# Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training

arXiv: https://arxiv.org/abs/1909.11430 · HTML: https://mlsanity.com/paper/1909.11430/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 7 of 7)

- [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)
- [Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning](https://mlsanity.com/paper/2409.19510/) (2024)
- [Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages](https://mlsanity.com/paper/2411.04699/) (2024)
- [When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation](https://mlsanity.com/paper/2502.00377/) (2025)
- [Improving speech translation by fusing speech and text](https://mlsanity.com/paper/2305.14042/) (2023)
- [MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages](https://mlsanity.com/paper/2512.01512/) (2025)

## Abstract (arXiv)

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel corpus composed of clean text and will perform poorly on text with recognition noise, a gap well known in speech translation community. In this paper, we propose a training architecture which aims at making a neural machine translation model more robust against speech recognition errors. Our approach addresses the encoder and the decoder simultaneously using adversarial learning and data augmentation, respectively. Experimental results on IWSLT2018 speech translation task show that our approach can bridge the gap between the ASR output and the MT input, outperforms the baseline by up to 2.83 BLEU on noisy ASR output, while maintaining close performance on clean text.