Show simple item record

dc.contributor.authorΜπώκος, Γιώργος Δ.el_GR
dc.contributor.authorΠούλος, Μάριος Σ.el_GR
dc.contributor.authorΠαπαβλασόπουλος, Σώζωνel_GR
dc.contributor.authorΚανελλόπουλος, Νικόλαοςel_GR
dc.contributor.authorPoulos, Marios S.en
dc.contributor.authorPapavlasopoulos, Sozonen
dc.contributor.authorKanellopoulos, Nikolaosen
dc.contributor.authorBokos, George D.en
dc.descriptionΠεριέχει το πλήρες κείμενοel_GR
dc.description.abstractIn this paper we investigate the problem of classification between sports and news broadcasting. We detect and classify files that consist of speech and music or background noise (news broadcasting), and speech and a noisy background (sports broadcasting). More specifically, this study investigates feature extraction and training and classification proce- dures. We compare the Average Magnitude Difference Function (AMDF) method, which we consider more robust to background noise, with a novel proposed method. This method uses several spectral audio features which may be considered as specific semantic information. We base the extrac- tion of these features on the theory of computational geometry using an Onion Algorithm (OA). We tested the classification procedure as well as the learning ability of the two methods using a Learning Vector Quantizer One (LVQ1) neural network. The results of the experiment showed that the OA method has a faster learning procedure, which we characterise as an accurate feature extraction method for several audio cases.en
dc.sourceJournal of Graph Algorithms and Applications Volume 11, Issue 1, 2007, Pages 277-307en
dc.titleSpecific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposesen
dc.subject.JITAΘεωρητικές και γενικές πτυχές των βιβλιοθηκών και της πληροφόρησηςel_GR
dc.subject.JITATheoretical and general aspects of libraries and informationen

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record