Speech/Music Classification using SVM and GMM

Today, digital audio applications are part of our everyday lives. Automatic audio classification is very useful in audio indexing; content based audio retrieval and online audio distribution. The accuracy of the classification relies on the strength of the features and classification scheme. In this work both, time domain and frequency domain features are extracted from the input signal. Time domain features are Zero Crossing Rate (ZCR) and Short Time Energy (STE). Frequency domain features are spectral centroid, spectral flux, spectral entropy and spectral roll-off. After feature extraction, classification is carried out, using Support Vector Machine (SVM) and Gaussian Mixture Model (GMM). GMM is a classical technique taken as reference for comparing the performance of SVM in terms of accuracy and execution time. The proposed feature extraction and classification models results in better accuracy in speech/music classification. Keywords— Feature Extraction, Time domain features, Frequency domain features, Classification, Support Vector Machine, Gaussian Mixture Model.