@inproceedings{sun-etal-2021-new,
    title = "A New View of Multi-modal Language Analysis: Audio and Video Features as Text {\textquotedblleft}Styles{\textquotedblright}",
    author = "Sun, Zhongkai  and
      Sarma, Prathusha K  and
      Liang, Yingyu  and
      Sethares, William",
    editor = "Merlo, Paola  and
      Tiedemann, Jorg  and
      Tsarfaty, Reut",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-main.167/",
    doi = "10.18653/v1/2021.eacl-main.167",
    pages = "1956--1965"
}