{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:59:12Z","timestamp":1778605152579,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832320","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"682-689","source":"Crossref","is-referenced-by-count":33,"title":["E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS"],"prefix":"10.1109","author":[{"given":"Sefik Emre","family":"Eskimez","sequence":"first","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Manthan","family":"Thakker","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Canrun","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Chung-Hsien","family":"Tsai","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Hemin","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Zirun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Min","family":"Tang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Yanqing","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corporation,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren"},{"key":"ref2","article-title":"FastSpeech 2: Fast and high-quality end-toend text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref3","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","volume":"33","author":"Kim"},{"key":"ref4","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref6","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. NeurIPS","volume":"31","author":"Arik"},{"key":"ref7","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. NeurIPS","volume":"31","author":"Jia"},{"key":"ref8","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":"ref9","article-title":"Speechx: Neural codec language model as a versatile speech transformer","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2308.06873"},{"key":"ref10","article-title":"Vall-t: Decoder-only generative transducer for robust and decoding-controllable text-to-speech","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2401.14321"},{"key":"ref11","article-title":"RALL-E: Robust codec language modeling with chain-of-thought prompting for text-to-speech synthesis","author":"Xin","year":"2024","journal-title":"arXiv preprint arXiv:2404.03204"},{"key":"ref12","article-title":"VALLE 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2402.07383"},{"key":"ref13","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2310.00704"},{"key":"ref14","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2304.09116"},{"key":"ref15","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv:2403.03100"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref17","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICML","author":"Song"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref20","article-title":"Flow matching for generative modeling","volume-title":"Proc. ICLR","author":"Lipman"},{"key":"ref21","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389766"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","article-title":"Seed-TTS: A Family of HighQuality Versatile Speech Generation Models","author":"Anastassiou","year":"2024","journal-title":"arXiv preprint arXiv:2406.02430"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","article-title":"Neural ordinary differential equations","volume-title":"in Proc. NeurIPS","volume":"31","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref29","article-title":"The carnegie mellon university pronouncing dictionary","author":"Lenzo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447120"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref32","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. ICLR","author":"Lee"},{"key":"ref33","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv:2207.12598"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1336"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389666"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832320.pdf?arnumber=10832320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:18Z","timestamp":1737398358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832320","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}