An Analysis of Audio Fingerprint Complexity for Music Identification
Abstract:Music identification software has grown in popularity since the turn of the century, most notably with the release of Shazam and SoundHound. This technology is still incredibly relevant today, as Shazam was acquired by Apple in 2018. The general concept behind music identification is fairly straightforward: a user queries a huge database of encoded songs with a sample, and an algorithm finds and reports the closest match from the database. These popular software companies, however, provide fairly limited information regarding which algorithms are used. In this project, I assess various fingerprinting parameterizations over noisy data to determine how each parameter affects detection accuracy, and consider the tradeoff between complexity and noise resiliency for each parameter.