Soc progress report - Raphael Nunes

["Raphael Nunes" <raphael nunes enc04 gmail com>]

Hello,

   My name is Raphael Nunes and I will introduce my first report of
my GSoC project[1].

   I'm working on a first release of the speech recognition software,
developing a basic Speech Recognition System to Control the Gnome
Desktop.
   The first release will recognize a basic set of speechs like
minimize windows, maximize windows.
   The software is being developed as a applet.
   I already wrote some basic libraries of the system [2].
   I wrote a basic library that catches the audio and write it into a
raw file,
a basic library that catches the raw file and decode into text files
using the CMU Sphinx Tool [3], a basic library that catches the text
files and break into a token list.
   Currently I'm writing a library that catches the token list
processes it and executes the desired action over the GNOME Desktop.
I'm studying ATK, I think that is the better way to do the event of
execute the action over the GNOME Desktop.
   We have a skeleton of the applet too, that is placed on svn at
berlios.de [4].
   The remaining portion of the code I didn't put into the svn
because I'm trying to finish the libraries first and recognize my
voice better. After this I will update the applet skeleton with the
remaining code.
   I'm having some problems on recognition of my voice, I'm recording
my voice with the CMU Sphinx API. After talking with my
mentor(Nickolay Shmyrev) about the problems on recognition of my
voice, he proposes me to record the voice using GStreamer. Then I'm
writing a basic code using GStreamer, but isn't finished yet.
   My mentor give me a e-book, about speech processing, to read [5][6].
I am reading the book and it's upgrading a lot my knowledge on speech
processing.

                                   Thanks,
                                   Raphael Nunes

[1] http://code.google.com/soc/gnome/appinfo.html?csaid=4F64D394968BB092
[2] http://www.comp.ufscar.br/~raphael18/gnome-voice-control/
[3] http://cmusphinx.sourceforge.net/html/cmusphinx.php
[4] http://svn.berlios.de/svnroot/repos/festlang/trunk/gnome-voice-control/
[5] http://www.comp.ufscar.br/~raphael18/SLP1.djvu
[6] http://www.comp.ufscar.br/~raphael18/SLP2.djvu