{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T07:53:07Z","timestamp":1776412387983,"version":"3.51.2"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3369528","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T19:10:02Z","timestamp":1708715402000},"page":"1650-1661","source":"Crossref","is-referenced-by-count":15,"title":["EfficientTTS 2: Variational End-to-End Text-to-Speech Synthesis and Voice Conversion"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1986-3035","authenticated-orcid":false,"given":"Chenfeng","family":"Miao","sequence":"first","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0155-0709","authenticated-orcid":false,"given":"Qingying","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1512-6672","authenticated-orcid":false,"given":"Minchuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8713-0667","authenticated-orcid":false,"given":"Jun","family":"Ma","sequence":"additional","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8955-8566","authenticated-orcid":false,"given":"Shaojun","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9615-4749","authenticated-orcid":false,"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology, Shanghai, China"}]}],"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":"214","article-title":"Deep voice 3: 2000-Speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref5","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref6","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref10","first-page":"1","article-title":"End-to-end adversarial text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue","year":"2021"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref12","first-page":"8067","article-title":"Glow-TTS: A. generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2020"},{"key":"ref13","article-title":"NICE: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232"},{"key":"ref15","first-page":"7700","article-title":"EfficientTTS: An efficient and high-quality text-to-speech architecture","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Miao","year":"2021"},{"key":"ref16","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref18","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref21","first-page":"1","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma","year":"2018"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","first-page":"1","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"Non-Attentive Tacotron: Robust and controllable neural tts synthesis including unsupervised duration modeling","author":"Shen","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref28","first-page":"1","article-title":"Very deep VAEs generalize autoregressive models and can outperform them on images","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Child","year":"2021"},{"key":"ref29","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-41"},{"key":"ref31","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref32","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref34","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","author":"Heo","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref36","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref38","first-page":"1","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2019"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10444060.pdf?arnumber=10444060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T02:25:19Z","timestamp":1709864719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3369528","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}