{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:01:39Z","timestamp":1775199699694,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434632","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers"],"prefix":"10.1109","author":[{"given":"Yuepeng","family":"Jiang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio Speech and Language Processing Group (ASLP@NPU) School of Software,Xi’an,China"}]},{"given":"Ziqian","family":"Ning","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio Speech and Language Processing Group (ASLP@NPU) School of Software,Xi’an,China"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University Hong Kong,School of Intelligence Science and Technology,Suzhou,China"}]},{"given":"Chengjia","family":"Wang","sequence":"additional","affiliation":[{"name":"NetEase,Fuxi AI Lab,China"}]},{"given":"Mengxiao","family":"Bi","sequence":"additional","affiliation":[{"name":"NetEase,Fuxi AI Lab,China"}]},{"given":"Pengcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Geely,China"}]},{"given":"Zhonghua","family":"Fu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio Speech and Language Processing Group (ASLP@NPU) School of Software,Xi’an,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio Speech and Language Processing Group (ASLP@NPU) School of Software,Xi’an,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107807"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.01.003"},{"key":"ref3","article-title":"Noro: A noise-robust one-shot voice conversion system with hidden speaker representation capabilities","volume":"abs\/2411.19770","author":"He","year":"2024","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746636"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcce.2024.12.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1157"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref14","article-title":"Selfvc: Voice conversion with iterative refinement using self transformations","volume-title":"Proc. ICML","author":"Neekhara"},{"key":"ref15","first-page":"1","article-title":"Freevc: Towards high-quality text-free oneshot voice conversion","volume-title":"Proc. ICASSP","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2362"},{"key":"ref17","article-title":"SKQVC: one-shot voice conversion by kmeans quantization with self-supervised speech representations","volume":"abs\/2411.16147","author":"Sim","year":"2024","journal-title":"CoRR"},{"key":"ref18","article-title":"Takin-vc: Zero-shot voice conversion via jointly hybrid content and memory-augmented context-aware timbre modeling","volume":"abs\/2410.01350","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"ref21","article-title":"Flow matching for generative modeling","volume-title":"Proc. ICLR","author":"Lipman"},{"key":"ref22","article-title":"One step diffusion via shortcut models","volume":"abs\/2410.12557","author":"Frans","year":"2024"},{"key":"ref23","article-title":"Zero-shot voice conversion with diffusion transformers","volume":"abs\/2411.09943","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097147"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389740"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34758"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832365"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref30","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","volume":"139","author":"Kim"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434632.pdf?arnumber=11434632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:33Z","timestamp":1775192253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434632","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}