{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:59:50Z","timestamp":1776887990170,"version":"3.51.2"},"reference-count":32,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/icassp48485.2024.10446160","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T14:56:31Z","timestamp":1710773791000},"page":"12296-12300","source":"Crossref","is-referenced-by-count":20,"title":["SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention"],"prefix":"10.1109","author":[{"given":"Junjie","family":"Li","sequence":"first","affiliation":[{"name":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Guo","sequence":"additional","affiliation":[{"name":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xie","family":"Chen","sequence":"additional","affiliation":[{"name":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,X-LANCE Lab, Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref2","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref3","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref4","first-page":"6332","article-title":"Speechsplit2. 0: Unsupervised speech disentanglement for voice conversion without tuning autoencoder bottlenecks","volume-title":"Proc. IEEE ICASSP","author":"Chan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747434"},{"key":"ref6","author":"Wang","year":"2021","journal-title":"Noisevc: Towards high quality zero-shot voice conversion"},{"key":"ref7","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. NeurIPS","volume":"31","author":"Kingma"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3308374"},{"key":"ref10","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":"ref11","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. ICLR","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747743"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11225"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746278"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414975"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3308474"},{"key":"ref25","author":"Huang","year":"2023","journal-title":"Make-a-voice: Unified voice synthesis with discrete representation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29747"},{"key":"ref27","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094850"},{"key":"ref32","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. IEEE ASRU.","author":"Povey"}],"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\/10446160.pdf?arnumber=10446160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:33:29Z","timestamp":1769488409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446160","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}