That's amazing, I'm impressed. I have no idea how voice recognition software works, but is it possible using this open source project to add other non-Latin languages (e.g. Greek, Arabic, Japanese)?
It uses the CMUSphinx project (http://cmusphinx.sourceforge.net/wiki/) that is language independent. You can download language models for English, Chinese, French, Spanish, German, Russian.
I'm working with PocjketSphinx now, it's totally language independant. There is a paper floating around for Arabic, in which they used several reads of the Qu'ran as training data. For Chinese there's a model in the official Sphinx page.
