{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:40:03Z","timestamp":1783183203381,"version":"3.54.6"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005374","name":"Nanjing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446284","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12161-12165","source":"Crossref","is-referenced-by-count":2,"title":["ESVC: Combining Adaptive Style Fusion and Multi-Level Feature Disentanglement for Expressive Singing Voice Conversion"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Yang","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minchuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanping","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Li","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389671"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853599"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2014-539"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10316"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"ICML 2022","author":"Qian"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"ref13","article-title":"Phonetic posteriorgrams based many-to-many singing voice conversion via adversarial training","author":"Guo","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414137"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746812"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294712"},{"key":"ref19","article-title":"Styletts: A style-based generative model for natural and diverse text-to-speech synthesis","author":"Li","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref23","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICML 2021","author":"Kim"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389651"},{"key":"ref26","first-page":"1779","article-title":"Club: A contrastive log-ratio upper bound of mutual information","volume-title":"International conference on machine learning","author":"Cheng"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-960"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475437"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446284.pdf?arnumber=10446284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:09:08Z","timestamp":1722575348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446284","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}