Random Post!.
Theres a open source voice recognition software: CMUSphinx
Heres a list of Acoustic and Language Models
http://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/
The spanish one have 2812 downloads, the german one have 1683 downloads. Spanish is more popular, but not by much.
Here is a tutorial to create a new Acousting Language Model:
The recipe ask for this:
1 hour of recording for command and control for single speaker
5 hour of recordings of 200 speakers for command and control for many speakers
10 hours of recordings for single speaker dictation
50 hours of recordings of 200 speakers for many speakers dictation
The hard part seems getting 200 friends to read the random control text.
Heres is a paper of some dudes doing is for the spanish language
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.61.8971&rep=rep1&type=pdf
Never heard the word “Utterance” before :D
I am posting this for no reason whatsoever.
postdata:
Something funny that Microsoft don’t know: You can be in USA, and want to talk in german, or you can be in france, and talk in spanish, or in australia, and portuguesse. There are many countries where 50% of the gamers talk a different language than the default. Language != Country.