@article{unsupervisedcrossmodalaudiorepresentatio,
  title = {Unsupervised Cross-Modal Audio Representation Learning from Unstructured Multilingual Text},
  author = {Alexander Schindler and Sergiu Gordea and Peter Knees},
  year = {2020},
  eprint = {2003.12265},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.12265v1},
}