{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:57:26Z","timestamp":1776884246672,"version":"3.51.2"},"reference-count":47,"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"}],"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890230","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["E1 TTS: Simple and Fast Non-Autoregressive TTS"],"prefix":"10.1109","author":[{"given":"Zhijun","family":"Liu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxiao","family":"Bi","sequence":"additional","affiliation":[{"name":"NetEase Inc.,Fuxi AI Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref2","article-title":"Deep Voice: Real-time neural text-to-speech","volume-title":"ICML","author":"Ar\u0131k"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413889"},{"key":"ref4","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"NeurIPS","author":"Ren"},{"key":"ref5","article-title":"VARA-TTS: Non-autoregressive text-to-speech synthesis based on very deep VAE with residual attention","author":"Liu","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref7","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2235"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1392"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"ref12","article-title":"Seed-TTS: A family of high-quality versatile speech generation models","author":"Anastassiou","year":"2024"},{"key":"ref13","article-title":"DiTTo-TTS: Efficient and scalable zero-shot text-to-speech with diffusion transformer","author":"Lee","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448121"},{"key":"ref15","article-title":"YourTTS: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"ICML","author":"Casanova"},{"key":"ref16","article-title":"The paradox of diffusion distillation","author":"Dieleman","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref18","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681044"},{"key":"ref21","article-title":"Consistency models","volume-title":"ICML","author":"Song"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445948"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447822"},{"key":"ref24","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"ICLR","author":"Liu"},{"key":"ref25","article-title":"Diff-Instruct: A universal approach for transferring knowledge from pre-trained diffusion models","volume-title":"NeurIPS","author":"Luo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00632"},{"key":"ref27","article-title":"Prolific-Dreamer: High-fidelity and diverse text-to-3D generation with variational score distillation","volume-title":"NeurIPS","author":"Wang"},{"key":"ref28","article-title":"LCM-LoRA: A universal stable-diffusion acceleration module","author":"Luo","year":"2023"},{"key":"ref29","article-title":"Diffusion models are innate one-step generators","author":"Zheng","year":"2024"},{"key":"ref30","article-title":"Generative adversarial nets","volume-title":"NeurIPS","author":"Goodfellow"},{"key":"ref31","article-title":"Autoregressive diffusion transformer for text-to-speech synthesis","author":"Liu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref35","article-title":"Non-autoregressive neural text-to-speech","volume-title":"ICML","author":"Peng"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095100"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref40","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"Lee","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref42","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"NeurIPS","author":"Heusel"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29747"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34703"},{"key":"ref45","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICML","author":"Kim"},{"key":"ref46","article-title":"Noise schedules considered harmful","author":"Dieleman","year":"2024"},{"key":"ref47","article-title":"DMDSpeech: Distilled diffusion model surpassing the teacher in zero-shot speech synthesis via direct metric optimization","author":"Li","year":"2024"}],"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\/10890230.pdf?arnumber=10890230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:39Z","timestamp":1774416399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890230","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}