@inproceedings{srinivasan-etal-2020-fine,
    title = "Fine-Grained Grounding for Multimodal Speech Recognition",
    author = "Srinivasan, Tejas  and
      Sanabria, Ramon  and
      Metze, Florian  and
      Elliott, Desmond",
    editor = "Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.findings-emnlp.242/",
    doi = "10.18653/v1/2020.findings-emnlp.242",
    pages = "2667--2677"
}