{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:55Z","timestamp":1774420015878,"version":"3.50.1"},"reference-count":34,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889531","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["ZCS-CDiff: A Zero-Shot Code-Switching TTS System with Conformer-Based Diffusion Model"],"prefix":"10.1109","author":[{"given":"Ke","family":"Chen","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihua","family":"Huang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682927"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096027"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1754"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687605"},{"key":"ref7","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","author":"Min","year":"2021","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-368"},{"key":"ref10","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"Kim","year":"2021","journal-title":"ICML"},{"key":"ref12","first-page":"16624","article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446855"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref16","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref18","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2021","journal-title":"ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref24","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2021","journal-title":"ICLR"},{"key":"ref25","article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","author":"Heo","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref27","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","article-title":"Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref32","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746806"}],"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\/10889531.pdf?arnumber=10889531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:57Z","timestamp":1774416357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889531","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}