<html>
<body>
<font color="#0000FF">Hi,<br><br>
Thanks a lot for describing the vad algo it seems rather a basic
algo and I am surprised it is not more sophisticated. I hear also from
speex users (must be same algo?) that the vad algo is very poor and
should be improved. That is what I am doing, try to improve vad and echo
cancellation algorithms. I would appreciate a link where I can find data
files (audio) to download on which I can perform tests. Of course I will
feedback the freeswitch community in case of improvment.<br><br>
best<br><br>
Zelda<br><br>
<br><br>
</font>At 15:09 15/02/2008, Anthony Minessale wrote:<br>
<blockquote type=cite class=cite cite="">The algorithm used is not so
great and could stand to be replaced<br>
by a better one if we get the chance.<br><br>
basically we decode the audio to signed linear 16bit samples<br>
for each packet we receive and iterate the samples and add up the<br>
absolute values then compute the average and compare it to the <br>
acceptable level considered "talking" then we use a counter to
make<br>
sure it's in the same state several times in a row before actually<br>
changing the status of the channel to talking or not talking.<br><br>
<br>
A real vad algorithm would also be able to filter out the voice from<br>
the background noise and judge the energy based only on that.<br>
</blockquote></body>
</html>