"We examine the problem of keyboard acoustic emanations.
We present a novel attack taking as input a 10-minute sound recording of a user
typing English text using a keyboard, and then recover- ing up to 96% of typed
characters. There is no need for a labeled training recording. Moreover the
recognizer bootstrapped this way can even recognize random text such as
passwords: In our experi- ments, 90% of 5-character random passwords using only
letters can be generated in fewer than 20 attempts by an adversary; 80% of 10-
character passwords can be generated in fewer than 75 attempts.
http://www.cs.berkeley.edu/~tygar/keyboard.htm