# Improving the Robustness of Speech Translation

arXiv: https://arxiv.org/abs/1811.00728 · HTML: https://mlsanity.com/paper/1811.00728/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2018.

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

- [An Approach to Improve Robustness of NLP Systems against ASR Errors](https://mlsanity.com/paper/2103.13610/) (2021)
- [Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning](https://mlsanity.com/paper/2104.10357/) (2021)
- [NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation](https://mlsanity.com/paper/2111.05196/) (2021)
- [Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition](https://mlsanity.com/paper/2401.10447/) (2024)
- [Improving Speech Recognition Error Prediction for Modern and Off-the-shelf Speech Recognizers](https://mlsanity.com/paper/2408.11258/) (2024)
- [Exploring the Usage of Chinese Pinyin in Pretraining](https://mlsanity.com/paper/2310.04960/) (2023)
- [Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text](https://mlsanity.com/paper/2602.11933/) (2026)

## Abstract (arXiv)

Although neural machine translation (NMT) has achieved impressive progress recently, it is usually trained on the clean parallel data set and hence cannot work well when the input sentence is the production of the automatic speech recognition (ASR) system due to the enormous errors in the source. To solve this problem, we propose a simple but effective method to improve the robustness of NMT in the case of speech translation. We simulate the noise existing in the realistic output of the ASR system and inject them into the clean parallel data so that NMT can work under similar word distributions during training and testing. Besides, we also incorporate the Chinese Pinyin feature which is easy to get in speech translation to further improve the translation performance. Experiment results show that our method has a more stable performance and outperforms the baseline by an average of 3.12 BLEU on multiple noisy test sets, even while achieves a generalization improvement on the WMT'17 Chinese-English test set.