{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:22:46Z","timestamp":1772205766754,"version":"3.50.1"},"reference-count":21,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447661","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11336-11340","source":"Crossref","is-referenced-by-count":3,"title":["DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation"],"prefix":"10.1109","author":[{"given":"Zhichao","family":"Wu","sequence":"first","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiulin","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sixing","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University of Aeronautics and Astronautics,Nanjing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref9","article-title":"Taming visually guided sound generation","author":"Iashin","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094639"},{"key":"ref14","article-title":"g2pe","author":"Park","year":"2019"},{"key":"ref15","article-title":"Discrete contrastive diffusion for cross-modal music and image generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhu"},{"key":"ref16","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref17","article-title":"Fast and reliable f0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech","volume-title":"Audio Engineering Society Conference: 35th International Conference: Audio for Games","author":"Morise"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"}],"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\/10447661.pdf?arnumber=10447661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:55:37Z","timestamp":1722578137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447661","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}