I want to implement a system that receives speech through a microphone on my Mac OS x. I know arbitrary speech recognition is close to impossible without training the system so I'm willing to restrict it to 10 simple sentences. It must recognize with a high degree of accuracy which of these 10 sentences are being spoken, generate the text and add an entry to a remote MySQL database.
With these being the architecture of the system I want to implement, could anyone give me an overview of what would be the best way to go about implementing this system? I'm looking for ideas like open source libraries to minimize the coding as this is just a prototype application for a demonstration. Basically I'm looking for a quick and easy solution. Thanks!