{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:54:58Z","timestamp":1780444498738,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053436","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6699-6703","source":"Crossref","is-referenced-by-count":47,"title":["Generating Diverse and Natural Text-to-Speech Samples Using a Quantized Fine-Grained VAE and Autoregressive Prosody Prior"],"prefix":"10.1109","author":[{"given":"Guangzhi","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/01690961003589492"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref12","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"battenberg","year":"2019","journal-title":"arXiv 1906 03402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref14","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref15","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Variational recurrent auto-encoders","author":"fabius","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref17","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref28","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1811 00707"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"Deep voice 3: 2000speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref6","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref5","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"5206","article-title":"LibriSpeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref8","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref7","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":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","article-title":"A generative adversarial network for style modeling in a text-to-speech system","author":"ma","year":"2019","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref1","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref22","article-title":"Reducing F0 frame error of F0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend","author":"chu","year":"2009","journal-title":"Proc ICASSP"},{"key":"ref21","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053436.pdf?arnumber=9053436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:29:39Z","timestamp":1696015779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053436","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}