@inproceedings{li-etal-2021-ctal,
    title = "{CTAL}: Pre-training Cross-modal Transformer for Audio-and-Language Representations",
    author = "Li, Hang  and
      Ding, Wenbiao  and
      Kang, Yu  and
      Liu, Tianqiao  and
      Wu, Zhongqin  and
      Liu, Zitao",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.emnlp-main.323/",
    doi = "10.18653/v1/2021.emnlp-main.323",
    pages = "3966--3977"
}