Speech/Music Classification Using Empirical Mode Decomposition

Audio classification serves as the fundamental step towards application like content based audio retrieval. In this work, we have tried to exploit the inherent difference in the composition of speech and music signal. A music signal has richer frequency component in comparison to speech signal. Energy distribution of speech and music signal also reflects a pattern that can be used to differentiate the two categories. With these observations, the signal is first decomposed using empirical mode decomposition method. For each decomposed signal, STE and ZCR based features are computed to provide a multiresolution description of the signal. The features thus obtained are used to classify the signals. Experimental result indicates that the performance of the proposed methodology is good enough.