SELF-SUPERVISED AUGMENTATION DEFENSE MODEL AGAINST ADVERSARIAL ATTACKS FOR SPEECH EMOTION RECOGNITION
Published in IEEE ICASSP, 2021
Recommended citation: Under Review." IEEE ICASSP2022.. 1(1).
In this paper, we proposed a self-supervised augmentation defense (SSAD) model that can defend against different adversarial attacks without knowing the types beforehand.
Recommended citation: Under Review. “SELF-SUPERVISED AUGMENTATION DEFENSE MODEL AGAINST ADVERSARIAL ATTACKS FOR SPEECH EMOTION RECOGNITION” IEEE ICASSP2022. 1(1).