Is there an otoacoustic fingerprint?
Authors: Peter Knopp
Abstract:
This study examines the notion of fingerprint like properties of otoacoustic emissions (OAE) and their consequential biometric potential. To do this, transient-evoked otoacoustic emissions (TEOAE) of 10 subjects were recorded over a period of 7 days. A subset of these measurements was used to train an artificial neural network. The trained network was then used to identify the same subjects on the basis of a second subset of TEOAE measurements. All 10 subjects were identified with a 100 % success rate. This successful biometric application of TEOAE supports the idea of the otoacoustic fingerprint.