Re: VEDICS Speech Assistant

[José Félix Ontañón <felixonta gmail com>]

2010/5/21 Nischal Rao <rao nischal gmail com>

Hi,

I and some of my friends have created a speech assistant software for linux called VEDICS(Voice Enabled Desktop Interaction and Control System). Using this software the user can access any element found on the user's screen through speech. The user can also navigate the filesystem through speech.

We have created some demo screencasts of the software:

1. Accessing the gnome panel and application.
http://www.youtube.com/watch?v=WrVaJXtv0WU
 
2. Changing the theme and background.
http://www.youtube.com/watch?v=zRgX94qGj3g

3. Navigating directories and playing songs:
http://www.youtube.com/watch?v=kVQwAoeIavk

4. Running a slide show:
http://www.youtube.com/watch?v=JtzA8TFwvuI

5. Running default applications and window operations:
http://www.youtube.com/watch?v=iCEANbu8p50

6. Stopping and starting vedics:
http://www.youtube.com/watch?v=TLFtdrlt3lM

7. Creating and deleting files:
http://www.youtube.com/watch?v=_3CFAl22h2o

8. Navigating links:
http://www.youtube.com/watch?v=AufBaaJazKU


Currently the software doesn't support the dictation facility. However, we are planning to add this feature in the future.
The best part of this software is that it is speaker independent, no training is required and it can recognize words not present in the English dictionary.

You can find the source code at : http://sourceforge.net/projects/vedics/

Hi Nischal,

Congrats! The screencasts are amazing and, as i can see in
sourceforge, it relies on at-spi for discovering the elements that
could be commanded, isn't?

I suppose you know about
gnome-voice-control, even both projects shares sphinx for speech
recognition so, what do you think vedics differs from
gnome-voice-control or improve it?

Cheers!

-- 
http://fontanon.org