Uninformed Abnormal Event Detection on Audio

Konferenz: Sprachkommunikation - Beiträge zur 10. ITG-Fachtagung
26.09.2012 - 28.09.2012 in Braunschweig, Deutschland

Tagungsband: Sprachkommunikation

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Bardeli, Rolf; Stein, Daniel (Fraunhofer Institute for Intelligent Analysis and Information Systems, Schloss Birlinghoven, 53754 Sankt Augustin, Germany)

Although abnormal events in an audio stream are by their nature hard to define, a continuous monitoring of audio surveillance data can detect crucial information in, e.g., train engines that might require critical maintenance. Our method detects abnormal events without being trained on a certain situation, by building a model of the expected sound environment given a continuously adapting history of past audio material within a limited time interval. We evaluate the precision of this method on recordings from train rides.