{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T16:01:39Z","timestamp":1757779299876,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746238","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7592-7596","source":"Crossref","is-referenced-by-count":7,"title":["Discourse-Level Prosody Modeling with a Variational Autoencoder for Non-Autoregressive Expressive Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ning-Qian","family":"Wu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao-Ci","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413696"},{"article-title":"Using previous acoustic context to improve text-to-speech synthesis","year":"2020","author":"oplustil-gallegos","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1411"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414102"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-12"},{"key":"ref17","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"ming-wei chang kenton","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref19","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","volume":"29","author":"kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref3","first-page":"3171","article-title":"Fastspeech: fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems"},{"key":"ref6","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"kim","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref8","first-page":"1","article-title":"Auto-encoding variational bayes","volume":"1050","author":"kingma","year":"2014","journal-title":"Stat"},{"key":"ref7","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume":"139","author":"popov","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning ICML 2021 18-24 July 2021 Virtual Event"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref9","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/e19020047"},{"key":"ref23","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1375"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746238.pdf?arnumber=9746238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:57Z","timestamp":1661199117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746238","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}