Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!mcnc!decvax.dec.com!decuac!wbc.enet.dec.com!baker
From: baker@wbc.enet.dec.com
Newsgroups: sci.electronics
Subject: Speech Recognition stuff...
Message-ID: <3269@decuac.DEC.COM>
Date: 27 Aug 90 13:13:43 GMT
Sender: guest@decuac.DEC.COM
Organization: Digital Equipment Corporation
Lines: 23

josef@nixpbe.UUCP (Moellers) writes

>A couple of years ago BYTE Magazine (when it was still usefull) had an
>article or two by Steve Ciarcia on a speech recognition system based on
>a chip made by General Instruments (I think). It was called something
>like SP256. The interesting thing about this chip is that it is
>advertised as being a speech synthesis chip.
.
.
.
>| Josef Moellers		|	c/o Nixdorf Computer AG	|

	Not quite. The Lis'ner 1000 board used an SP1000 -- an LPC
	coding chip to do the speech-parametrization.  The SP256 was
	an optional add-on that would do speech-output; it wasn't
	used by the recoginition mechanism at all.   

	The relevant article was reprinted in Ciarcia's Circuit Cellars
	Volume 5.

	~art baker		|  "Whatever happened to Fay Wrey,
	 (usual disclaimers)	|    that delicate, satin-draped frame..."
	-------------------------------------------------------------------