Li Zhuang, Feng Zhou, and Doug Tygar have an interesting new paper [1] showing that if you have an audio recording of somebody typing on an ordinary computer keyboard for fifteen minutes or so, you can figure out everything they typed. The idea is that different keys tend to make slightly different sounds, and although you don't know in advance which keys make which sounds, you can use machine learning to figure that out, assuming that the person is mostly typing English text. (Presumably it would work for other languages too.)
Via Robot Wisdom [2], “Acoustic Snooping on Typed Information [3]”
I may have to rethink the keyboards I use [4] …
[1] http://www.cs.berkeley.edu/~tygar/papers/Keyboard_Acoustic_Emanations
[2] http://www.robotwisdom.com/