BriefGPT.xyz
Oct, 2022
不止一种鲁棒性：用对抗样本欺骗Whisper
There is more than one kind of robustness: Fooling Whisper with adversarial examples
HTML
PDF
Raphael Olivier, Bhiksha Raj
TL;DR
本文研究了对抗性噪声下自动语音识别模型的鲁棒性。作者通过小幅度输入扰动，即使增加了最高45分贝的噪音，可以显著降低模型精度，甚至能够转录出所选目标句子。作者还证明了欺骗模型语言检测器可以极大地降低多语言模型的性能，强调了adversarially robust ASR的必要性。
Abstract
Whisper is a recent
automatic speech recognition
(ASR) model displaying impressive
robustness
to both out-of-distribution inputs and random noise. In this work, we show that this
→