{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:09:52Z","timestamp":1776110992013,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683143","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"3617-3621","source":"Crossref","is-referenced-by-count":558,"title":["Waveglow: A Flow-based Generative Network for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Prenger","sequence":"first","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Rafael","family":"Valle","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}]}],"member":"263","reference":[{"key":"ref10","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Nice: Non-linear independent components estimation","author":"dinh","year":"2014"},{"key":"ref12","article-title":"Density estimation using real nvp","author":"dinh","year":"2016"},{"key":"ref13","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015"},{"key":"ref14","article-title":"Image transformer","author":"parmar","year":"2018"},{"key":"ref15","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref17","author":"yamamoto","year":"2018","journal-title":"Wavenet vocoder"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref19","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017"},{"key":"ref3","article-title":"Waveglow","author":"prenger","year":"2018"},{"key":"ref6","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017"},{"key":"ref5","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017"},{"key":"ref8","article-title":"Fast spectrogram inversion using multi-head convolutional neural networks","author":"arik","year":"2018"},{"key":"ref7","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2018"},{"key":"ref2","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016"},{"key":"ref1","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"kingma","year":"2018"},{"key":"ref9","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"den oord","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref20","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"2017"},{"key":"ref22","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683143.pdf?arnumber=8683143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:29:06Z","timestamp":1756153746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683143\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683143","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}