Fourier Transform in Song Classification

Shazam, a music recognition application, does several steps before being able to identify the title of the song a user has asked the program to recognize. It has to analyze the wave forms of the song and one of the methods they use for doing so is Fourier Transform. The following exerpt is an explanation on how it was actually used for the analysis,”The DFT is a mathematical methodology for performing Fourier analysis on a discrete (sampled) signal. It converts a finite list of equally spaced samples of a function into the list of coefficients of a finite combination of complex sinusoids, ordered by their frequencies, by considering if those sinusoids had been sampled at the same rate.”(Jovanovic, 2015). The analysis doesn’t end here but with the FFT analysis, a big part of the work has been done.

References:
https://www.toptal.com/algorithms/shazam-it-music-processing-fingerprinting-and-recognition
https://www.shazam.com/
https://www.quora.com/How-can-Fourier-transform-be-used-for-feature-selection-in-machine-learning#

Advertisements