@article{emphasisrenderingforconversationaltextto,
  title = {Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling},
  author = {Rui Liu and Zhenqi Jia and Jie Yang and Yifan Hu and Haizhou Li},
  year = {2024},
  eprint = {2410.09524},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.09524v1},
}