Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _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 |