[Sugar-devel] GSOC 2010: Speech Recognition in Sugar

[Benjamin M. Schwartz]

I think your proposal is very interesting.  It contains a number of
different ideas.  One major division is between Voice Commands and Speech
Recognition.  Each of these contains many other possibilities. My biggest
suggestion is to specify further which possibilities you want to work on.
 I recommend you schedule the _easiest_ thing first, before moving on to
the hard things.  Most GSoC students are too ambitious and never produce
anything useful.

Some specific ideas:

Voice Commands:
 - integrate with a text-command system like Gnome Do [1], so that the
commands are accessible through the keyboard as well as microphone.  Also
look at Perlbox [2].  (Note that neither Gnome Do or Perlbox can be used
directly.)
 - integrate with GnomeVoiceControl [3], which already uses PocketSphinx
and should be highly compatible with Sugar.   This could allow voice
control of unmodified Activities.

Speech Recognition:
 - supply text to any unmodified activity
 - control input language easily for multilingual users

[1] http://do.davebsd.com/index.shtml
[2] http://perlbox.sourceforge.net/
[3] http://live.gnome.org/GnomeVoiceControl

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 198 bytes
Desc: OpenPGP digital signature
Url : http://lists.sugarlabs.org/archive/sugar-devel/attachments/20100403/748c4576/attachment.pgp