Utilizing Voice Biometrics

Patent metadata

Field	Value
Publication number	US-2016125884-A1
Application number	US-201614992344-A
Country	US
Kind code	A1
Filing date	Jan 11, 2016
Priority date	Jun 20, 2013
Publication date	May 5, 2016
Grant date	—

Abstract

Methods, systems, computer-readable media, and apparatuses for utilizing voice biometrics to prevent unauthorized access are presented. In some embodiments, a computing device may receive a voice sample. Subsequently, the computing device may determine a voice biometric confidence score based on the voice sample. The computing device then may evaluate the voice biometric confidence score in combination with one or more other factors to identify an attempt to access an account without authorization.

First claim

1 .- 21 . (canceled)

22 . A system, comprising:
at least one processor; and memory storing computer readable instructions that, when executed by the at least one processor, cause the system to:
receive a first voice sample associated with a first channel;
determine a first voice biometric confidence score based on the first voice sample;
evaluate the first voice biometric confidence score in combination with one or more other factors to identify a first attempt to access a first account without authorization, the first account being maintained by a financial institution;
determine that the first voice sample is associated with an actual attempt to access the first account without authorization based on evaluating the first voice biometric confidence score in combination with the one or more other factors;
based on determining that the first voice sample is associated with the actual attempt to access the first account without authorization, lock the first account to prevent one or more transactions from being performed on the first account until the first account is unlocked by at least one legitimate user of the first account;
receive a second voice sample associated with a second channel, the second voice sample being different from the first voice sample, and the second channel being different from the first channel;
determine a second voice biometric confidence score based on the second voice sample; and
evaluate the second voice biometric confidence score in combination with the one or more other factors to identify a second attempt to access a second account without authorization, the second account being maintained by the financial institution,
wherein the first channel is a first product channel of the financial institution, and the second channel is a second product channel of the financial institution, wherein evaluating the first voice biometric confidence score in combination with the one or more other factors comprises assigning a weight to the first voice biometric confidence score and assigning one or more additional weights to the one or more other factors, wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the system to dynamically adjust one or more of the weights based on call metrics, and wherein the first voice sample is captured by a mobile banking application executed on a mobile device, the mobile banking application being configured to allow a user of the mobile device to view one or more account balances, deposit one or more checks, and transfer funds associated with one or more financial accounts.

23 . The system of claim 22 , wherein the second voice sample is received via a telephonic channel of the financial institution, and the first voice sample is received via a mobile application channel of the financial institution.

24 . The system of claim 22 , wherein the one or more other factors include one or more of phone type, phone number authenticity, call origin, phone number history, or call purpose.

25 . The system of claim 22 , wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the system to:
based on determining that the first voice sample is associated with the actual attempt to access the first account without authorization, analyze the first voice sample and store analysis results in a database of suspicious voiceprints.

26 . The system of claim 22 , wherein the memory stores additional computer readable instructions that, when executed by the at least one processor, cause the system to:
based on determining that the first voice sample is associated with the actual attempt to access the first account without authorization, inform a customer service representative of the financial institution that a person associated with the first voice sample is attempting to access the first account without authorization by presenting a notification to the customer service representative of the financial institution via at least one user interface.

27 . The system of claim 22 , wherein the first channel is associated with a first contact center of a card services department of the financial institution, and the second channel is associated with a second contact center of a mortgage services department of the financial institution.

28 . The system of claim 22 , wherein the second voice sample is captured by an automated teller machine (ATM) prompting a user to speak a certain phrase.

29 . The system of claim 22 , wherein the second voice sample is captured by an interactive voice response (IVR) system prompting a caller to speak a certain phrase.

30 . The system of claim 22 , wherein locking the first account to prevent the one or more transactions from being performed on the first account comprises locking the mobile banking application executed on the mobile device until the first account is unlocked by the at least one legitimate user of the first account.

31 . A method, comprising:
at a computer system comprising at least one processor and memory storing computer readable instructions:
receiving, by the at least one processor, a first voice sample associated with a first channel;
determining, by the at least one processor, a first voice biometric confidence score based on the first voice sample;
evaluating, by the at least one processor, the first voice biometric confidence score in combination with one or more other factors to identify a first attempt to access a first account without authorization, the first account being maintained by a financial institution;
determining, by the at least one processor, that the first voice sample is associated with an actual attempt to access the first account without authorization based on evaluating the first voice biometric confidence score in combination with the one or more other factors;
based on determining that the first voice sample is associated with the actual attempt to access the first account without authorization, locking, by the at least one processor, the first account to prevent one or more transactions from being performed on the first account until the first account is unlocked by at least one legitimate user of the first account;
receiving, by the at least one processor, a second voice sample associated with a second channel, the second voice sample being different from the first voice sample, and the second channel being different from the first channel;
determining, by the at least one processor, a second voice biometric confidence score based on the second voice sample; and
evaluating, by the at least one processor, the second voice biometric confidence score in combination with the one or more other factors to identify a second attempt to access a second account without authorization, the second account being maintained by the financial institution,
wherein the first channel is a first product channel of the financial institution, and the second channel is a second product channel of the financial institution, wherein evaluating the first voice biometric confidence score in combination with the one or more other factors comprises assigning a weight to the first voice biometric confidence score and assigning one or more additional weights to the one or more other factors, wherein the method comprises dynamically adjusting, by the at least one processor, one or more of the weights based on call metrics, and wherein the first voice sample is captured by a mobile banking application executed on a mobile device, the mobile banking application being configured to allow a user of the mobile device to view one or more account balances, deposit

Assignees

• Bank Of America

Inventors

• Timem Joseph
• Perry Donald
• Rosenberger Jenny
• Karpey David

Classifications

• H04L63/102

  Entity profiles · CPC title

• H04L63/0861

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• G10L17/22 Primary

  Interactive procedures; Man-machine interfaces · CPC title

• G06Q20/40145

  Biometric identity checks · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title