Recording infrastructure having biometrics engine and analytics service

• US 9,237,232 B1
• Filed: 03/14/2014
• Issued: 01/12/2016
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Williams, Jamie Richard, Barnes, Robert John, Linsdell, Ian, Bluman, Scott M.
• Primary Examiner(s): King, Simon
• Application Number:
  US14/213,507
• Time in Patent Office: 669 Days
• Field of Search: 379/88.02, 704/247
• US Class Current: 1/1
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/551 Call history recording a computer conference H04L12/1831
• CPC Class Codes: H04M 2203/6045 Identity confirmation
• CPC Class Codes: H04M 2203/6054 Biometric subscriber identification
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends

Abstract

Systems and methods for analyzing digital recordings of the human voice in order to find characteristics unique to an individual. A biometrics engine may use an analytics service in a contact center to supply audio streams based on configured rules and providers for biometric detection. The analytics service may provide call audio data and attributes to connected engines based on a provider-set of selection rules. The connected providers send call audio data and attributes through the analytics service. The engines are notified when a new call is available for processing and can then retrieve chunks of audio data and call attributes by polling an analytics service interface. A mathematical model of the human vocal tract in the call audio data is created and/or matched against existing models. The result is analogous to a fingerprint, i.e., a pattern unique to an individual to within some level of probability.

Claims

1. A method for providing a biometrics engine that is associated with a contact center, comprising:

receiving audio calls at the contact center;

processing the audio calls to derive a mathematical model of a vocal tract that is associated with a predetermined caller;

storing the mathematical model in a person database;

receiving call attributes associated with the audio calls;

comparing, in accordance with the call attributes, the mathematical model to a subsequent audio call that includes the predetermined caller; and

analyzing the patterns of resonant frequencies produced as a result of the shape of the vocal tract, during both consonantal sounds and vowel sounds.

2. The method of claim 1, further comprising storing information regarding a number of audio calls used to create the mathematical model.

3. The method of claim 1, further comprising determining an identity of a caller associated with audio call.

4. The method of claim 3, determining whether the caller associated with the audio call is blacklisted.

5. The method of claim 3, further comprising tagging audio calls in accordance with information derived by an analytics service.

6. The method of claim 1, further comprising performing the comparing in real-time during an on-going audio call.

7. The method of claim 1, further comprising comparing audio from an audio call with the mathematical model stored in the database that was created a predetermined period of time prior to the audio call.

8. The method of claim 1, further comprising generating an alert as a result of the comparing.

9. The method of claim 8, wherein the alert is indicative of a fraudster associated with an audio call.

10. A method for providing a biometrics engine that is associated with a contact center, comprising:

receiving audio calls at the contact center;

processing the audio calls to derive a mathematical model of a vocal tract that is associated with a predetermined caller;

storing the mathematical model in a person database;

receiving call attributes associated with the audio calls;

comparing, in accordance with the call attributes, the mathematical model to a subsequent audio call that includes the predetermined caller;

determining if a caller associated with an audio call is known by matching a model stored in the person database with Previously Presented audio from the audio call; and

creating a Previously Presented model if the caller is not known.

11. A method for providing a biometrics engine that is associated with a contact center, comprising:

receiving audio calls at the contact center;

processing the audio calls to derive a mathematical model of a vocal tract that is associated with a predetermined caller;

storing the mathematical model in a person database;

receiving call attributes associated with the audio calls;

comparing, in accordance with the call attributes, the mathematical model to a subsequent audio call that includes the predetermined caller

further comprising determining if a caller associated with an audio call is known by matching a model stored in the person database with Previously Presented audio from the audio call; and

enhancing a quality of the mathematical model if the caller is known.

12. A method for providing a biometrics engine that is associated with a contact center, comprising:

receiving audio calls at the contact center;

processing the audio calls to derive a mathematical model of a vocal tract that is associated with a predetermined caller;

storing the mathematical model in a person database; and

receiving call attributes associated with the audio calls; and

comparing, in accordance with the call attributes, the mathematical model to a subsequent audio call that includes the predetermined caller, the comparing using resonant frequencies identified within the audio calls.