{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:38:44Z","timestamp":1730198324122,"version":"3.28.0"},"reference-count":34,"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\/apsipaasc47483.2019.9023283","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"165-169","source":"Crossref","is-referenced-by-count":6,"title":["A Prosodic Mandarin Text-to-Speech System Based on Tacotron"],"prefix":"10.1109","author":[{"given":"Chuxiong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Sheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haibing","family":"Zhong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"year":"0","key":"ref33"},{"year":"0","key":"ref32"},{"year":"0","key":"ref31"},{"year":"0","key":"ref30"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-011-0043-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref16","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume":"abs 1710 7654","author":"ping","year":"2017","journal-title":"CoRR"},{"journal-title":"Char2Wav End-to-end speech synthesis","year":"2017","author":"sotelo","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701851"},{"key":"ref19","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"2016 ISCA Speech Synthesis Workshop (SSW)"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref27","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref6","first-page":"1964","article-title":"Tts synthesis with bidirectional lstm based recurrent neural networks","author":"fan","year":"2014","journal-title":"2014 Annual Conference of the International Speech Communication Association (INTERSPEECH)"},{"journal-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","year":"2014","author":"chung","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472657"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref2","first-page":"601","author":"black","year":"1997","journal-title":"Automatically Clustering Similar Units for Unit Selection in Speech Synthesis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref20","first-page":"2347","author":"yoshimura","year":"2002","journal-title":"Simultaneous modeling of phonetic and prosodic parameters and characteristic conversion for HMM-based text-to-speech systems"},{"journal-title":"Style tokens Unsupervised style modeling control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref22"},{"journal-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","year":"2018","author":"skerry-ryan","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1983.1164162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","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\/09023283.pdf?arnumber=9023283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:53:51Z","timestamp":1658094831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023283","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}