Chris Dobbs wrote:
> I realised early on that PA used /dev/dsp so I did "ln -s /dev/dsptask/pcm1
> /dev/dsp"
> I have tried various others but to no avail, can anyone help I know PA
> supports OSS and ALSA which are both installed on the N800, although I think
> esd is the default driver.
I ha
Hi,
I'm not exactly sure where to report this bug, since maemo is using
quite an old version of GCC, and I'm not sure if it is still present in
the more recent ones.
Anyway, when compiling this code:
#include
__thread FILE *logfp = (FILE *)-1;
FILE *
set_logfp(FILE *newfp)
{
FILE *oldfp
On Wed, 2008-04-23 at 14:15 -0500, nisha jain wrote:
> to port it to N800 later on...Please let me know if some one has
> developed such
> application and used fft calculation for discrete signals...
If you are dealing with real-valued data (e.g. audio), you can use the
fixed-point FFT routine
Marco Solari wrote:
> Hi!
> I have a question about the voice recognition problem on the Nokia platform,
> hoping it's not too off-topic...
> I see on this platform some voice recognition tool is available, but it's
> extremely resource demanding, slow and performs with quite a low success
> percen
David Huggins-Daines wrote:
> Yes, this is exactly the case. Recognizing a limited set of names in
> isolation is not at all computationally intensive compared to
> recognizing full sentences of connected words.
>
> See: http://en.wikipedia.org/wiki/Dynamic_time_warping
Marco Solari wrote:
> The question is: is the task of recognizing a small set of utterances
> basically different from the task of recognizing spoken words out of a
> bigger dictionary (I limit the problem to single words, not considering the
> spoken speech...)
Yes, this is exactly the case. Reco
Tuomas Kulve wrote:
>
> Sorry for bad paste, but I would guess that removing the noexec in
> /etc/fstab would help.
>
Also to turn on the exec option without having to unmount and remount
the filesystem, you can run:
mount /media/mmc1 -oremount,exec
(or /media/mmc2 for the internal one).
Thi
Hi,
Though I know that GStreamer is the preferred way to do audio capture
and playback on Maemo, I couldn't resist trying out the ALSA support
that is built into PocketSphinx. On the previous release of ITOS2007 it
didn't work at all - at a certain point during initialization, reading
from th
Hi,
I've finally gotten around to packaging PocketSphinx
(http://www.pocketsphinx.org/) for the N800. This is *not* going to be
useful for anyone who isn't a developer, because the included language
models aren't very good, and the audio input using ALSA doesn't seem to
work correctly. Nonet
Hi,
Is it possible to use gprof on binaries compiled for the N800? Or is
there any other means of profiling?
Thanks!
___
maemo-developers mailing list
maemo-developers@maemo.org
https://lists.maemo.org/mailman/listinfo/maemo-developers
Simon Pickering wrote:
>
> Yes, that's the wiki page I made to pull together the details of how
> to get everything up and running. It should get you up and running. As
> more projects (hopefully) get started, we may need to make some
> changes to detail problems, tips, etc.
If anyone has succes
Simon Pickering wrote:
> I chose something relatively easy to make sure I didn't lose the will
> (battling against both the algorithm and the DSP oddities).
>
> Anyway, my hope is that this might show people that it's quite easy to
> use the dsp (for something simple at least), and to get people
Marco Solari wrote:
> When You speak about "acoustic models", You mean "English acoustic models",
> is it true ? Do some different language acoustic models exist ? Do Italian
> language acoustic models exist ? If not, which do You think would be the
> effort to put it up, in terms of time and knowl
David Huggins-Daines wrote:
> Marco Solari wrote:
>> I am currently evaluating the porting to the ARM architecture of
>> open-source
>> projects 'rsynth' and 'festival' for text2speech, and 'pockesphinx' for
>> speech2text ...
> Hi
Marco Solari wrote:
> I am currently evaluating the porting to the ARM architecture of open-source
> projects 'rsynth' and 'festival' for text2speech, and 'pockesphinx' for
> speech2text ...
Hi, I'm working on speech recognition for the N800. Plans and status
can be found at http://lima.lti.cs.cm
15 matches
Mail list logo
