Automatic Content based Classification of Speech Audio using Multiple Instance Learning

Audio content understanding is an active research problem in the area of speech analytics. A novel approach for content-based news audio classification using Multiple Instance Learning (MIL) approach is introduced in this paper. Content-based analysis provides useful information for audio classification as well as segmentation. A key step taken in this direction is to propose a classifier that can predict the category of the input audio sample. There are two types of features used for audio content detection, namely, Perceptual Linear Prediction (PLP) coefficients and Mel-Frequency Cepstral Coefficients (MFCC). Two MIL techniques viz. mi-Graph and mi-SVM are used for classification purpose. The results obtained using these methods are evaluated using different performance matrices. From the experimental results, it is marked that the MIL demonstrates excellent audio classification capability.