@inproceedings{bahar-etal-2019-using,
    title = "On Using {S}pec{A}ugment for End-to-End Speech Translation",
    author = {Bahar, Parnia  and
      Zeyer, Albert  and
      Schl{\"u}ter, Ralf  and
      Ney, Hermann},
    editor = {Niehues, Jan  and
      Cattoni, Rolando  and
      St{\"u}ker, Sebastian  and
      Negri, Matteo  and
      Turchi, Marco  and
      Ha, Thanh-Le  and
      Salesky, Elizabeth  and
      Sanabria, Ramon  and
      Barrault, Loic  and
      Specia, Lucia  and
      Federico, Marcello},
    booktitle = "Proceedings of the 16th International Conference on Spoken Language Translation",
    month = nov # " 2-3",
    year = "2019",
    address = "Hong Kong",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2019.iwslt-1.22/",
    abstract = "This work investigates a simple data augmentation technique, SpecAugment, for end-to-end speech translation. SpecAugment is a low-cost implementation method applied directly to the audio input features and it consists of masking blocks of frequency channels, and/or time steps. We apply SpecAugment on end-to-end speech translation tasks and achieve up to +2.2{\%} BLEU on LibriSpeech Audiobooks En{\textrightarrow}Fr and +1.2{\%} on IWSLT TED-talks En{\textrightarrow}De by alleviating overfitting to some extent. We also examine the effectiveness of the method in a variety of data scenarios and show that the method also leads to significant improvements in various data conditions irrespective of the amount of training data."
}