@article{showandspeakdirectlysynthesizespoken,
  title = {Show and Speak: Directly Synthesize Spoken Description of Images},
  author = {Xinsheng Wang and Siyuan Feng and Jihua Zhu and Mark Hasegawa-Johnson and Odette Scharenborg},
  year = {2020},
  eprint = {2010.12267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2010.12267v2},
}