Conference paper Open Access

On Using SpecAugment for End-to-End Speech Translation

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

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Bahar, Parnia</dc:creator>
  <dc:creator>Zeyer, Albert</dc:creator>
  <dc:creator>Schlüter, Ralf</dc:creator>
  <dc:creator>Ney, Hermann</dc:creator>
  <dc:description>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.</dc:description>
  <dc:title>On Using SpecAugment for End-to-End Speech Translation</dc:title>
All versions This version
Views 109107
Downloads 8383
Data volume 63.8 MB63.8 MB
Unique views 9593
Unique downloads 7171


Cite as