@article{transcriptionenrichedjointembeddingsfor,
  title = {Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and Videos},
  author = {Benet Oriol and Jordi Luque and Ferran Diego and Xavier Giro-i-Nieto},
  year = {2020},
  eprint = {2006.00785},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2006.00785v1},
}