Displaying 5 results from an estimated 5 matches for "omap1510".
Did you mean:
imap1514
2006 Nov 02
2
echo cancellation on PDA
Hello all,
Today I tried speex echo cancellation on my VoIP application running
on a windows mobile based PDA (OMAP1510 168MHz). The result is
disappointing: it takes 150-250 ms to do echo cancellation (by calling
speex_echo_capture() ) for a 20 ms frame!
I've defined the FIXED_POINT macro. Is there anyway to do some optimization?
Nick
2004 Aug 06
4
XScale realtime encoding possible?
Le dim 09/11/2003 à 14:33, Steve Kann a écrit :
> Just out of curiosity, has anyone profiled the difference between the
> floating point and fixed point implementations on processors with
> decent floating point support? (i.e. x86, PPC).
On recent x86 processors, floating point is faster than fixed-point.
Jean-Marc
--
Jean-Marc Valin, M.Sc.A., ing. jr.
LABORIUS
2004 Aug 06
0
XScale realtime encoding possible?
I'm developing a Personalized system of news audible for PDAs(Pocket PC
and Palm OS), I have somes PDAs with differents processors(Samsung
(2410) 266 MHz, Intel Xscale PXA 250 to 200 and 400 MHz, OMAP1510) with
Pocket PC 2002 and 2003, and Palm OS 5 operating system. I offer myself
to test any application of speex that runs in these machines, only you
must send me the source code.
Regards.
Rodrigo Parra M.
MSc.(c), Computer Engenieer.
Pontific Catholic University of Chile
-----Mensaje original----...
2006 Nov 02
2
echo cancellation on PDA
2006/11/2, Jean-Marc Valin <jean-marc.valin@usherbrooke.ca>:
> > Today I tried speex echo cancellation on my VoIP application running
> > on a windows mobile based PDA (OMAP1510 168MHz). The result is
> > disappointing: it takes 150-250 ms to do echo cancellation (by calling
> > speex_echo_capture() ) for a 20 ms frame!
>
> Are you by any chance using an insane sampling rate and/or tail length.
> Try a sampling rate of 8000 Hz, 128-sample frame size an...
2005 Mar 22
1
Re: Speex on a T.I. TMS320C5510 DSP
Hi Frank,
Actually, I just merged (in SVN) a patch doing exactly that. AFAIK it
allows Speex to run on a C55x. I think it should work for you with the
following caveats:
1) The static codebooks still take up 16 bits for every 8-bit value
(that's only a code size issue)
2) The bit-packer always returns a multiple of 16 bits instead of 8 bits
(but it uses all bits when packing).
Jean-Marc