{"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":1774589997857,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023186","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"623-627","source":"Crossref","is-referenced-by-count":50,"title":["End-to-End Emotional Speech Synthesis Using Style Tokens and Semi-Supervised Training"],"prefix":"10.1109","author":[{"given":"Pengfei","family":"Wu","sequence":"first","affiliation":[]},{"given":"Zhenhua","family":"Ling","sequence":"additional","affiliation":[]},{"given":"Lijuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Hongchuan","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"561","article-title":"Emotional speech synthesis: a review","author":"schr\u00f6der","year":"2001","journal-title":"EUROSPEECH 2001 Scandinavia 7th European Conference on Speech Communication and Technology 2nd INTERSPEECH Event"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.9.1406"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282282"},{"key":"ref14","article-title":"Emotional end-to-end neural speech synthesizer","volume":"abs 1711 5447","author":"lee","year":"2017","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref16","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref17","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref19","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2018","journal-title":"CoRR vol abs\/1807 07281"},{"key":"ref4","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref3","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref8","first-page":"1","article-title":"The generation of affect in synthesized speech","volume":"8","author":"cahn","year":"1990","journal-title":"Journal of the American Voice I\/O Society"},{"key":"ref7","first-page":"501","article-title":"Informed blending of databases for emotional speech synthesis","author":"hofer","year":"2005","journal-title":"Interspeech 2005 - Eurospeech 9th European Conference on Speech Communication and Technology"},{"key":"ref2","article-title":"Statistical parametric speech synthesis: from hmm to lstm-rnn","author":"zen","year":"0","journal-title":"2015 lecture given at RTTH Summer School on Speech Technology"},{"key":"ref1","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":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00005-9"},{"key":"ref20","first-page":"3969","article-title":"Reducing F0 frame error of F0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend","author":"chu","year":"0","journal-title":"2009 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref21","article-title":"Fastdtw: Toward accurate dynamic time warping in linear time and space","author":"salvador","year":"0","journal-title":"KDD Workshop on Mining Temporal and Sequential Data"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Lanzhou, China","start":{"date-parts":[[2019,11,18]]},"end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023186.pdf?arnumber=9023186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T07:34:41Z","timestamp":1695886481000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023186","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}