Processing Electromyographic Signals to Recognize Words
From: NASA Tech Briefs - 05/2009 - page 59

The speaker need not make any sound.

A recently invented speech-recognition method applies to words that are
articulated by means of the tongue and throat muscles but are otherwise not
voiced or, at most, are spoken sotto voce. This method could satisfy a need
for speech recognition under circumstances in which normal audible speech is
difficult, poses a hazard, is disturbing to listeners, or compromises
privacy. The method could also be used to augment traditional speech
recognition by providing an additional source of information about
articulator activity. The method can be characterized as intermediate between
(1) conventional speech recognition through processing of voice sounds and
(2) a method, not yet developed, of processing electroencephalographic
signals to extract unspoken words directly from thoughts. 

From:
http://www.techbriefs.com/component/content/article/5195

Links:
Chuck Jorgensen
http://www.nasatech.com/NEWS/May04/who_0504.html

Subvocal Speech and the Development of Biological Interfaces
http://hci.stanford.edu/cs547/abstracts/05-06/060217-jorgensen.html

NASA researchers can hear what you're saying, even when you don't make a sound
http://www.forbes.com/free_forbes/2006/0410/084.html

Muscles tapped for virtual input
http://www.trnmag.com/Stories/020701/Muscles_tapped_for_virtual_input_020701.html