{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:47Z","timestamp":1730199347896,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688074","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"634-641","source":"Crossref","is-referenced-by-count":4,"title":["On-The-Fly Data Augmentation for Text-to-Speech Style Transfer"],"prefix":"10.1109","author":[{"given":"Raymond","family":"Chung","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering"}]},{"given":"Brian","family":"Mak","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"hinton","year":"2012","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2019-2250"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/SLT.2018.8639672"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2020-2793"},{"year":"2017","author":"ito","journal-title":"The LJ speech dataset","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP39728.2021.9413466"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2020-1251"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref18","first-page":"498","article-title":"Montreal Forced Aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"0","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.18653\/v1\/N19-2026"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP.2019.8683865"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2020-1361"},{"key":"ref5","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/SLT48900.2021.9383454"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref2","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Multi-reference neural TTS stylization with adversarial cycle consistency","author":"whitehill","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"LibriTTS: A corpus derived from librispeech for text-to-speech","author":"heiga","year":"2019","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688074.pdf?arnumber=9688074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:10Z","timestamp":1652733730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688074\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688074","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}