System and method for tracking fraudulent electronic transactions using voiceprints of uncommon words
View Patent ↗Disclosed are systems, methods, and computer readable media for comparing customer voice prints comprising of uncommonly spoken words with a database of known fraudulent voice signatures and continually updating the database to decrease the risk of identity theft. The method embodiment comprises comparing a received voice signal against a database of known fraudulent voice signatures, denying the caller's transaction if the voice signal substantially matches the database of known fraudulent voice signatures, adding the caller's voice signal to the database of known fraudulent voice signatures if the voice signal does not substantially match a separate speaker verification database and received additional information is not verified.
1. A method comprising:
comparing a first voice signal associated with a user against a database of known fraudulent voice signatures, wherein the first voice signal corresponds to word patterns used previously by people engaged in fraud securing a transaction of a credit card;
identifying the first voice signal as fraudulent when the first voice signal substantially matches an entry in the database of known fraudulent voice signatures;
comparing a second voice signal against a speaker verification database of voice signals associated with the credit card when the first voice signal is not identified as fraudulent, wherein the second voice signal comprises an uncommonly spoken word;
requesting a third voice signal containing personal information for the user associated with the first voice signal and associated with the credit card when the first voice signal does not substantially match an entry in the speaker verification database for the user; and
adding the first voice signal to the database of known fraudulent voice signatures when the personal information cannot be verified.
2. The method of claim 1 , further comprising:
employing a sliding threshold scale of confidence in query results obtained from the speaker verification database based on a confidence level of query results obtained from the database of known fraudulent voice signatures.
3. The method of claim 2 , wherein the personal information for the user associated with the first voice signal and associated with the credit card comprises a personal identification number and a card security code.
4. The method of claim 1 , further comprising:
performing a transaction when the first voice signal substantially matches the speaker verification database and the personal information is verified.
5. The method of claim 1 , further comprising:
denying further user action when the personal information is not verified.
6. The method of claim 1 , wherein the personal information for the user associated with the first voice signal and associated with the credit card comprises one of a personal identification number, a billing address, and a card security code.
7. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
comparing a first voice signal associated with a user against a database of known fraudulent voice signatures, wherein the first voice signal corresponds to word patterns used previously by people engaged in fraud securing a transaction of a credit card;
identifying the first voice signal as fraudulent when the first voice signal substantially matches an entry in the database of known fraudulent voice signatures;
comparing a second voice signal against a speaker verification database of voice signals associated with the credit card when the first voice signal is not identified as fraudulent, wherein the second voice signal comprises an uncommonly spoken word;
requesting a third voice signal containing personal information for the user associated with the first voice signal and associated with the credit card when the first voice signal does not substantially match an entry in the speaker verification database for the user; and
adding the first voice signal to the database of known fraudulent voice signatures when the personal information cannot be verified.
8. The system of claim 7 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
performing a transaction when the first voice signal substantially matches the speaker verification database and the personal information is verified.
9. The system of claim 7 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
denying further user action when the personal information is not verified.
10. The system of claim 7 , the computer-readable storage medium having additional instructions stored which result in the operations further comprising:
employing a sliding threshold scale of confidence in query results obtained from the speaker verification database based on a confidence level of query results obtained from the database of known fraudulent voice signatures.
11. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
comparing a first voice signal associated with a user against a database of known fraudulent voice signatures, wherein the first voice signal corresponds to word patterns used previously by people engaged in fraud securing a transaction of a credit card;
identifying the first voice signal as fraudulent when the first voice signal substantially matches an entry in the database of known fraudulent voice signatures;
comparing a second voice signal against a speaker verification database of voice signals associated with the credit card when the first voice signal is not identified as fraudulent, wherein the second voice signal comprises an uncommonly spoken word;
requesting a third voice signal containing personal information for the user associated with the first voice signal and associated with the credit card when the first voice signal does not substantially match an entry in the speaker verification database for the user; and
adding the first voice signal to the database of known fraudulent voice signatures when the personal information cannot be verified.
12. The computer readable storage device of claim 11 , the computer-readable storage device having additional instructions stored which result in the operations further comprising:
performing a transaction when the voice signal substantially matches the speaker verification database and the personal information is verified.
13. The computer readable storage device of claim 11 , the computer-readable storage device having additional instructions stored which result in the operations further comprising:
denying further user action when the personal information is not verified.
14. The computer readable storage device of claim 11 , the computer-readable storage device having additional instructions stored which result in the operations further comprising:
employing a sliding threshold scale of confidence in query results obtained from the speaker verification database based on a confidence level of query results obtained from the database of known fraudulent voice signatures.