@article{facetronmultispeakerfacetospeechmodel,
  title = {Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations},
  author = {Se-Yun Um and Jihyun Kim and Jihyun Lee and Hong-Goo Kang},
  year = {2021},
  eprint = {2107.12003},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2107.12003v3},
}