By way of arrogating pedantic prerogative, I note that the more precise usage is "speech recognition", although admittedly both terms are recognized.

"Voice recognition" more precisely refers to biometric applications, i.e., deducing the identity of a speaker based on characteristics of his/her voice.

"Speech recognition" refers to the inference of speech based on vocal utterances.

If all your SR software did was to tell you who is speaking based on your voice, you wouldn't find that useful. You want it to produce the text of what you say.

Alternatively, consider that coloraturas, mechanized garage doors and my hyper-vocal Irish Setter all have distinctive voices, but none of them are properly considered as producing speech. Formally, speech is a proper subset of all vocalizations.

My speaker set seems to have died -- at least it hasn't produced noise the past week or so. I took it apart to stare at it and drain static electricity off by grounding it on a water faucet. This is my standard therapy for wayward electronic parts -- it doesn't actually work on anything except my AT&T handset, but I do it because it's the only thing I know how to do.

I took it apart mainly because I wanted to see if there was some sort of electronic burn-smell, but all I can smell is the aroma of the pressed woodchip panels in the subwoofer -- actually not all that bad! There's a 3 amp 250 V fuse which seems to be intact and a bunch of discrete things like capacitors, transistors, and other stuff I don't know the names of. But there doesn't seem to be anything obviously wrong -- no transitors that rattle when you shack them, no capacitors whose leads come off when you pull them, etc.

Submitted by Joeblake1 on Tue, 08/30/2005 - 01:23.

Here's how I've "remotely trained" my DNS to a speaker who doesn't even know they're doing it (ie training the Dragon).

Firstly, some more caveats: or the same ones in different words. I mentioned that it could be "fiddly" because it depends on which version of DNS you're using. Whilst I have V6 and V7, and the V7 upgrade, I reverted back to V5 because it was faster and easier. Secondly, there are three parts, the first part, creation the training document is reasonably straight forward, the second part is probably the most difficult, the third is easy, but initially time consuming.