Automatic Classification and Indexing of Audio Broadcast Data

Abstract

Audio classification has been a focus area in the research of audio processing and pattern recognition. Automatic audio classification is very useful to audio indexing, content-based audio retrieval and online audio distribution, but the extraction of the most common and salient themes from unstructured raw audio data is a major challenge. The paper presents effective algorithms to automatically classify audio clips into one of the six classes: music, news, sports, advertisement, cartoon and movie. For these categories, a number of acoustic features that include linear predictive coefficients (LPC), linear predictive cepstral coefficients (LPCC) and Mel frequency cepstral coefficients (MFCC) are extracted to characterize the audio content. The auto associative neural network model (AANN) is used to capture the distribution of the acoustic feature vectors. The AANN model captures the distribution of the acoustic features of a class, and the back propagation learning algorithm is used to adjust the weights of the network to minimize the mean square error for each feature vector. This work also proposes an efficient audio indexing system which indexes movie clips using K-means clustering algorithm. Experimental results indicate that the proposed algorithms can produce satisfactory results.