{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:39:57Z","timestamp":1774589997855,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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":[[2021,10]]},"DOI":"10.1109\/mapr53640.2021.9585267","type":"proceedings-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T19:28:04Z","timestamp":1635535684000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["FastTacotron: A Fast, Robust and Controllable Method for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Dinh Viet","family":"Sang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lam Xuan","family":"Thu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Jose Sotelo, Alexandre de Brébisson, Yoshua Bengio, and Aaron Courville. Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref13","article-title":"Professor forcing: A new algorithm for training recurrent networks","author":"lamb","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"},{"key":"ref15","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref18","article-title":"Parallel neural text-to-speech","author":"peng","year":"2019"},{"key":"ref19","article-title":"Forwardtacotron","author":"schaefer","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref27","first-page":"97","article-title":"Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound","volume":"17","author":"boersma","year":"1993","journal-title":"Proceedings of the Institute of Phonetic Sciences"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref8","article-title":"A generative model for raw audio","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-219","article-title":"Automatically clustering similar units for unit selection in speech synthesis","author":"black","year":"1997"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref20","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref22","article-title":"Highway networks","author":"srivastava","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref25","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","location":"Hanoi, Vietnam","start":{"date-parts":[[2021,10,15]]},"end":{"date-parts":[[2021,10,16]]}},"container-title":["2021 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9585222\/9585196\/09585267.pdf?arnumber=9585267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T23:35:38Z","timestamp":1699745738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9585267\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/mapr53640.2021.9585267","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}