US 12,216,746 B2
Biometric authentication using voice accelerometer
Robert J. Littrell, Boston, MA (US); and Mathew Crowley, Boston, MA (US)
Assigned to QUALCOMM Technologies, Inc., San Diego, CA (US)
Filed by Qualcomm Technologies Inc., San Diego, CA (US)
Filed on Jun. 4, 2021, as Appl. No. 17/339,813.
Claims priority of provisional application 63/034,857, filed on Jun. 4, 2020.
Prior Publication US 2021/0382972 A1, Dec. 9, 2021
Int. Cl. H04L 29/06 (2006.01); G05B 19/042 (2006.01); G06F 21/32 (2013.01); G10L 17/04 (2013.01); G10L 17/06 (2013.01); G10L 17/22 (2013.01); H04R 17/02 (2006.01); H04R 19/04 (2006.01)
CPC G06F 21/32 (2013.01) [G05B 19/042 (2013.01); G10L 17/04 (2013.01); G10L 17/06 (2013.01); G10L 17/22 (2013.01); H04R 17/02 (2013.01); H04R 19/04 (2013.01); G05B 2219/24167 (2013.01); G06F 2221/2133 (2013.01); H04R 2201/003 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method performed by at least one processor for biometric authentication, comprising:
receiving, by the at least one processor, a first signal representing an output by a voice accelerometer of a device;
determining, by the at least one processor, that at least one feature of the first signal is greater than at least one feature threshold, wherein the at least one feature includes at least one of an amplitude of the first signal or an energy of the first signal;
determining, by the at least one processor, that the first signal is a live voice signal of a user of the device based on determining that the at least one feature of the first signal is greater than the at least one feature threshold;
receiving, by the at least one processor, a second signal representing an output by an acoustic transducer of the device;
performing, by the at least one processor, a first comparison of biometric characteristics of the first signal with stored voice accelerometer signal biometric characteristics for the user of the device;
performing, by the at least one processor, a second comparison of biometric characteristics of the second signal with stored acoustic signal biometric characteristics for the user of the device; and
authenticating, by the at least one processor, the user of the device based on determining that the first signal is the live voice signal of the user, based on the first comparison indicating the biometric characteristics of the first signal are within a threshold level of similarity to the stored voice accelerometer signal biometric characteristics for the user, and based on the second comparison indicating the biometric characteristics of the second signal are within the threshold level of similarity to the stored acoustic signal biometric characteristics for the user.