SRSL 2009

From Openresearch
Jump to: navigation, search

Most of those use smnothieg called a Fourier Transform (usually a Fast Fourier Transform FFT) to get the primary frequencies of the sound, and detect beats, etc, which then it packages into a signature or fingerprint, which you can think of as kind of like a hash. It then compares that signature to its database, and picks the closest song.