I have just started to use MAX/MSP (one month ago) and I am working on a project that has to do with speech recognition and voice detection.
I am currently using the Dragon Dictate 2.5 but its to specific and trained on ones voice, but I needed to be more general... I have noticed that the embedded Dictation that comes with Mountain Lion is more opened to different voices, but the problem is that you always have to start it and then stop it in order to recognise your words.
Thus, I am interested to know if someone had written an external for that, or if someone knows and could guide me through the process to do that.
I don't know if the new Dragon Dictate should work better with different voices, anybody knows anything?
Thank you all in advance!