{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T11:46:46Z","timestamp":1752666406233},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095431","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling"],"prefix":"10.1109","author":[{"given":"Bac","family":"Nguyen","sequence":"first","affiliation":[{"name":"Stuttgart Laboratory 1,Sony Europe B.V., R&D Center,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabien","family":"Cardinaux","sequence":"additional","affiliation":[{"name":"Stuttgart Laboratory 1,Sony Europe B.V., R&D Center,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Uhlich","sequence":"additional","affiliation":[{"name":"Stuttgart Laboratory 1,Sony Europe B.V., R&D Center,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"article-title":"Naturalspeech: End-to-end text to speech synthesis with human-level quality","year":"2022","author":"tan","key":"ref34"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref14","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"popov","year":"2021","journal-title":"ICML"},{"article-title":"The LJ Speech dataset","year":"2017","author":"ito","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2008.11.006"},{"key":"ref11","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ICLRE"},{"key":"ref33","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"ICLRE"},{"key":"ref10","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"ICASSP"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using Kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref19","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref18","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"ICLRE"},{"key":"ref24","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref23","first-page":"7700","article-title":"EfficientTTS: An efficient and high-quality text-to-speech architecture","author":"miao","year":"2021","journal-title":"ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref25","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref28","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref27","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"2016","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref8","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref9","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref4","first-page":"2966","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"ar?k","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"ar?k","year":"2017","journal-title":"ICML"},{"key":"ref6","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ICASSP Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095431.pdf?arnumber=10095431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T18:59:22Z","timestamp":1701111562000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095431\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095431","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}