EarEcho

Abstract

Smart wearable devices have recently become one of the major technological trends and been widely adopted by the general public. Wireless earphones, in particular, have seen a skyrocketing growth due to its great usability and convenience. With the goal of seeking a more unobtrusive wearable authentication method that the users can easily use and conveniently access, in this study we present EarEcho as a novel, affordable, user-friendly biometric authentication solution. EarEcho takes advantages of the unique physical and geometrical characteristics of human ear canal and assesses the content-free acoustic features of in-ear sound waves for user authentication in a wearable and mobile manner. We implemented the proposed EarEcho on a proof-of-concept prototype and tested it among 20 subjects under diverse application scenarios. We can achieve a recall of 94.19% and precision of 95.16% for one-time authentication, while a recall of 97.55% and precision of 97.57% for continuous authentication. EarEcho has demonstrated its stability over time and robustness to cope with the uncertainties on the varying background noises, body motions, and sound pressure levels.