Thank you, Alex<div><br></div><div>yes, I expect the pickup time to vary within 1 second (it's just a guess). If I have to tolerate higher bias, so I would start doubting about the efficiency of this method.<br><br><div class="gmail_quote">
On Mon, May 16, 2011 at 4:00 PM, Alex Balashov <span dir="ltr"><<a href="mailto:abalashov@evaristesys.com" target="_blank">abalashov@evaristesys.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">You would have to make the tolerance of variance fairly high. There are many reasons why pickup time by a mechanical device such as an answering machine or a fax machine may vary quite significantly.<br>
<br>
--<br>
Alex Balashov - Principal<br>
Evariste Systems LLC<br>
260 Peachtree Street NW<br>
Suite 2200<br>
Atlanta, GA 30303<br>
Tel: <a href="tel:%2B1-678-954-0670" value="+16789540670" target="_blank">+1-678-954-0670</a><br>
Fax: <a href="tel:%2B1-404-961-1892" value="+14049611892" target="_blank">+1-404-961-1892</a><br>
Web: <a href="http://www.evaristesys.com/" target="_blank">http://www.evaristesys.com/</a><br>
<div><div></div><div><br>
On May 16, 2011, at 8:56 AM, Aurimas Skirgaila <<a href="mailto:a.skirgaila@gmail.com" target="_blank">a.skirgaila@gmail.com</a>> wrote:<br>
<br>
> Hi,<br>
><br>
> long time ago, I came up with an optimal configuration set for my environment - good detection and little false positives. Unfortunately some people are always being detected as Answering Machines.<br>
><br>
> I'm not up to re-adjust my precious balance of initial_silence/max_words/... , so I'm thinking about to check if the pickup time is equal to the pickup time when the same phone number was previously detected as AM - if the pickup time is different from the last time, - it's HUMAN, else proceed standard AMD().<br>
><br>
> has anyone done this before,so I wouldn't be reinventing bicycle?<br>
><br>
><br>
> --<br>
> Mvh,<br>
> Aurimas Skirgaila<br>
</div></div>> --<br>
> _____________________________________________________________________<br>
> -- Bandwidth and Colocation Provided by <a href="http://www.api-digital.com" target="_blank">http://www.api-digital.com</a> --<br>
> New to Asterisk? Join us for a live introductory webinar every Thurs:<br>
> <a href="http://www.asterisk.org/hello" target="_blank">http://www.asterisk.org/hello</a><br>
><br>
> asterisk-users mailing list<br>
> To UNSUBSCRIBE or update options visit:<br>
> <a href="http://lists.digium.com/mailman/listinfo/asterisk-users" target="_blank">http://lists.digium.com/mailman/listinfo/asterisk-users</a><br>
<br>
--<br>
_____________________________________________________________________<br>
-- Bandwidth and Colocation Provided by <a href="http://www.api-digital.com" target="_blank">http://www.api-digital.com</a> --<br>
New to Asterisk? Join us for a live introductory webinar every Thurs:<br>
<a href="http://www.asterisk.org/hello" target="_blank">http://www.asterisk.org/hello</a><br>
<br>
asterisk-users mailing list<br>
To UNSUBSCRIBE or update options visit:<br>
<a href="http://lists.digium.com/mailman/listinfo/asterisk-users" target="_blank">http://lists.digium.com/mailman/listinfo/asterisk-users</a><br>
</blockquote></div><br><br clear="all"><br>-- <br>Mvh,<br>Aurimas Skirgaila<br>
</div>