@article{improvingjointspeechtextrepresentations,
  title = {Improving Joint Speech-Text Representations Without Alignment},
  author = {Cal Peyser and Zhong Meng and Ke Hu and Rohit Prabhavalkar and Andrew Rosenberg and Tara N. Sainath and Michael Picheny and Kyunghyun Cho},
  year = {2023},
  eprint = {2308.06125},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2308.06125v1},
}