Phantom in the opera: adversarial music attack for robot dialogue system

Phantom in the opera: adversarial music attack for robot dialogue system

This study explores the vulnerability of robot dialogue systems' automatic speech recognition (ASR) module to adversarial music attacks. Specifically, we explore music as a natural camouflage for such attacks. We propose a novel method to hide ghost speech commands in a music clip by slightly p...

Full description

Bibliographic Details
Main Authors: Sheng Li, Jiyi Li, Yang Cao
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-02-01
Series:Frontiers in Computer Science
Subjects:
an industry-popular ASR model
namely the time-delay neural network (TDNN)
widely used for speech and speaker adversarial music attack
deep neural network
robot dialogue system
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/full

Internet

https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/full

Similar Items