System and method for generating challenge utterances for speaker verification
First Claim
1. A method comprising:
- receiving a username associated with an asserted identity from a user;
based on the username, accessing a user profile comprising voice characteristics;
identifying, using the voice characteristics, a plurality of asserted identity-specific more valuable phonemes determined to be more valuable than second phonemes for verifying the asserted identity;
generating a challenge sentence, based on the voice characteristics, wherein the challenge sentence is generated randomly according to one of a rule and a grammar, and wherein the challenge sentence comprises the plurality of asserted identity-specific more valuable phonemes;
prompting the user to speak the challenge sentence to yield a spoken challenge sentence;
comparing voice characteristics of the spoken challenge sentence to the voice characteristics of the user profile to yield an asserted identity voice score;
comparing the voice characteristics of the spoken challenge sentence with voice characteristics of a set of imposter identities to yield imposter identity voice scores; and
when the claimed identity voice score is within a threshold specific to the user profile, authenticating the user as the asserted identity.
3 Assignments
0 Petitions
Accused Products
Abstract
Disclosed herein are systems, methods, and non-transitory computer-readable storage media relating to speaker verification. In one aspect, a system receives a first user identity from a second user, and, based on the identity, accesses voice characteristics. The system randomly generates a challenge sentence according to a rule and/or grammar, based on the voice characteristics, and prompts the second user to speak the challenge sentence. The system verifies that the second user is the first user if the spoken challenge sentence matches the voice characteristics. In an enrollment aspect, the system constructs an enrollment phrase that covers a minimum threshold of unique speech sounds based on speaker-distinctive phonemes, phoneme clusters, and prosody. Then user utters the enrollment phrase and extracts voice characteristics for the user from the uttered enrollment phrase. The system generates a user profile, based on the voice characteristics, for generating random challenge sentences according to a grammar.
47 Citations
20 Claims
-
1. A method comprising:
-
receiving a username associated with an asserted identity from a user; based on the username, accessing a user profile comprising voice characteristics; identifying, using the voice characteristics, a plurality of asserted identity-specific more valuable phonemes determined to be more valuable than second phonemes for verifying the asserted identity; generating a challenge sentence, based on the voice characteristics, wherein the challenge sentence is generated randomly according to one of a rule and a grammar, and wherein the challenge sentence comprises the plurality of asserted identity-specific more valuable phonemes; prompting the user to speak the challenge sentence to yield a spoken challenge sentence; comparing voice characteristics of the spoken challenge sentence to the voice characteristics of the user profile to yield an asserted identity voice score; comparing the voice characteristics of the spoken challenge sentence with voice characteristics of a set of imposter identities to yield imposter identity voice scores; and when the claimed identity voice score is within a threshold specific to the user profile, authenticating the user as the asserted identity. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A system comprising:
-
a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising; receiving a username associated with an asserted identity from a user; based on the username, accessing a user profile comprising voice characteristics; identifying, using the voice characteristics, a plurality of asserted identity-specific more valuable phonemes determined to be more valuable than second phonemes for verifying the asserted identity; generating a challenge sentence, based on the voice characteristics, wherein the challenge sentence is generated randomly according to one of a rule and a grammar, and wherein the challenge sentence comprises the plurality of asserted identity-specific more valuable phonemes; prompting the user to speak the challenge sentence to yield a spoken challenge sentence; comparing voice characteristics of the spoken challenge sentence to the voice characteristics of the user profile to yield an asserted identity voice score; comparing the voice characteristics of the spoken challenge sentence with voice characteristics of a set of imposter identities to yield imposter identity voice scores; and when the asserted identity voice score is within a threshold specific to the user profile, authenticating the user as the asserted identity. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19)
-
-
20. A computer-readable storage device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
-
receiving a username associated with an asserted identity from a user; based on the username, accessing a user profile comprising voice characteristics; identifying, using the voice characteristics, a plurality of asserted identity-specific more valuable phonemes determined to be more valuable than second phonemes for verifying the asserted identity; generating a challenge sentence, based on the voice characteristics, wherein the challenge sentence is generated randomly according to one of a rule and a grammar, and wherein the challenge sentence comprises the plurality of asserted identity-specific more valuable phonemes; prompting the user to speak the challenge sentence to yield a spoken challenge sentence; comparing voice characteristics of the spoken challenge sentence to the voice characteristics of the user profile to yield an asserted identity voice score; comparing the voice characteristics of the spoken challenge sentence with voice characteristics of a set of imposter identities to yield imposter identity voice scores; and when the asserted identity voice score is within a threshold specific to the user profile, authenticating the user as the asserted identity.
-
Specification