I think Fast Fourier Transform (FFT) can be used for comparison. FFT is an algorithm for converting a time-domain signal into a frequency-domain representation of the relative amplitude of different frequency regions in the signal.
Steps you need to follow
Step 1: Load audio files – Read in two audio files into the workspace.
Step2: Truncate both signals so that their durations are equivalent.
Step 3: Perform FFT – Compute normalized energy spectral density (ESD) from DFT's two signals
Step 4: Compute mean-square-error (MSE)
– Compute mean-square-error (MSE) between normalized ESD's of two signals
– Two perfectly identical signals will obviously have MSE of zero.
