# On Using SpecAugment for End-to-End Speech Translation

arXiv: https://arxiv.org/abs/1911.08876 · HTML: https://mlsanity.com/paper/1911.08876/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 19 of 19)

- [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://mlsanity.com/paper/2203.10426/) (2022)
- [Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?](https://mlsanity.com/paper/2106.01045/) (2021)
- [Learning Shared Semantic Space for Speech-to-Text Translation](https://mlsanity.com/paper/2105.03095/) (2021)
- [RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer](https://mlsanity.com/paper/2106.04833/) (2021)
- [Learning When to Translate for Streaming Speech](https://mlsanity.com/paper/2109.07368/) (2021)
- [End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021](https://mlsanity.com/paper/2105.04512/) (2021)
- [Understanding and Bridging the Modality Gap for Speech Translation](https://mlsanity.com/paper/2305.08706/) (2023)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation](https://mlsanity.com/paper/2105.13782/) (2021)
- [ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2305.14838/) (2023)
- [Tuning Large language model for End-to-end Speech Translation](https://mlsanity.com/paper/2310.02050/) (2023)
- [Dealing with training and test segmentation mismatch: FBK@IWSLT2021](https://mlsanity.com/paper/2106.12607/) (2021)
- [Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation](https://mlsanity.com/paper/2210.09556/) (2022)
- [SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations](https://mlsanity.com/paper/2212.09699/) (2022)
- [Does Joint Training Really Help Cascaded Speech Translation?](https://mlsanity.com/paper/2210.13700/) (2022)
- [Improving speech translation by fusing speech and text](https://mlsanity.com/paper/2305.14042/) (2023)
- [Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021](https://mlsanity.com/paper/2106.00197/) (2021)
- [The IWSLT 2021 BUT Speech Translation Systems](https://mlsanity.com/paper/2107.06155/) (2021)
- [AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/2503.14185/) (2025)

## Abstract (arXiv)

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.