Adversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness
This addresses robustness issues in SER systems for applications like human-computer interaction, but it is incremental as it builds on existing adversarial machine learning techniques.
The paper tackles the vulnerability of speech emotion recognition (SER) systems to adversarial attacks by proposing the first black-box adversarial attack on SER and exploring defenses like adversarial training and GANs, with experimental evaluations showing aspects useful for improving robustness.
Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of SER systems by showing the susceptibility of deep neural networks to adversarial examples as they rely only on small and imperceptible perturbations. In this study, we evaluate how adversarial examples can be used to attack SER systems and propose the first black-box adversarial attack on SER systems. We also explore potential defenses including adversarial training and generative adversarial network (GAN) to enhance robustness. Experimental evaluations suggest various interesting aspects of the effective utilization of adversarial examples useful for achieving robustness for SER systems opening up opportunities for researchers to further innovate in this space.