Synthesising Audio Adversarial Examples for Automatic Speech Recognition.

Xinghua Qu Pengfei Wei Mingyong Gao Zhu Sun Yew Soon Ong Zejun Ma

Published in: KDD (2022)

Keyphrases

automatic speech recognition
broadcast news
speech recognition
speech signal
acoustic features
hidden markov models
conversational speech
spoken words
speaker identification
speech retrieval
word error rate
spontaneous speech
noisy environments
multimedia
word recognition
recognition errors
computer vision