Saved in:
Bibliographic Details
Main Authors: Pizzi, Karla, Pizarro, Matías, Fischer, Asja
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.01813
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918190938849280
author Pizzi, Karla
Pizarro, Matías
Fischer, Asja
author_facet Pizzi, Karla
Pizarro, Matías
Fischer, Asja
contents In this study, we investigate whether 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 ASR architectures, each trained under three different augmentation conditions: (1) background noise, speed variations, and reverberations; (2) speed variations only; (3) no data augmentation. We then evaluate the robustness of all resulting models against attacks with white-box or black-box adversarial examples. Our results demonstrate that noise augmentation not only enhances model performance on noisy speech but also improves the model's robustness to adversarial attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_01813
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
Pizzi, Karla
Pizarro, Matías
Fischer, Asja
Audio and Speech Processing
Machine Learning
Sound
In this study, we investigate whether 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 ASR architectures, each trained under three different augmentation conditions: (1) background noise, speed variations, and reverberations; (2) speed variations only; (3) no data augmentation. We then evaluate the robustness of all resulting models against attacks with white-box or black-box adversarial examples. Our results demonstrate that noise augmentation not only enhances model performance on noisy speech but also improves the model's robustness to adversarial attacks.
title Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2409.01813