Speech/Music Classification Using Occurrence Pattern of ZCR and STE

With the rapid growth in audio data volume, research in the area of content-based audio retrieval has gained impetus in the last decade. Audio classification serves as the fundamental step towards it. Accuracy in classifying data relies on the strength of the features and on the efficacy of classification scheme. In this work, we have focused on the features only. We have restricted ourselves further in the time domain based low level features. Zero crossing rate (ZCR) and shot time energy (STE) are the most widely used features in this category. We have tried to develop the features reflecting the quasi-periodic pattern of the signal by studying the occurrence pattern of ZCR and STE. Co-occurrence matrix for ZCR and STE are formed and features are computed from that to parameterize the signal. For classification, simple k-means clustering is followed and experimental result indicates that proposed features perform better than the traditional feature derived from ZCR and STE.