An acoustic fingerprint is a small summary of an audio signal. They are commonly created from songs and can be used to identify which song a short audio sample originated from.
A robust acoustic fingerprint algorithm must take into account the perceptual characteristics of the audio. If two files sound alike to the human ear, their acoustic fingerprints should match, even if their binary representations are quite different.
For my project I will investigate various acoustic fingerprinting techniques. I will also implement a small program that demonstrates creating a fingerprint from an audio file and matching segments of audio to a database of fingerprints.
The source for this project can be found on Github.