| CPC G06Q 20/40145 (2013.01) [G06Q 20/38215 (2013.01); G06Q 20/3825 (2013.01); G06Q 20/3827 (2013.01)] | 17 Claims |
|
1. A system for enhanced authentication using voice modulation matching, the system comprising:
at least one non-transitory storage device; and
at least one processing device coupled to the at least one non-transitory storage device, wherein the at least one processing device is configured to:
electronically capture, via a first user input device, a digital audio stream of speech data of a first user;
electronically receive, via the first user input device, one or more identification credentials associated with the first user;
encode, using one or more encryption algorithms, the speech data to generate encoded speech data;
extract, using a feature extraction algorithm, one or more features associated with the encoded speech data associated with the first user;
query one or more data repositories using the encoded speech data;
in response, retrieve, from the one or more data repositories, encoded speech data associated with a second user that matches the encoded speech data of the first user, wherein retrieving further comprises:
extracting, using the feature extraction algorithm, one or more features associated with the encoded speech data associated with the second user;
comparing the one or more features associated with the encoded speech data associated with the first user with the one or more features associated with the encoded speech data associated with the second user, wherein comparing further comprises:
vectorizing the one or more features associated with the encoded speech data associated with the first user and the one or more features associated with the encoded speech data associated with the second user in a high dimensional feature space; and
determining, using a nearest neighbor algorithm, a similarity index between the one or more features associated with the encoded speech data associated with the first user and the one or more features associated with the encoded speech data associated with the second user in the high dimensional feature space;
determine that the first user has a familial relationship with the second user based on at least the one or more identification credentials and the similarity index;
generate an authentication token for the first user based on at least determining that the first user has a familial relationship with the second user; and
record the authentication token for the first user in a distributed ledger associated with the second user.
|