{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:26:44Z","timestamp":1779208004651,"version":"3.51.4"},"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.2019.8683862","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6940-6944","source":"Crossref","is-referenced-by-count":59,"title":["Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yu-An","family":"Chung","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ning","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.J.","family":"Skerry-Ryan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Zoneout: Regularizing RNNs by randomly preserving hidden activations","author":"krueger","year":"2017","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref12","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref14","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref17","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"ICLR Workshop"},{"key":"ref18","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref4","article-title":"Unsupervised learning for text-to-speech synthesis","author":"watts","year":"2013","journal-title":"Ph D thesis"},{"key":"ref3","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"ICLRE"},{"key":"ref6","article-title":"Sentence-level control vectors for deep neural network speech synthesis","author":"watts","year":"2015","journal-title":"InterSpeech"},{"key":"ref5","article-title":"Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis","author":"lu","year":"2013","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref8","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178898"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","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":"InterSpeech"},{"key":"ref9","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","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\/08683862.pdf?arnumber=8683862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:11:49Z","timestamp":1657854709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683862","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}