论文标题
您能听到我的声音$ \ textit {现在} $吗？人类和机器感知的敏感比较
Can you hear me $\textit{now}$? Sensitive comparisons of human and machine perception
论文作者
论文摘要
处理感官输入的机器学习系统的兴起使人与机器感知之间的比较有所增加。但是，这种比较面临着一个挑战：尽管机器对某些刺激的感知通常可以通过直接和明确的措施来探测，但人类知识的大部分知识是潜在的，不完整的或不可用的。在这里，我们探讨了这种不对称性如何导致这种比较误解了人类和机器感知的重叠。作为一个案例研究，我们考虑了人类对\ textit {对抗性语音}的感知 - 合成音频命令被自动语音识别系统识别为有效消息，但据报道，人类听众听到了无意义的噪音。 In five experiments, we adapt task designs from the human psychophysics literature to show that even when subjects cannot freely transcribe such speech commands (the previous benchmark for human understanding), they often can demonstrate other forms of understanding, including discriminating adversarial speech from closely matched non-speech (Experiments 1--2), finishing common phrases begun in adversarial speech (Experiments 3--4), and solving simple math problems posed in对抗性言语（实验5） - 即使对于先前描述为人类听众难以理解的刺激也是如此。我们建议在比较人类和机器感知时采用这种“敏感测试”，并讨论评估系统之间重叠的这种方法的更广泛的后果。
The rise of machine-learning systems that process sensory input has brought with it a rise in comparisons between human and machine perception. But such comparisons face a challenge: Whereas machine perception of some stimulus can often be probed through direct and explicit measures, much of human perceptual knowledge is latent, incomplete, or unavailable for explicit report. Here, we explore how this asymmetry can cause such comparisons to misestimate the overlap in human and machine perception. As a case study, we consider human perception of \textit{adversarial speech} -- synthetic audio commands that are recognized as valid messages by automated speech-recognition systems but that human listeners reportedly hear as meaningless noise. In five experiments, we adapt task designs from the human psychophysics literature to show that even when subjects cannot freely transcribe such speech commands (the previous benchmark for human understanding), they often can demonstrate other forms of understanding, including discriminating adversarial speech from closely matched non-speech (Experiments 1--2), finishing common phrases begun in adversarial speech (Experiments 3--4), and solving simple math problems posed in adversarial speech (Experiment 5) -- even for stimuli previously described as unintelligible to human listeners. We recommend the adoption of such "sensitive tests" when comparing human and machine perception, and we discuss the broader consequences of such approaches for assessing the overlap between systems.
