IP: [well maybe djf] Machine Demonstrates Superhuman Speech Recognition Abilities

[David Farber <farber () cis upenn edu>]

I asked for an opinion and got

"I watched their vidoe over the net.  There's a lot that's not said in
their demo.  They present a 4 word recognition system, by the way."

djf


> Date: Fri, 1 Oct 1999 23:54:06 +0200 (CEST)
> From: Gunnar Helliesen <gunnar () bitcon no>
> To: Dave Farber <farber () cis upenn edu>
>
>
> Prof. Farber,
>
> I came across this through a link on Slashdot. I thought perhaps it would
> be interesting to IP-ers. Excerpts from the USC press release:
>
>
> "University of Southern California biomedical engineers have created the
> world's first machine system that can recognize spoken words better than
> humans can. A fundamental rethinking of a long-underperforming computer
> architecture led to their achievement."
>
> "Neural nets are computing devices that mimic the way brains process
> information. Speaker-independent systems can recognize a word no matter
> who or what pronounces it."
>
> "The system can distinguished words in vast amounts of random
> 'white' noise - noise with amplitude 1,000 times the strength of the
> target auditory signal. Human listeners can deal with only a fraction as
> much."
>
> "'Even large nets with more than 1,000 neurons and 10,000 interconnections
> have shown lackluster results compared with theoretical
> capabilities. Deficiencies were often laid to the fact that even
> 1,000-neuron networks are tiny, compared with the millions or billions of
> neurons in biological systems.'
>
> Remarkably, USC's neural net system uses an architecture consisting of
> just 11 neurons connected by a mere 30 links."
>
>
> More information here (the USC press release):
> http://www.usc.edu/ext-relations/news_service/releases/stories/36013.html
>
>
> Gunnar
>
> --
> Gunnar Helliesen   | Bergen IT Consult AS  | NetBSD/VAX on a uVAX II
> Systems Consultant | Bergen, Norway        | '86 Jaguar Sovereign 4.2
> gunnar () bitcon no   | http://www.bitcon.no/ | '73 Mercedes 280 (240D)