@inproceedings{sun2020generating,
  title={Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and autoregressive prosody prior},
  author={Sun, Guangzhi and Zhang, Yu and Weiss, Ron J and Cao, Yuan and Zen, Heiga and Rosenberg, Andrew and Ramabhadran, Bhuvana and Wu, Yonghui},
  booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={6699--6703},
  year={2020},
  organization={IEEE}
}