Speex dev - Oct 2005 - About echo CPU consuption

Hi,

Jean, thanks for your source code example.

I like ask info about cpu consuption, in our example enabling echo removing
cause the sound poppling with a celeron 1.7Ghz (taskman show cpu full,
without echo is at 30%).

Does exist a mode to lower the cpu consuption in echo removing? Because a
large part of users base own still "old" CPU of 6-7 generation, as
from
500-700 Mhz and lower too.

Perhaps the code need be optimized? Or can be possible adapt the echo
removal upon consume a max cpu bound?

Again yours,

Roberto

The echo cancellation should take that much CPU. Maybe the echo tail
(filter length) you're using is too large? Try with 160-sample frame
size and 800-sample filter length.

	Jean-Marc

Le mardi 11 octobre 2005 ? 14:05 +0200, Roberto Della Pasqua a ?crit
:
> Hi,
> 
> Jean, thanks for your source code example.
> 
> I like ask info about cpu consuption, in our example enabling echo removing
> cause the sound poppling with a celeron 1.7Ghz (taskman show cpu full,
> without echo is at 30%).
> 
> Does exist a mode to lower the cpu consuption in echo removing? Because a
> large part of users base own still "old" CPU of 6-7 generation,
as from
> 500-700 Mhz and lower too.
> 
> Perhaps the code need be optimized? Or can be possible adapt the echo
> removal upon consume a max cpu bound?
> 
> Again yours,
> 
> Roberto 
> 
> _______________________________________________
> Speex-dev mailing list
> Speex-dev@xiph.org
> http://lists.xiph.org/mailman/listinfo/speex-dev
>

Hi, all.
I'm a programmer lived in Korea.
This time, I was investingating echo cancellation and found speex echo 
cancellation related API.
But echo stilll remains.

1. echo cancellation using only files works propertly.
2. echo cancellation using sound device works not propertly.

You can download test files as followed.

http://www.vdream.co.kr/temp/ec/echocancel.wmv ( testing screen capture 
file )

http://www.vdream.co.kr/temp/ec/echocancel.zip ( test files )

The reason why echo still remains is that speaking signal from sound device 
differs from speaking signal from file, I guess.

It's my pleasure to see my testring files.
Thanks in advanced.