Conference paper Open Access

On Using SpecAugment for End-to-End Speech Translation

Bahar, Parnia; Zeyer, Albert; Schlüter, Ralf; Ney, Hermann

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 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.

Files (769.0 kB)
Name Size
769.0 kB Download
All versions This version
Views 147145
Downloads 105105
Data volume 80.7 MB80.7 MB
Unique views 129127
Unique downloads 9393


Cite as