@article{humanespeechsynthesisthroughzeroshot,
  title = {Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation},
  author = {Rohan Chaudhury and Mihir Godbole and Aakash Garg and Jinsil Hwaryoung Seo},
  year = {2024},
  eprint = {2404.01339},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.01339v1},
}