SPEECH - MUSIC
DISCRIMINATION DEMO
VERSION 1.0
INTRODUCTION Automatic
discrimination of speech and music in radio recordings is important
in many audio content characterization
applications. To this end, we have developed a speech / music discrimination
system that combines a Variable Duration Hidden Markov
Model (VDHMM) with a Bayesian Network and, at a
pre-processing step, employs a computationally efficient region growing technique (see "References") This demo version is provided only for educational purposes without any warranty. Your feedback will help us improve the system in future versions. Please note that we are not currently distributing the source code. Software Requirements Note: (Updated 1/9/2007) After the suggestion of some of the DEMO's users, we have uploaded an updated version, which saves the segmentation results in a .mat file for further usage. For more details read the documentation page.
|