# Training Augmentation with Adversarial Examples for Robust Speech Recognition

arXiv: https://arxiv.org/abs/1806.02782 · HTML: https://mlsanity.com/paper/1806.02782/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2018.

## Built on by (most cited first, 11 of 11)

- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Sequential Randomized Smoothing for Adversarially Robust Speech Recognition](https://mlsanity.com/paper/2112.03000/) (2021)
- [Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation](https://mlsanity.com/paper/2206.01909/) (2022)
- [SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2103.10651/) (2021)
- [AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction](https://mlsanity.com/paper/2407.18324/) (2024)
- [Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey](https://mlsanity.com/paper/2202.10594/) (2022)
- [Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition](https://mlsanity.com/paper/2202.08532/) (2022)
- [Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems](https://mlsanity.com/paper/2203.15283/) (2022)
- [MIXPGD: Hybrid Adversarial Training for Speech Recognition Systems](https://mlsanity.com/paper/2303.05758/) (2023)
- [Trustworthy Sensor Fusion against Inaudible Command Attacks in Advanced Driver-Assistance System](https://mlsanity.com/paper/2306.05358/) (2023)
- [Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training](https://mlsanity.com/paper/2307.12498/) (2023)

## Abstract (arXiv)

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmentation based on data transformations, the examples are dynamically generated based on current acoustic model parameters. We assess the impact of adversarial data augmentation in experiments on the Aurora-4 and CHiME-4 single-channel tasks, showing improved robustness against noise and channel variation. Further improvement is obtained when combining adversarial examples with teacher/student training, leading to a 23% relative word error rate reduction on Aurora-4.