{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T07:23:52Z","timestamp":1730273032973,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706263","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"483-487","source":"Crossref","is-referenced-by-count":5,"title":["End-to-End Mongolian Text-to-Speech System"],"prefix":"10.1109","author":[{"given":"Jingdong","family":"Li","sequence":"first","affiliation":[]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xueliang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"End to End Learning for Self-Driving Cars","year":"2016","author":"bojarski","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"journal-title":"Char2Wav End-to-end speech synthesis","year":"0","author":"sotelo","key":"ref12"},{"journal-title":"Voiceloop Voice fitting and synthesis via a phonological loop","year":"2017","author":"taigman","key":"ref13"},{"key":"ref14","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref15","first-page":"2099","article-title":"Simultaneous modeling of spectrum, pitch and duration in hmm-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"European Conference on Speech Communication and Technology Eurospeech 1999 Budapest Hungary September"},{"key":"ref16","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"ze","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","first-page":"80","article-title":"Research on hmm-based mongolian speech synthesis","volume":"41","author":"zhao","year":"0","journal-title":"Computer Science"},{"key":"ref18","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":"ref19","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"arXiv preprint arXiv 1712 05884"},{"key":"ref4","first-page":"1039","article-title":"Statistical parametric speech synthesis","volume":"51","author":"black","year":"0","journal-title":"Speech Communication"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref5","first-page":"1296","article-title":"Building of a speech corpus optimised for unit selection tts synthesis","author":"matousek","year":"2008","journal-title":"International Conference on Language Resources and Evaluation Lrec 2008 26 May - 1 June 2008 Marrakech Morocco"},{"journal-title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","year":"2016","author":"wen","key":"ref8"},{"key":"ref7","first-page":"167","author":"miao","year":"0","journal-title":"Eesen End-to-end speech recognition using deep rnn models and wfst-based decoding"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"journal-title":"Text-to-Speech Synthesis","year":"2009","author":"lin","key":"ref1"},{"key":"ref9","article-title":"End-to-end sequence labeling via bidirectional lstm-cnns-crf","author":"ma","year":"2016","journal-title":"arXiv preprint arXiv 1603 02895"},{"key":"ref20","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41644-6_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICINIS.2011.64"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-69005-6_38"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei City, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706263.pdf?arnumber=8706263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T03:40:47Z","timestamp":1598240447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706263","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}