","volume-title":"WLSI\/OIAF4HLT2016","author":"Luong","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29411"},{"key":"ref23","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":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","volume":"33","author":"Baevski"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"}],"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\/10889083.pdf?arnumber=10889083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:41Z","timestamp":1774416221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889083\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889083","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}