一个令人惊讶的密度虚幻的自然语言
A Surprising Density of Illusionable Natural Speech
摘要：
最近对对抗性例子的研究表明，大多数自然输入都可以被干扰，甚至可以欺骗最先进的机器学习系统。但这也会发生在人类身上吗？在这项工作中，我们调查：语音的自然实例中的哪一部分可以变成“错觉”，要么改变人类的感知或导致不同的人有显着不同的看法？我们首先考虑McGurk效应，通过这种现象，在音频通道中添加精心选择的视频剪辑会影响观众对所说内容的感知（McGurk和MacDonald，1976）。我们得到的经验估计，一个显着的部分发生在自然语音的单词和句子有一定的易感性，这种效果。我们还学习了预测麦格克错觉的模型。最后，我们证明了Yanny或Laurel听觉错觉（Pressnitzer等人，2018年）并不是一个孤立的事件，它产生了几个非常不同的新实例。我们相信，令人惊讶的密度的幻觉自然语音值得进一步调查，从安全和认知科学的角度。补充视频请访问：https://www.youtube.com/playlist?列表= PLaX 7 t1 K-e_fF 2 iaenoKznCatm 0 RC 37 B_k。
英文摘要：
Recent work on adversarial examples has demonstrated that most natural inputs can be perturbed to fool even state-of-the-art machine learning systems. But does this happen for humans as well? In this work, we investigate: what fraction of natural instances of speech can be turned into "illusions" which either alter humans' perception or result in different people having significantly different perceptions? We first consider the McGurk effect, the phenomenon by which adding a carefully chosen video clip to the audio channel affects the viewer's perception of what is said (McGurk and MacDonald, 1976). We obtain empirical estimates that a significant fraction of both words and sentences occurring in natural speech have some susceptibility to this effect. We also learn models for predicting McGurk illusionability. Finally we demonstrate that the Yanny or Laurel auditory illusion (Pressnitzer et al., 2018) is not an isolated occurrence by generating several very different new instances. We believe that the surprising density of illusionable natural speech warrants further investigation, from the perspectives of both security and cognitive science. Supplementary videos are available at: https://www.youtube.com/playlist?list=PLaX7t1K-e_fF2iaenoKznCatm0RC37B_k.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
