I am new in digital signal processing. I have 2 audio (stereo / 2 channels) files that each audio file says "ba a ta" recorded by 2 different people. Example 2 audio files can be heard on this link and this link. I want to compare 2 audio files and want to get the score (only pitch score) based on this paper. There are so many terms in the paper that I still do not understand even though there is explained to get a pitch score and it is quite complex. My question is, how to get pitch score in detail (step by step) and what terms should I learn to get pitch score based on that paper?