Mixture of experts for audio classification: an application to male female classification and musical genre recognition

Abstract : We report the experimental results obtained when applying a mixture of experts to the problem of audio classification for multimedia applications. The mixture of experts is based on multilayer perceptron neural networks as individual experts and piecewise Gaussian modeling was used for audio signal representation. Experimental results on two audio classification problems, male/female classification and musical genre recognition, show a clear improvement in using a mixture of experts in comparison to one individual expert