On Using SpecAugment for End-to-End Speech Translation

Parnia Bahar, Albert Zeyer, Ralf Schlüter, Hermann Ney
2019 Zenodo  
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→Fr and +1.2% on IWSLT TED-talks En→De by alleviating overfitting to some extent. We also examine the
more » ... ectiveness 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.
doi:10.5281/zenodo.3525009 fatcat:xwpicnx3cjdwhmwpi7hcmnr26i