<div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Note to self: "Never release anything asterisk related without testing<br>
on RHEL/Centos 5"<br>
<br>
Thank you for reporting this. I have replaced sox with flac and it seems<br>
to work now on older platforms too (tested on Centos 5 with asterisk 1.4).<br>
You can get the updated code here:<br>
<a href="https://github.com/zaf/asterisk-speech-recog/tarball/master" target="_blank">https://github.com/zaf/asterisk-speech-recog/tarball/master</a><br>
<div><div></div><div><br>
----------------<br>
Lefteris Zafiris<br>
</div></div><div><br></div></blockquote><div><br></div><div>Works beautifully. Amazing job Lefteris. Thanks.</div><div><br></div><div>The best result I got in probability was 0.9725632 by saying, "hello". I think there is some non-phonetic logic built-in as well. I tried, "1, 2" and I got "0.86534226" in accuracy. While I tried "1, 2, 3, 4, 5" I got, "0.97256315". Probably Google sees the pattern?!</div>
<div><br></div><div>What are some of the other tricks (if any) or consideration that one should make while creating a strong speech recognition enabled IVR?</div><div><br></div><div>Best,</div></div><br>