Subvocal Speech

In preliminary experiments, NASA scientists found that button-sized sensors,
stuck under the chin and on either side of the "Adam's apple," could gather
nerve signals, transmit them to a processor, and then deliver them to a
computer program that translates them into words. 

"A person using the subvocal system thinks of phrases and talks to himself so
quietly, it cannot be heard, but the tongue and vocal chords do receive
speech signals from the brain," Chuck Jorgensen, a scientist whose team is
developing silent, subvocal speech recognition at NASA's Ames Research Center
explained. 

Eventually, such "subvocal speech" systems could be used in spacesuits, in
noisy places like airport towers to capture air-traffic controller commands,
or even in traditional voice-recognition programs to increase accuracy. A
spin-off would be that handicapped persons could use this system for a
variety of tasks. 

Initial word recognition results were an average of 92% accurate. Scientists
are testing new, "noncontact" sensors that can read muscle signals even
through a layer of clothing. 

Read the complete story at:
http://www.nasa.gov/centers/ames/news/releases/2004/subvocal/subvocal.html

---

NASA Develops 'Mind-Reading' System
From: New Scientist Magazine - 03/18/2004
By: Maggie McKee

NASA scientists have developed a software program that can analyze the nerve
signals in the mouth and throat to read a person's mind. "Biological signals
arise when reading or speaking to oneself with or without actual lip or
facial movement," says Chuck Jorgensen, a neuroengineer at NASA's Ames
Research Center in Moffett Field, CA, who heads the research effort. The NASA
researchers have used the computer program to perform simple searches on the
Web. Button-sized sensors, placed under the chin and on either side of the
Adam's apple, were able to pick up nerve signals from the tongue, throat, and
vocal cords. NASA researchers trained the software program to recognize six
words, and the system was able to pick up the word thought by participants
hooked up to sensors 92 percent of the time. Moreover, they programmed the
system with a matrix of the letters of the alphabet with each column and row
assigned a single-digit number, then had participants silently spell "NASA"
into a Web search engine, which enabled them to browse the Web without using
a keyboard. The system eventually could be used to send commands to rovers on
other planets, or help an injured astronaut to control machines. The
handicapped, including people who are unable to talk, might be able to
benefit from the system as well. University of Sheffield computer scientist
Phil Green says the technology is "interesting and novel," and although he
says it needs more testing, it could be coupled with existing
voice-recognition technology for greater effect. 

Read the entire story at:
http://www.newscientist.com/news/news.jsp?id=ns99994795