@article{slamaunifiedencoderforspeechand,
  title = {SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training},
  author = {Ankur Bapna and Yu-An Chung and Nan Wu and Anmol Gulati and Ye Jia and Jonathan H. Clark and Melvin Johnson and Jason Riesa and Alexis Conneau and Yu Zhang},
  year = {2021},
  eprint = {2110.10329},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.10329v1},
}