{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T22:39:05Z","timestamp":1730241545398,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,2,6]],"date-time":"2022-02-06T00:00:00Z","timestamp":1644105600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,6]],"date-time":"2022-02-06T00:00:00Z","timestamp":1644105600000},"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":[[2022,2,6]]},"DOI":"10.1109\/iceic54506.2022.9748515","type":"proceedings-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T17:19:21Z","timestamp":1649697561000},"page":"1-4","source":"Crossref","is-referenced-by-count":1,"title":["Effective Data Augmentation Methods for Neural Text-to-Speech Systems"],"prefix":"10.1109","author":[{"given":"Suhyeon","family":"Oh","sequence":"first","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}]},{"given":"Ohsung","family":"Kwon","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}]},{"given":"Min-Jae","family":"Hwang","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}]},{"given":"Jae-Min","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}]},{"given":"Eunwoo","family":"Song","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2116"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383549"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-976"},{"key":"ref16","first-page":"79627966","article-title":"Statistical parametric speech synthesis using deep neural networks","volume":"2013","author":"zen","year":"0","journal-title":"Proc ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref18","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"2010","author":"glorot","year":"0","journal-title":"Proc AISTATS"},{"key":"ref19","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"0","journal-title":"Proc ICLR"},{"key":"ref4","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"0","journal-title":"CoRR abs\/1609 03499"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref6","first-page":"810","article-title":"LP-WaveNet: Linear prediction-based WaveNet speech synthesis","volume":"2020","author":"hwang","year":"0","journal-title":"Proc APSIPA"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902701"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414408"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1437"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","author":"odena","year":"2016","journal-title":"Distillation"},{"journal-title":"On the variance of the adaptive learning rate and beyond","year":"0","author":"liu","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref24","first-page":"1459","article-title":"OpenSMILE - The Munich versatile and fast open-source audio feature extractor","volume":"2010","author":"eyben","year":"0","journal-title":"Proc ACM"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"}],"event":{"name":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","start":{"date-parts":[[2022,2,6]]},"location":"Jeju, Korea, Republic of","end":{"date-parts":[[2022,2,9]]}},"container-title":["2022 International Conference on Electronics, Information, and Communication (ICEIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9748174\/9748152\/09748515.pdf?arnumber=9748515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,14]],"date-time":"2022-06-14T16:44:05Z","timestamp":1655225045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9748515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iceic54506.2022.9748515","relation":{},"subject":[],"published":{"date-parts":[[2022,2,6]]}}}