@article{tmttrimodaltranslationbetweenspeech,
  title = {TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages},
  author = {Minsu Kim and Jee-weon Jung and Hyeongseop Rha and Soumi Maiti and Siddhant Arora and Xuankai Chang and Shinji Watanabe and Yong Man Ro},
  year = {2024},
  eprint = {2402.16021},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.16021v2},
}