Shazam Maps Millions of Songs Into Audio Fingerprints - WSJ

[Astoneroad]

This description copied directly from the YT post. "More than 23,000 songs are identified each minute by Shazam and the app has been used over 70 billion times. But while using it is simple, a complex computation makes it possible. Apple purchased the company in 2018, helping Shazam become one of the most popular free music apps in the App Store. But how does Shazam actually identify songs?"

<iframe width="560" height="315" src="

" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>

 

[Curvature]

The interesting thing about the algorithm is that it is designed to work in terrible conditions. The assumption is that the music signal will be buried in noise, i.e., negative SNR!