Authentication using active acoustic sensing

Abstract

Techniques and apparatuses are described that perform authentication using active acoustic sensing. During active acoustic sensing, a hearable transmits and receives at least one ultrasound signal, which propagates within a person's ear canal. The ultrasound signal contains information that is related to the vocalization as well as additional contextual information in how the person created the vocalization using their body and how the vocalization travels, via bone conduction, from the person's vocal chords to their ear canal. With active acoustic sensing, the hearable can generate an ultrasound-based voice signature based on the ultrasound signal and directly perform authentication based on the ultrasound-based voice signature. In some cases, authentication can be performed using a combination of the ultrasound-based voice signature and a voice signature. With active acoustic sensing, the hearable can realize a target spoof acceptance rate and a target false acceptance rate to provide a desired level of security.