{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:28:38Z","timestamp":1776889718015,"version":"3.51.2"},"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888169","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ye-Xin","family":"Lu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Yan","family":"Sheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref4","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. ICML","author":"Casanova"},{"key":"ref5","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-645"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447809"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054701"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447818"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10348"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.09.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref17","article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","author":"Heo","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-441"},{"key":"ref20","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1428"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162849"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"}],"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\/10888169.pdf?arnumber=10888169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:17Z","timestamp":1774416377000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888169","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}