@inproceedings{ma-etal-2020-simulmt,
    title = "{S}imul{MT} to {S}imul{ST}: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation",
    author = "Ma, Xutai  and
      Pino, Juan  and
      Koehn, Philipp",
    editor = "Wong, Kam-Fai  and
      Knight, Kevin  and
      Wu, Hua",
    booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
    month = dec,
    year = "2020",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.aacl-main.58/",
    doi = "10.18653/v1/2020.aacl-main.58",
    pages = "582--587",
    abstract = "We investigate how to adapt simultaneous text translation methods such as wait-$k$ and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module. A detailed analysis is provided on the latency-quality trade-offs of combining fixed and flexible pre-decision with fixed and flexible policies. We also design a novel computation-aware latency metric, adapted from Average Lagging."
}