{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T14:34:44Z","timestamp":1767969284606,"version":"3.49.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region of China","award":["2022D01C59"],"award-info":[{"award-number":["2022D01C59"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12464060"],"award-info":[{"award-number":["12464060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3543456","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T18:28:16Z","timestamp":1739903296000},"page":"1051-1055","source":"Crossref","is-referenced-by-count":1,"title":["UnitDiff: A Unit-Diffusion Model for Code-Switching Speech Synthesis"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3069-9769","authenticated-orcid":false,"given":"Ke","family":"Chen","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Urumqi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0973-4401","authenticated-orcid":false,"given":"Zhihua","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xinjiang University, Urumqi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6907-5770","authenticated-orcid":false,"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682927"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1754"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2019.107175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687605"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10316"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445804"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref15","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref17","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref18","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-715"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446058"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446830"},{"key":"ref23","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Salimans","year":"2022"},{"key":"ref24","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref25","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref26","article-title":"Chinese standard Mandarin speech corpus"},{"key":"ref27","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref28","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref29","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref30","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2020"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/97\/10802935\/10891773-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10891773.pdf?arnumber=10891773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:53:37Z","timestamp":1742234017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3543456","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}