{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:32:11Z","timestamp":1761895931394,"version":"build-2065373602"},"reference-count":32,"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\/icme59968.2025.11209204","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":["AVENet: Disentangling Features by Approximating Average Features for Voice Conversion"],"prefix":"10.1109","author":[{"given":"Wenyu","family":"Wang","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiquan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwu","family":"Ding","sequence":"additional","affiliation":[{"name":"Anhui University,School of Computer Science and Technology,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Xu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Software Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihao","family":"Li","sequence":"additional","affiliation":[{"name":"Union Wheatland Culture and Media Ltd.,Division of Music and Audio,Chengdu,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":"10.21437\/interspeech.2020-2412"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096471"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-319"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2977678"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037890"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref12","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref16","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00291"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref22","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","year":"2021","author":"Popov","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687538"},{"key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-534"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"issue":"11","key":"ref30","article-title":"Visualizing data using t-sne","volume":"9","author":"der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"}],"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\/11209204.pdf?arnumber=11209204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:02:08Z","timestamp":1761890528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209204","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}