Privacy-enhanced perceptual hashing of audio data

Audio hashes are compact and robust representations of audio data and allow the efficient identification of specific recordings and their transformations. Audio hashing for music identification is well established and similar algorithms can also be used for speech data. A possible application is the identification of replayed telephone spam. This contribution investigates the security and privacy issues of perceptual hashes and follows an information-theoretic approach. The entropy of the hash should be large enough to prevent the exposure of audio content. We propose a privacy-enhanced randomized audio hash and analyze its entropy as well as its robustness and discrimination power over a large number of hashes.