@article{whydospeechlanguagemodelsfailto,
  title = {Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective},
  author = {Hankun Wang and Haoran Wang and Yiwei Guo and Zhihan Li and Chenpeng Du and Xie Chen and Kai Yu},
  year = {2024},
  eprint = {2412.17048},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.17048v1},
}