@article{improvingaudiocodecbasedzeroshottextto,
  title = {Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model},
  author = {Jinlong Xue and Yayue Deng and Yicheng Han and Yingming Gao and Ya Li},
  year = {2024},
  eprint = {2406.03706},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.03706v1},
}