1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial speech signals. Spec

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

00:14:18

2 views

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial speech signals. Spec

Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement

00:14:01

0 views

Recent studies have highlighted adversarial examples as ubiquitous threats to the deep neural network (DNN) based speech recognition systems. In this work, we present a U-Net based attention model, U-Net$_{At}$, to enhance adversarial speech signals. Spec