Conference paper Open Access
Bahar, Parnia; Zeyer, Albert; Schlüter, Ralf; Ney, Hermann
{ "description": "<p>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.</p>", "license": "https://creativecommons.org/licenses/by/4.0/legalcode", "creator": [ { "affiliation": "Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany & AppTek, 52062 Aachen, Germany", "@type": "Person", "name": "Bahar, Parnia" }, { "affiliation": "Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany & AppTek, 52062 Aachen, Germany", "@type": "Person", "name": "Zeyer, Albert" }, { "affiliation": "Human Language Technology and Pattern Recognition Group, Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany", "@type": "Person", "name": "Schl\u00fcter, Ralf" }, { "affiliation": "Human Language Technology and Pattern Recognition Group Computer Science Department, RWTH Aachen University, 52062 Aachen, Germany & AppTek, 52062 Aachen, Germany", "@type": "Person", "name": "Ney, Hermann" } ], "headline": "On Using SpecAugment for End-to-End Speech Translation", "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", "datePublished": "2019-11-02", "url": "https://zenodo.org/record/3525010", "@context": "https://schema.org/", "identifier": "https://doi.org/10.5281/zenodo.3525010", "@id": "https://doi.org/10.5281/zenodo.3525010", "@type": "ScholarlyArticle", "name": "On Using SpecAugment for End-to-End Speech Translation" }
All versions | This version | |
---|---|---|
Views | 109 | 107 |
Downloads | 83 | 83 |
Data volume | 63.8 MB | 63.8 MB |
Unique views | 95 | 93 |
Unique downloads | 71 | 71 |