II-Avida - A Personalized Interactive Audio and Video Portal

Gerhard Paass, Jörg Kindermann, and Edda Leopold

We describe a system for enregistering, storing and distributing multimedia data streams. For each modality -- audio, speech, video -- characteristic features are extracted and used to classify the content into a range of topic categories. Using data mining techniques classifier models are determined from training data. These models are able to assign existing and new multimedia documents to one or several topic categories. We describe the features used as inputs for these classifiers. We demonstrate that the classification of audio material may be improved by using phonemes and syllables instead of words. Finally we show that the categorization performance mainly depends on the quality of speech recognition and that the simple video features we tested are of only marginal utility.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.