PROJECT TITLE :

Speech/Music Discrimination For Analysis Of Radio Stations - 2017

ABSTRACT:

A computationally economical feature, referred to as Minimum Energy Density (MED) was applied to discriminate audio signals between speech and music in the radio stations programs. The presented binary classifier is based on testing 2 options: energy distribution and differences between energy in channels. We analyzed 240 hours of signals, from ten Polish radio stations. Our analysis permits us to supply info concerning content of particular radio stations.