@inproceedings{xu-etal-2021-stacked, title = "Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders", author = "Xu, Chen and Hu, Bojie and Li, Yanyang and Zhang, Yuhao and Huang, Shen and Ju, Qi and Xiao, Tong and Zhu, Jingbo", editor = "Zong, Chengqing and Xia, Fei and Li, Wenjie and Navigli, Roberto", booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.acl-long.204/", doi = "10.18653/v1/2021.acl-long.204", pages = "2619--2630" }