<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD><TITLE id=ridTitle>Blank</TITLE>
<META content="text/html; charset=us-ascii" http-equiv=Content-Type>
<STYLE>BODY {
MARGIN-TOP: 25px; FONT-SIZE: 10pt; MARGIN-LEFT: 25px; COLOR: #808080; FONT-FAMILY: Verdana
}
P.msoNormal {
MARGIN-TOP: 0px; FONT-SIZE: 10pt; MARGIN-LEFT: 0px; COLOR: #ffffcc; FONT-FAMILY: Helvetica, "Times New Roman"
}
LI.msoNormal {
MARGIN-TOP: 0px; FONT-SIZE: 10pt; MARGIN-LEFT: 0px; COLOR: #ffffcc; FONT-FAMILY: Helvetica, "Times New Roman"
}
</STYLE>
<META name=GENERATOR content="MSHTML 8.00.6001.19298"></HEAD>
<BODY style="FONT-FAMILY: Verdana; COLOR: #808080; FONT-SIZE: 10pt" id=ridBody
background=cid:828262211@02102012-355A>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>Hi Guys,</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>As I mentioned in a
previous email, we are moving into the pilot phase of our project and we are in
the middle of defining objectives for the pilot. One of these will be to
test the accuracy of the speech recognition. I'm interested in knowing
what people find are the main factors that affect accuracy of recognition, so
that we can test them. I suspect they include the
following:</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>- the amount of voice
training provided for the speech model;</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>- the detection threshold
set in simon;</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>- the background
noise;</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>- what microphone you are
using;</SPAN></FONT></P>
<P><FONT color=#3a3a3a><SPAN class=828262211-02102012>What points have I
missed? I suspect that individuals get better with time as they adjust
their speech to fit system with the benefit of
experience.</SPAN></FONT></P>
<P><FONT color=#3a3a3a>Regards<BR><BR>Steve</FONT></P></BODY></HTML>