[aklug] Speech recognition

Any of you guys ever played around with voice recognition software or programming APIs? Any stories to tell or helpful experiences?

I dived into this recently. I don't know anything about waveform models or anything fancy like that. I'm just trying to integrate existing software into my PC in order to control it through audio commands.

I had hoped fully-integrated (open-source) solutions were already available, but it doesn't seem so. I played around with three high level applications but couldn't get them to work for me: Perlbox runs fine, but has poor recognition. CVoiceControl is rather old and doesn't seem to be compatible with my modern audio system. Gnome-voice-applet looked promising, but I can't get the applet to initialize without crashing.

So now I'm diving a little deeper and learning about Snack. It seems to have Python, Tcl, and Ruby bindings, so I think I'll be able to pick up enough to utilize the API for my own purposes. Sphinx3 seems to be another possibility, although I think it is too low-level a tool to be practically useful to me.

-- 
Christopher Howard
frigidcode.com
theologia.indicium.us
---------
To unsubscribe, send email to <aklug-request@aklug.org>
with 'unsubscribe' in the message body.