L. Zhuang, F. Zhou, J. D. Tygar, "Keyboard Acoustic Emanations Revisited", in 12th ACM Conference on Computer and Communications
Security (CCS'05), pp. 373-382, November 2005.

Abstract
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 recovering 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 experiments, 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. Our attack uses the statistical constraints of the
underlying content, English language, to reconstruct text from sound recordings
without any labeled training data. The attack uses a combination of standard
machine learning and speech recognition techniques, including cepstrum features,
Hidden Markov Models, linear classification, and feedback-based incremental
learning.

@inproceedings{1102169,
 author = {Li Zhuang and Feng Zhou and J. D. Tygar},
 title = {Keyboard acoustic emanations revisited},
 booktitle = {CCS '05: Proceedings of the 12th ACM conference on Computer and communications security},
 year = {2005},
 isbn = {1-59593-226-7},
 pages = {373--382},
 location = {Alexandria, VA, USA},
 doi = {http://doi.acm.org/10.1145/1102120.1102169},
 publisher = {ACM Press},
 address = {New York, NY, USA},
 }

http://dx.doi.org/1102120.1102169