@misc{lee2023hierspeech,
  title={HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis},
  author={Sang-Hoon Lee and Ha-Yeong Choi and Seung-Bin Kim and Seong-Whan Lee},
  year={2023},
  eprint={2311.12454},
  archivePrefix={arXiv},
  primaryClass={cs.SD},
  url={https://arxiv.org/abs/2311.12454}
}