@inproceedings{fathullah-etal-2024-audiochatllama,
    title = "{A}udio{C}hat{L}lama: Towards General-Purpose Speech Abilities for {LLM}s",
    author = "Fathullah, Yassir  and
      Wu, Chunyang  and
      Lakomkin, Egor  and
      Li, Ke  and
      Jia, Junteng  and
      Shangguan, Yuan  and
      Mahadeokar, Jay  and
      Kalinli, Ozlem  and
      Fuegen, Christian  and
      Seltzer, Mike",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.naacl-long.309/",
    doi = "10.18653/v1/2024.naacl-long.309",
    pages = "5522--5532"
}