{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:22:46Z","timestamp":1768339366392,"version":"3.49.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389766","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":12,"title":["E3 TTS: Easy End-to-End Diffusion-Based Text To Speech"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Gao","sequence":"first","affiliation":[{"name":"Google"}]},{"given":"Nobuyuki","family":"Morioka","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Nanxin","family":"Chen","sequence":"additional","affiliation":[{"name":"Google"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref3","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv:2011.13456"},{"key":"ref4","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint arXiv:2204.06125"},{"key":"ref6","article-title":"simple diffusion: End-to-end diffusion for high resolution images","author":"Hoogeboom","year":"2023","journal-title":"arXiv preprint arXiv:2301.11093"},{"key":"ref7","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref8","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"International Conference on Learning Representations","author":"Kong"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095100"},{"key":"ref11","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref15","article-title":"Non-attentive tacotron: Robust and controllable neural tts synthesis including unsupervised duration modeling","author":"Shen","year":"2020","journal-title":"arXiv preprint arXiv:2010.04301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414718"},{"key":"ref17","article-title":"Guided-tts: A diffusion model for text-to-speech via classifier guidance","author":"Kim","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00439"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref22","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref23","article-title":"End-to-end adversarial text-to-speech","volume-title":"International Conference on Learning Representations","author":"Donahue"},{"key":"ref24","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Ming-Wei Chang Kenton"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","article-title":"Glow-tts: A generative flow for text-tospeech via monotonic alignment search","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Kim"},{"key":"ref27","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Popov"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref29","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref30","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref36","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Kalchbrenner"},{"key":"ref37","first-page":"3370","article-title":"FloWaveNet: A generative flow for raw audio","volume-title":"Proceedings of the 36th International Conference on Machine Learning","volume":"97","author":"Kim"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094909"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-204"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref41","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389766.pdf?arnumber=10389766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:35Z","timestamp":1706027795000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389766","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}