@article{msrstrainingmultimodalspeechrecognition,
  title = {MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization},
  author = {Adriana Fernandez-Lopez and Honglie Chen and Pingchuan Ma and Lu Yin and Qiao Xiao and Stavros Petridis and Shiwei Liu and Maja Pantic},
  year = {2024},
  eprint = {2406.17614},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.17614v1},
}