Abstract

In this paper, we describe automatic segmentation methods for audio broadcast data. Today, digital audio applications are part of our everyday lives. Since there are more and more digital audio databases in place these days, the importance of effective management for audio databases have become prominent. Broadcast audio data is recorded from the Television which comprises of various categories of audio signals. Efficient algorithms for segmenting the audio broadcast data into predefined categories are proposed. Audio features namely Linear prediction coefficients (LPC), Linear prediction cepstral coefficients, and Mel frequency cepstral coefficients (MFCC) are extracted to characterize the audio data. Auto Associative Neural Networks are used to segment the audio data into predefined categories using the extracted features. Experimental results indicate that the proposed algorithms can produce satisfactory results.