How do systems like Shazam and Midomi match low-quality samples of audio to actual songs? We set out to explore the existing solutions in this area, and try to implement one on a small scale ourselves. We began with a review of the existing literature in this area, and continued by implementing a beat-detection algorithm of our own design, and an actual mostly-working audio fingerprinting algorithm.
This work is licensed under a Creative Commons Attribution 3.0 United States License.