Non-acoustic sensors detect speech without sound

New Scientist ^ | 4/9/05 | David Hambling

[LibWhacker]

Just think how eerie it would be, yet also how peaceful - people all around having conversations on their mobile phones, but without uttering a sound.

Thanks to some military research, this social nirvana just might come true. DARPA, the US Department of Defense's research agency, is working on a project known as Advanced Speech Encoding, aimed at replacing microphones with non-acoustic sensors that detect speech via the speaker's nerve and muscle activity, rather than sound itself.

One system, being developed for DARPA by Rick Brown of Worcester Polytechnic Institute in Massachusetts, relies on a sensor worn around the neck called a tuned electromagnetic resonator collar (TERC). Using sensing techniques developed for magnetic resonance imaging, the collar detects changes in capacitance caused by movement of the vocal cords, and is designed to allow speech to be heard above loud background noise.

DARPA is also pursuing an approach first developed at NASA's Ames lab, which involves placing electrodes called electromyographic sensors on the neck, to detect changes in impedance during speech. A neural network processes the data and identifies the pattern of words. The sensor can even detect subvocal or silent speech. The speech pattern is sent to a computerised voice generator that recreates the speaker's words.

DARPA envisages issuing the technology to soldiers on covert missions, crews in noisy vehicles or divers working underwater. But one day civilians might use a refined version to be heard over the din of a factory or engine room, or a loud bar or party. More importantly, perhaps, the technology would allow people to use phones in places such as train carriages, cinemas or libraries without disturbing others. Brown has produced a TERC prototype, and an electromyographic prototype is expected in 2008.

However, both systems come at a cost. Because the words are produced by a computer, the receiver of the call would hear the speaker talking with an artificial voice. But for some that may be a price worth paying for a little peace and quiet.

[LibWhacker]

Y'all know what's gonna happen, doncha 'ya? DARPA will perfect the technology, the price will come way down, it'll be widely available in the civilian sector, but there'll ALWAYS be some lout at the theater who will insist on carrying a loud conversation on his cellphone in the middle of the movie! :-P

[TigerLikesRooster]

Well, consonants are controlled by lip, tongue, opening of the mouth. Could neck-senors also pick up muscle activities and neuro signals which affect lip, tongue, and mouth?

While it can be handy, it sounds rather bulky to wear, sensors around your neck and their processing units somewhere on the body. Is the current version more like a motorcycle helmet?

However, someday not long in the future they can be made smaller. We may see a new fashion emerging. People were pretty collars around their neck, which are commercial version of this machine. Would we be still wearing neckties? Or would it be out of fashion by then?

[yer gonna put yer eye out]

"One system.....relies on a sensor worn around the neck..."

When they get the weight of this sensor down from 800 lbs. to about 40, they'll sell like hotcakes...:0)

Also, they might want to work on eliminating the 220V AC cable.

[TigerLikesRooster]

Re #2

And some suits of big corporation who claim that they did it all, stealing credits from DARPA. Without DARPA, some billionaires would never existed.

DARPA can take bolder trail-blazing projects because the bottom line they face is not profit but survival. You cannot discount the role of military competition in creating high-tech industry. In many cases, military does initial innovating, which is most difficult. And private sector later commercialize them to be useful consumer products.

In discussing modern economy, we heard a lot about the latter, but little in the former.

[Graymatter]

"non-acoustic sensors that detect speech via the speaker's nerve and muscle activity, rather than sound itself.

We have these already. We call them "wives."

[Dallas59]

Can you hear me now...

[ThreePuttinDude]

HA HA HA, good one......Glad you said it first

[Route101]

...One system, being developed for DARPA by Rick Brown of Worcester Polytechnic Institute in Massachusetts, relies on a sensor worn around the neck called a tuned electromagnetic resonator collar (TERC)...that's nice, but can they develop an (RCL).A collar that lets me know when a radical socialist liberal is around?

[infocats]

DARPA is also pursuing an approach first developed at NASA's Ames lab, which involves placing electrodes called electromyographic sensors on the neck, to detect changes in impedance during speech. A neural network processes the data and identifies the pattern of words. The sensor can even detect subvocal or silent speech. The speech pattern is sent to a computerised voice generator that recreates the speaker's words.

Interesting. I hope it works better than Via Voice ;-)