{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:21:57Z","timestamp":1767626517462,"version":"3.37.3"},"reference-count":20,"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\/icassp48485.2024.10446855","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10916-10920","source":"Crossref","is-referenced-by-count":3,"title":["DETS: End-to-End Single-Stage Text-to-Speech Via Hierarchical Diffusion Gan Models"],"prefix":"10.1109","author":[{"given":"Linqin","family":"Wang","sequence":"first","affiliation":[{"name":"Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengxiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunli","family":"Mao","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Huang","sequence":"additional","affiliation":[{"name":"Kunming University of Science and Technology"}],"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","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proceedings of PMLR","author":"Ar\u0131k"},{"key":"ref4","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proceedings of NeurIPS","volume":"30","author":"Gibiansky"},{"key":"ref5","first-page":"6706","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"Proceedings of ICLR","author":"Ping"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref9","first-page":"17022","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proceedings of NeurIPS","volume":"33","author":"Kong"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proceedings of ICLR","author":"Ren","key":"ref10"},{"article-title":"End-to-end adversarial text-to-speech","volume-title":"Proceedings of ICLR","author":"Donahue","key":"ref11"},{"article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of PMLR","author":"Kim","key":"ref12"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proceedings of NeurIPS","volume":"33","author":"Ho"},{"article-title":"Denoising diffusion implicit models","volume-title":"Proceedings of ICLR","author":"Song","key":"ref14"},{"article-title":"Bddm: Bilateral denoising diffusion models for fast and high-quality speech synthesis","volume-title":"Proceedings of ICLR","author":"Lam","key":"ref15"},{"article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"Proceedings of ICLR","author":"Liu","key":"ref16"},{"key":"ref17","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proceedings of NeurIPS","volume":"34","author":"Dhariwal"},{"article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"Proceedings of ICLR","author":"Kong","key":"ref18"},{"article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"Proceedings of ICLR","author":"Chen","key":"ref19"},{"journal-title":"Diffgan-tts: High-fidelity and efficient text-to-speech with denoising diffusion gans","year":"2022","author":"Liu","key":"ref20"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446855.pdf?arnumber=10446855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:45Z","timestamp":1722576405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446855","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}