@inproceedings{arkhangorodsky-etal-2020-didi,
    title = "{D}i{D}i Labs' End-to-end System for the {IWSLT} 2020 Offline Speech {T}ranslation{T}ask",
    author = "Arkhangorodsky, Arkady  and
      Huang, Yiqi  and
      Axelrod, Amittai",
    editor = {Federico, Marcello  and
      Waibel, Alex  and
      Knight, Kevin  and
      Nakamura, Satoshi  and
      Ney, Hermann  and
      Niehues, Jan  and
      St{\"u}ker, Sebastian  and
      Wu, Dekai  and
      Mariani, Joseph  and
      Yvon, Francois},
    booktitle = "Proceedings of the 17th International Conference on Spoken Language Translation",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.iwslt-1.6/",
    doi = "10.18653/v1/2020.iwslt-1.6",
    pages = "69--72",
    abstract = "This paper describes the system that was submitted by DiDi Labs to the offline speech translation task for IWSLT 2020. We trained an end-to-end system that translates audio from English TED talks to German text, without producing intermediate English text. We use the S-Transformer architecture and train using the MuSTC dataset. We also describe several additional experiments that were attempted, but did not yield improved results."
}