| CPC G06F 21/32 (2013.01) [G06F 40/30 (2020.01); G10L 17/02 (2013.01); G10L 17/04 (2013.01); G10L 17/08 (2013.01); G10L 17/24 (2013.01)] | 24 Claims |

|
1. A non-transitory computer-readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:
receiving, from a user via a first communication channel corresponding to the user, authentication information for authenticating the user for access to a resource;
verifying the authentication information to successfully complete a first step of an authentication process;
responsive to successfully completing the first step of the authentication process, initiating a second step of the authentication process by:
selecting text comprising a plurality of words to be spoken by the user based at least on a distance value meeting a minimum difference, the distance value representing a difference between (a) a first feature vector corresponding to a first word of the plurality of words and (b) a second feature vector corresponding to a second word of the plurality of words, the first feature vector and the second feature vector corresponding to different pronunciations and/or spellings of the first word and second word, respectively; and
transmitting the text to be spoken by the user;
receiving, from the user, voice input that vocalizes the text transmitted to the user;
verifying the voice input to successfully complete the second step of the authentication process; and
responsive to successfully completing the second step of the authentication process, granting access to the resource.
|