{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:44:09Z","timestamp":1776887049101,"version":"3.51.2"},"reference-count":22,"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"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","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\/icassp43922.2022.9747837","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7917-7921","source":"Crossref","is-referenced-by-count":19,"title":["Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-Based Multi-Modal Context Modeling"],"prefix":"10.1109","author":[{"given":"Jingbei","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}]},{"given":"Yi","family":"Meng","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}]},{"given":"Chenyi","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University,Shenzhen,China"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management,Hong Kong SAR, China"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent,Shenzhen,China"}]},{"given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"AI Lab, Tencent,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","article-title":"Quasi-recurrent neural networks","author":"bradbury","year":"2016","journal-title":"arXiv preprint arXiv 1611 01576"},{"key":"ref13","first-page":"5998","article-title":"Attention is All you Need","author":"vaswani","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref14","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":"ref15","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":"ref16","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-412"},{"key":"ref19","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"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":"10.1007\/s12559-015-9326-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"arXiv 1703 10135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"ref22","first-page":"8024","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","author":"paszke","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","author":"ito","year":"2017","journal-title":"The LJ speech dataset"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09747837.pdf?arnumber=9747837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:18Z","timestamp":1660594278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747837\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747837","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}