Reassessing Noise Augmentation Methods in the Context of Adversarial Speech
In this study, we investigate if noise-augmented training can concurrently improve adversarial robustness in automatic speech recognition (ASR) systems. We conduct a comparative analysis of the adversarial robustness of four different state-of-the-art ASR architectures, where each of the ASR architectures is trained under three different augmentation conditions: one subject to background noise, speed variations, and reverberations, another subject to speed variations only, and a third without any form of data augmentation. The results demonstrate that noise augmentation not only improves model performance on noisy speech but also the model's robustness to adversarial attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Data Augmentationspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding Overfitting in Adversarial Training via Kernel Regression
Adversarial training and data augmentation with noise are widely adopted techniques to enhance the performance of neural networks. This paper investigates adversarial training and data augmentation with noise in the cont…
Data AugmentationregressionConsistency Training with Virtual Adversarial Discrete Perturbation
Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that t…
Semi-Supervised Text ClassificationText ClassificationWord Embedding Perturbation for Sentence Classification
In this technique report, we aim to mitigate the overfitting problem of natural language by applying data augmentation methods. Specifically, we attempt several types of noise to perturb the input word embedding, such as…
ClassificationData AugmentationGeneral ClassificationSentence+1Adversarial Robustness for Deep Learning-based Wildfire Prediction Models
Smoke detection using Deep Neural Networks (DNNs) is an effective approach for early wildfire detection. However, because smoke is temporally and spatially anomalous, there are limitations in collecting sufficient traini…
Adversarial AttackAdversarial RobustnessData AugmentationDeep LearningPathology-Aware Generative Adversarial Networks for Medical Image Augmentation
Convolutional Neural Networks (CNNs) can play a key role in Medical Image Analysis under large-scale annotated datasets. However, preparing such massive dataset is demanding. In this context, Generative Adversarial Netwo…
Data AugmentationImage AugmentationMedical Image Analysis