{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:29Z","timestamp":1740100649804,"version":"3.37.3"},"reference-count":24,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp43922.2022.9747438","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7922-7926","source":"Crossref","is-referenced-by-count":6,"title":["Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Shun","family":"Lei","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyin","family":"Kang","sequence":"additional","affiliation":[{"name":"Huya Inc.,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"ref12","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021","journal-title":"arXiv preprint arXiv 2106 13112"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3074757"},{"key":"ref15","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NIPS 2014 Workshop on Deep Learning December 2014"},{"key":"ref16","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3439726"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"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"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref7","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref2","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv preprint arXiv 1810 04805"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"17022","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":"ref23","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"}],"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\/09747438.pdf?arnumber=9747438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:14:00Z","timestamp":1661199240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747438","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}