Improving speaker turn embedding by crossmodal transfer learning from face embedding. Le, N. & Odobez, J. In ICCV Workshop on Computer Vision for Audio-Visual Media, October, 2017.
doi  bibtex   
@InProceedings{MuMMER:Le.Odobez:2017a,
  author    = {Le, Nam and Odobez, Jean-Marc},
  booktitle = {ICCV Workshop on Computer Vision for Audio-Visual Media},
  title     = {Improving speaker turn embedding by crossmodal transfer learning from face embedding},
  year      = {2017},
  month     = oct,
  doi       = {10.1109/ICCVW.2017.58},
  file      = {Le_ICCV-CVAVM_2017.pdf:https\://publidiap.idiap.ch/downloads//papers/2017/Le_ICCV-CVAVM_2017.pdf:PDF},
  projects  = {Idiap, EUMSSI, MUMMER},
}

Downloads: 0