Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!usc!apple!bionet!hayes.ims.alaska.edu!accuvax.nwu.edu!nucsrl!telecom-request
From: slr@tybalt.caltech.edu (Steve Rhoades)
Newsgroups: comp.dcom.telecom
Subject: Re: Voice Activated Calling Cards
Message-ID: <14548@accuvax.nwu.edu>
Date: 9 Nov 90 19:18:05 GMT
Sender: news@accuvax.nwu.edu
Organization: California Institute of Technology, Pasadena
Lines: 30
Approved: Telecom@eecs.nwu.edu
X-Submissions-To: telecom@eecs.nwu.edu
X-Administrivia-To: telecom-request@eecs.nwu.edu
X-Telecom-Digest: Volume 10, Issue 806, Message 11 of 12


In article <14493@accuvax.nwu.edu> SABAHE@macalstr.edu (Arun Baheti
<SABahe@Macalstr.EDU>) writes:

>Sprint.  I recall a few years ago that there was a company (All-Net?)
>that allowed people not at touch-tone phones to "speak" their card
>numbers into a machine, one digit at a time, and then the destination
>number the same way.  It then asked for verification with yes/no

I remember a couple of companies about ten years ago that had this
system.  One in particular, I think it was called Travelnet, comes to
mind.  It was sort of a favorite phreaker thing to play with,
especially from coin phones.  Most of the coin phones in Los Angeles
were rotary at that time.

The major difference in these old systems and the new Sprint service
is Sprint uses voice-PATTERN recognition along with regular voice
recognition.  i.e. In the old systems, it didn't care who you were,
just as long as you uttered something resembling digits.

With Sprint's service, the uttered digits are supposed to match ones
you've previously recorded.

I am curious how their system would work from a noisy location, like
outside an airport.  It seems that the additional outside noise might
cause errors in the system.


Internet: slr@tybalt.caltech.edu  |  Voice-mail: (818) 794-6004
UUCP: ...elroy!tybalt!slr         |  USmail: Box 1000, Mt. Wilson, Ca.  91023