{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T13:04:01Z","timestamp":1743426241009},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054681","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"source":"Crossref","is-referenced-by-count":26,"title":["Teacher-Student Training For Robust Tacotron-Based TTS"],"prefix":"10.1109","author":[{"given":"Rui","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"The imu speech synthesis entry for blizzard challenge 2019","author":"liu","year":"2019","journal-title":"Proceedings of Blizzard Challenge 2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659543"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1311"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1131"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2910637"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639507"},{"key":"ref16","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164727"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1706"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref3","first-page":"99","article-title":"Mongolian text-to-speech system based on deep neural network","author":"liu","year":"2017","journal-title":"National Conference on Man-Machine Speech Communication"},{"key":"ref27","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-35"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00379"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS 2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref24","article-title":"How (not) to train your generative model: Scheduled sampling, likelihood, adversary?","author":"husz\u00e1r","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref23","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054681.pdf?arnumber=9054681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:46Z","timestamp":1696015726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054681","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}