Facetron: A Multi-Speaker Face-to-Speech Model Based on Cross-Modal Latent Representations

Seyun Um, Jihyun Kim, Jihyun Lee, Hong-Goo Kang. Facetron: A Multi-Speaker Face-to-Speech Model Based on Cross-Modal Latent Representations. In 31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, September 4-8, 2023. pages 281-285, IEEE, 2023. [doi]

@inproceedings{UmKLK23,
  title = {Facetron: A Multi-Speaker Face-to-Speech Model Based on Cross-Modal Latent Representations},
  author = {Seyun Um and Jihyun Kim and Jihyun Lee and Hong-Goo Kang},
  year = {2023},
  doi = {10.23919/EUSIPCO58844.2023.10290115},
  url = {https://doi.org/10.23919/EUSIPCO58844.2023.10290115},
  researchr = {https://researchr.org/publication/UmKLK23},
  cites = {0},
  citedby = {0},
  pages = {281-285},
  booktitle = {31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, September 4-8, 2023},
  publisher = {IEEE},
  isbn = {978-9-4645-9360-0},
}