{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:34:33Z","timestamp":1762432473846,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687605","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["CosDiff: Code-Switching TTS Model Based on A Multi-Task DDIM"],"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,Xinjiang Key Laboratory of Signal Detection and Processing,Urumqi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexin","family":"Lu","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":"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":"10.1109\/ICASSP.2019.8682927"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"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":"10.1016\/j.apacoust.2019.107175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054722"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref12","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"NeurIPS","author":"Kim"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref15","first-page":"13963","article-title":"PortaSpeech: Portable and high-quality generative text-to-speech","volume-title":"NeurIPS","volume":"34","author":"Ren"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho"},{"article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","key":"ref18"},{"key":"ref19","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"ICML","author":"Popov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref21","first-page":"1","article-title":"Light-Grad: Lightweight diffusion probabilistic model for text-to-speech","volume-title":"ICASSP","author":"Chen"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"ICLR","author":"Kong","key":"ref27"},{"key":"ref28","article-title":"Chinese standard Mandarin speech corpus"},{"article-title":"The LJ speech dataset","year":"2017","author":"Ito","key":"ref29"},{"key":"ref30","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","author":"Kong"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687605.pdf?arnumber=10687605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:15:05Z","timestamp":1727763305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687605\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687605","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}