@article{whisbertmultimodaltextaudiolanguage,
  title = {WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words},
  author = {Lukas Wolf and Greta Tuckute and Klemen Kotar and Eghbal Hosseini and Tamar Regev and Ethan Wilcox and Alex Warstadt},
  year = {2023},
  eprint = {2312.02931},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.02931v2},
}