{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:31Z","timestamp":1775229751798,"version":"3.50.1"},"reference-count":26,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp48485.2024.10447822","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10501-10505","source":"Crossref","is-referenced-by-count":9,"title":["Reflow-TTS: A Rectified Flow Model for High-Fidelity Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Wenhao","family":"Guan","sequence":"first","affiliation":[{"name":"Xiamen University,School of Informatics,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Su","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Miao","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjia","family":"Xie","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,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":"10.1609\/aaai.v33i01.33016706"},{"key":"ref3","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref5","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1151"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref12","article-title":"Diffgan-tts: High-fidelity and efficient text-to-speech with denoising diffusion gans","author":"Liu","year":"2022"},{"key":"ref13","article-title":"Resgrad: Residual denoising diffusion probabilistic models for text to speech","author":"Chen","year":"2022"},{"key":"ref14","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/960126.806879"},{"key":"ref17","article-title":"Voicebox: Text-guided multi-lingual universal speech generation at scale","author":"Le","year":"2023"},{"key":"ref18","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref20","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref23","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref25","first-page":"17022","article-title":"Hifigan: 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":"ref26","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"}],"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\/10447822.pdf?arnumber=10447822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:13:40Z","timestamp":1722579220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447822","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}