I am developing a system which includes a speech comparison. This system will be used by people having a speech disorder. Practically I need to capture the user's speech and compare it with a another speech audio file and return a percentage match. I need to develop this in Java.
I started doing some research and found that this can be done using some sort of algorithm using FFT.
Is there any other algorithms which you may suggest in order to implement this comparison of capturing the user voice and comparing it with a pre recorded audio file and perform a real time audio processing.
I need some assistance from you guys in which is the best way to handle this and develop it with the best practice.
Many thanks for your time! Much appreciated