@article{facestylespeechimprovedfacetovoice,
  title = {Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping},
  author = {Minki Kang and Wooseok Han and Eunho Yang},
  year = {2023},
  eprint = {2311.05844},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.05844v2},
}