Better speech recognition through chipsets

Researchers at Carnegie Mellon University are hoping to do for speech recognition what graphics cards did for gaming -- that is, make it better. The idea being to use specialized computer chips in order to overcome the problems inherent with software-based solutions, which'll also lower the power consumption required and allow for better speech recognition in things like cellphones. And according to the researchers, it's working, although currently limited to a not-very-practical 1,000 word vocabulary. The technology isn't just for dictating your email though; one of the many possible noted examples of applications is making search available on a specific piece of dialog from a movie. Wonder if they've been having any secret back room meetings with a certain rumor-happy video game company?

[Justin @ Aug 23rd 2006 6:02PM]

Computer, find that part in Ghostbusters where Egon says "Don't cross the streams."

[slyecho @ Aug 23rd 2006 6:02PM]

Now someone needs to make speech synthesis cards, and the computer can speak to itself!

[chris @ Aug 23rd 2006 6:26PM]

i think you've got it wrong. i think gaming made graphics cards better, not the other way around.

[Grammar boy @ Aug 24th 2006 5:38AM]

Surely a 1000 word vocabulary is more than enough for most Americans?

No what i'm sayin'?

[Tim Lesher @ Aug 24th 2006 9:53AM]

Actually, a 1000-word vocabulary is far more than enough for most industrial voice applications. In that area, you're usually dealing with vocabularies on the order of 100 words.

[ravuya @ Aug 24th 2006 10:18AM]

Didn't we have a voice-recognition or at least voice-synthesis card for the Apple II?

Evertyhin old is new again.

[Pete @ Aug 24th 2006 6:52PM]

That's actually a picture of me at work many years ago. Where did you find this picture? BTW: It has nothing to do with the article.