US 11,757,870 B1
Bi-directional voice authentication
Andrew J. Garner, IV, State Road, NC (US); Tyua Larsen Fraser, Livermore, CA (US); Kimberly Ann MacInnis, San Francisco, CA (US); Paul R. McMahon, Dayton, MN (US); Darrell Lee Suen, San Ramon, CA (US); and Zhong Wan, Pacifica, CA (US)
Assigned to Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Apr. 12, 2021, as Appl. No. 17/301,699.
Application 17/301,699 is a continuation of application No. 15/799,250, filed on Oct. 31, 2017, granted, now 10,979,423.
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); G10L 15/18 (2013.01); G10L 17/06 (2013.01); G10L 17/22 (2013.01)
CPC H04L 63/0861 (2013.01) [G10L 15/1815 (2013.01); G10L 15/1822 (2013.01); G10L 17/06 (2013.01); G10L 17/22 (2013.01); H04L 63/0853 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for bi-direction voice authentication comprising:
at least one processor; and
memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
receive an authentication request from a user;
determine that a device that transmitted the authentication request is located in a public place;
transmit an audio segment to the device with a request for confirmation of the audio segment and a request for a text-based response that includes a description of the audio segment from the user, the audio segment including audio content previously provided by the user;
receive the description of the audio segment from the device in the text-based response, wherein the description includes a unique sequence of words based on user-specific content of the audio segment;
compare the description to a profile description of the audio segment included in a profile stored for the user that includes the audio segment and the profile description, the profile description including a natural language description for the audio segment previously provided by the user;
upon receipt of the confirmation of the audio segment and a determination that the description matches the profile description, select an authentication token for the user;
transmit the authentication token to the device; and
authenticate requests for secure information using the authentication token for a duration of an interaction session between the user and the device.