{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:23:13Z","timestamp":1761920593888,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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.2019.8682528","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7060-7064","source":"Crossref","is-referenced-by-count":5,"title":["Quasi-fully Convolutional Neural Network with Variational Inference for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Mu","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Deyi","family":"Tuo","sequence":"additional","affiliation":[]},{"given":"Guangzhi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"2016","author":"doersch","article-title":"Tutorial on variational autoencoders","key":"ref10"},{"year":"2016","author":"den oord","journal-title":"WaveNet A Generative Model for Raw Audio","key":"ref11"},{"key":"ref12","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"den oord","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref13","article-title":"Quasi-Recurrent Neural Networks","author":"bradbury","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref14","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proceedings of the Neural Information Processing Systems (NIPS)"},{"key":"ref15","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"year":"2014","author":"kingma","article-title":"Adam: A method for stochastic optimization","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ISCSLP.2018.8706637"},{"key":"ref19","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2013.6639215"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proceedings of Interspeech"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2015.7178816"},{"year":"2018","author":"bai","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","first-page":"294","article-title":"The hmm-based speech synthesis system (hts) version 2.0","author":"zen","year":"2007","journal-title":"SSW Citeseer"},{"key":"ref1","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":"ref9","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"Proceedings of the Neural Information Processing Systems (NIPS)"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","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\/08682528.pdf?arnumber=8682528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:13Z","timestamp":1657854673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682528","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}