{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:30Z","timestamp":1761894690289,"version":"build-2065373602"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210176","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["InvoxSVC: Any-to-any Zero-shot Singing Voice Conversion with In-Context Learning in Latent Flow Matching"],"prefix":"10.1109","author":[{"given":"Wangjin","family":"Zhou","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Du","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Guan","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,Xiamen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Macau University of Science and Technology,Faculty of Innovation Engineering,Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglin","family":"Xu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Computer Science and Engineering,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800419"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800358"},{"article-title":"Zero-shot singing voice conversion: Built upon clustering-based phoneme representations","year":"2024","author":"Zhou","key":"ref6"},{"key":"ref7","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Van Den Oord","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.65"},{"article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","year":"2023","author":"Zhang","key":"ref10"},{"article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","year":"2024","author":"Du","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-250"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Flow matching for generative modeling","year":"2022","author":"Lipman","key":"ref18"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref19"},{"key":"ref20","first-page":"5775","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"article-title":"High-fidelity audio compression with improved rvqgan","year":"2023","author":"Kumar","key":"ref22"},{"article-title":"Long-form music generation with latent diffusion","year":"2024","author":"\u00c9vans","key":"ref23"},{"key":"ref24","first-page":"1583","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume":"33","author":"Ziyin","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"article-title":"Common voice: A massively-multilingual speech corpus","year":"2019","author":"Ardila","key":"ref26"},{"article-title":"Large scale gan training for high fidelity natural image synthesis","year":"2018","author":"Brock","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref30","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210176.pdf?arnumber=11210176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:42Z","timestamp":1761888822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210176","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}