{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:26:22Z","timestamp":1764401182423,"version":"3.46.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249193","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"2247-2251","source":"Crossref","is-referenced-by-count":0,"title":["Noro: Noise-Robust One-Shot Voice Conversion with Hidden Speaker Representation Learning"],"prefix":"10.1109","author":[{"given":"Haorui","family":"He","sequence":"first","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Song","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuancheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongping","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University,Wuhan,China,430072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University,Singapore,639798"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Data Science, Chinese University of Hong Kong,Shenzhen,China,518172"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","author":"Popov","year":"2022","journal-title":"ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832255"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832365"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3612835"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383498"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313426"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-570"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref11","article-title":"Speech Enhancement-Assisted Stargan Voice Conversion in Noisy Environments","author":"Chan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2970"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413739"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref18","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref22","article-title":"Naturalspeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","author":"Shen","year":"2023","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref24","article-title":"Naturalspeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","volume-title":"ICML","author":"Ju","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref28","article-title":"Vq-Wav2vec: Self-Supervised Learning of Discrete Speech Representations","author":"Baevski","year":"2019","journal-title":"ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249193.pdf?arnumber=11249193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:22:16Z","timestamp":1764400936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249193","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}