Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-Based Multi-Modal Context Modeling

Jingbei Li, Yi Meng, Chenyi Li, Zhiyong Wu 0001, Helen Meng, Chao Weng, Dan Su 0002. Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-Based Multi-Modal Context Modeling. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022. pages 7917-7921, IEEE, 2022. [doi]

@inproceedings{LiMLWMWS22,
  title = {Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-Based Multi-Modal Context Modeling},
  author = {Jingbei Li and Yi Meng and Chenyi Li and Zhiyong Wu 0001 and Helen Meng and Chao Weng and Dan Su 0002},
  year = {2022},
  doi = {10.1109/ICASSP43922.2022.9747837},
  url = {https://doi.org/10.1109/ICASSP43922.2022.9747837},
  researchr = {https://researchr.org/publication/LiMLWMWS22},
  cites = {0},
  citedby = {0},
  pages = {7917-7921},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022},
  publisher = {IEEE},
  isbn = {978-1-6654-0540-9},
}