iOS Speech recognition - not to text, recognition by other records

Question

I know for speech recognition there are several questions but I have a little different question. My client wants to make recognition by another recording (previously saved). Lets say user saved recording where he says: "voice command" and then when he touches some microphone icon in app it starts listening and then it will compare with previous recording and says if it is the same command or not. I tried to change client mind and use some Speech to text library/project but he wants to do this way.

So I am asking is it possible and can you show me some free/opensource libraries?

Answer 1

To get yourself started: start by reading this https://developer.apple.com/library/ios/samplecode/SpeakHere/Introduction/Intro.html

and then go for this library: https://code.google.com/p/improved-mistral/

This is a matlab library that does exactly what you intend: you can make a possible duplicate for iOS based on this library: https://github.com/codyaray/speaker-recognition