Training Augmentation With Adversarial Examples For Robust Speech Recognition

Abstract

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.

Stats

• citations32
• S2 citations—
• github stars0
• HF likes0
• heat score11.39
• arxiv keysun2018training

Related papers

• Audio Adversarial Examples For Robust Hybrid Ctc/attention Speech Recognition (2020)3.58
• Boosting Noise Robustness Of Acoustic Model Via Deep Adversarial Training (2018)9.23
• Augmentation Adversarial Training For Self-supervised Speaker Recognition (2020)0.00
• Data Augmentation Methods For End-to-end Speech Recognition On Distant-talk Scenarios (2021)6.34
• Personalized Adversarial Data Augmentation For Dysarthric And Elderly Speech Recognition (2022)11.49
• Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness (2018)0.00
• Improving Sequence-to-sequence Speech Recognition Training With On-the-fly Data Augmentation (2019)0.00
• Unsupervised Domain Adaptation For Robust Speech Recognition Via Variational Autoencoder-based Data Augmentation (2017)14.23