Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer

arXiv:2405.09470v1 Announce Type: cross
Abstract: In light of the widespread application of Automatic Speech Recognition (ASR) systems, their security concerns have received much more attention than ever before, primarily due to the susceptibility of Deep Neural Networks. Previous studies have illustrated that surreptitiously crafting adversarial perturbations enables the manipulation of speech recognition systems, resulting in the production of malicious commands. These attack methods mostly require adding noise perturbations under $\ell_p$ norm constraints, inevitably leaving behind artifacts of manual modifications. Recent …

adversarial application arxiv asr attention audio automatic cs.cr cs.lg cs.sd eess.as networks neural networks recognition robustness security security concerns speech speech recognition studies systems transfer