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→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.- Anthology ID:
- 2019.iwslt-1.22
- Volume:
- Proceedings of the 16th International Conference on Spoken Language Translation
- Month:
- November 2-3
- Year:
- 2019
- Address:
- Hong Kong
- Venue:
- IWSLT
- SIG:
- SIGSLT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2019.iwslt-1.22
- DOI:
- Cite (ACL):
- Parnia Bahar, Albert Zeyer, Ralf Schlüter, and Hermann Ney. 2019. On Using SpecAugment for End-to-End Speech Translation. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.
- Cite (Informal):
- On Using SpecAugment for End-to-End Speech Translation (Bahar et al., IWSLT 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2019.iwslt-1.22.pdf