New techniques for preliminary analysis and tamper detection of audio evidence

The advances in the digital audio processing technology and the increasing number of audio applications have led to a need for novel approaches in audio forensics. The first one concerns on the search and organization of the audio evidence. Our primary application focus is the preliminary examination of large amount of audio evidence in a storage device by clustering them into speech and non-speech classes, thereby reducing the work load of a forensic expert. We introduced a new technique that can improve the state-of-the-art in audio content classification. Another area is about authentication of audio signals. Techniques developed towards this goal aim at detecting double compressed audio and identifying traces of commonly used audio effects to ultimately distinguish between unmodified and tampered audio signals.