@inproceedings{lee-etal-2025-multimodal,
    title = "How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations",
    author = "Lee, Hyunji  and
      Liu, Danni  and
      Sinhamahapatra, Supriti  and
      Niehues, Jan",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-short.51/",
    pages = "600--610",
    ISBN = "979-8-89176-190-2"
}