XYBR - Xybernaut Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : XYBR - Xybernaut

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Fred Williams who wrote (2559)	4/29/1999 11:25:00 PM
From: Dave Shoe	Read Replies (1) of 6847

>>>effective speech recognition capability With 600MHz "Coppermine" laptop CPUs available from Intel in a matter of months, with 1GHz wearables a year or two away, and with a heavy worldwide focus on speech recognition (SR) software development, I feel it's only a matter of time before recognition error rates drop to insignificant levels. One type of voice microphone I'd someday like to see is an "in your ear" microphone. Yup, the "voice microphone" would be co-located with the "earplug speaker" in the computer's single earpiece. Though noise-cancelling microphones (which can't hear anything a few inches away or more) are readily available, co-location of the microphone and speaker in a single earpiece would eliminate the microphone boom and prevent nearby voices from activating the SR software because all external voices would have an entirely different acoustic signature than that of a voice which had been sourced from the direction of the ear canal and cranium. The SR software can be easily trained to recognize the unusual acoustic properties of an earplug microphone, though a reasonably simple active-noise-reduction (ANR) circuit and algorithm would need to be developed to mode-out speaker feedback into the microphone. This circuit would be patterned after the circuitry of noise-cancelling aircraft headsets (reference: st6.yahoo.com. Additionally, this circuitry could also create sound which allowed external voices and sounds to actively pass through the earpiece making it sound as though the earpiece wasn't even present. The only drawback would a slight increase in power consumption, but this would be minimized in an optimal design. Just dredging up bad and incomplete ideas again, Shoe.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next