CPC H04R 1/1041 (2013.01) [G06F 18/22 (2023.01); G06F 21/32 (2013.01); G06V 40/10 (2022.01); H04R 1/1091 (2013.01); H04R 2460/15 (2013.01)] | 19 Claims |
1. A method for authenticating a user, the method comprising:
obtaining ear biometric data for a user to be authenticated, the ear biometric data comprising one or more features characteristic of the user's ear canal and an associated fit metric indicative of a positioning of a personal audio device relative to the user's ear canal, the personal audio device comprising a transducer for application of acoustic stimulus to the user's ear to obtain the ear biometric data;
determining the one or more features and the associated fit metric from the ear biometric data; and
identifying the user as a particular authorised user using both the determined one or more features and the determined associated fit metric;
wherein identifying the user as a particular authorised user based on the one or more features and the associated fit metric comprises:
determining a target user model set from a plurality of target user model sets based on the fit metric, each target user model set being associated with a particular fit metric of a set of fit metrics and comprising at least one target user model;
determining one or more target user similarity scores indicative of the similarity of the one or more features to a corresponding target user model of the determined target user model set;
determining a non-target user model set from a plurality of non-target user model sets based on the fit metric, each non-target user model set being associated with a particular fit metric of a set of fit metrics and comprising a plurality of non-target user models;
determining a plurality of non-target user similarity scores, each indicative of the similarity of the one or more features to a respective non-target user model of the plurality of the non-target user model of the determined target user model set; and
adjusting the one or more target user similarity scores based on the plurality of non-target user similarity scores.
|