Methods and apparatus for identifying fraudulent callers

• US 9,837,079 B2
• Filed: 01/07/2015
• Issued: 12/05/2017
• Est. Priority Date: 11/09/2012
• Status: Active Grant

• Current Assignee: Mattersight Corporation (Nice Ltd)
• Original Assignee: Mattersight Corporation (Nice Ltd)
• Inventors: Warford, Roger, Brown, Douglas, Danson, Christopher, Gustafson, David
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US14/591,768
• Publication Number:
  US 20150154961A1
• Time in Patent Office: 1,063 Days
• Field of Search: 704246, 704239, 704210, 704233, 704244, 704201, 704236, 704247, 704273, 704250, 704231, 37911414, 370516, 700 94, 380236, 381312
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• 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 2025/783 based on threshold decision
• CPC Class Codes: G10L 25/27 characterised by the analysis technique
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10

Abstract

The methods, apparatus, and systems described herein are designed to identify fraudulent callers. A voice print of a call is created and compared to known voice prints to determine if it matches one or more of the known voice prints, and to transaction data associated with a database of voice prints. The methods include a pre-processing step to separate speech from non-speech, selecting a number of elements that affect the voice print the most, and/or computing an adjustment factor based on the scores of each received voice print against known voice prints.

Claims

1. An audible fraud detection system, comprising:

a node comprising a processor and a non-transitory computer readable medium operably coupled thereto, the non-transitory computer readable medium comprising a plurality of instructions stored therein that are accessible to, and executable by, the processor, wherein the plurality of instructions comprises;

instructions that, when executed, receive a telephonic communication from an unidentified caller via a network;

instructions that, when executed, separate a first portion of the communication into silent and non-silent segments;

instructions that, when executed, evaluate the non-silent segments to determine which portions are speech or non-speech;

instructions that, when executed, generate a plurality of parameters based on the evaluated non-silent segments that determine what is speech and non-speech;

instructions that, when executed, use the generated parameters to determine what is speech and non-speech for at least the remainder of the telephonic communication;

instructions, that when executed, create a voice print from the speech portions of the telephonic communication;

instructions, that when executed, compare the voice print to a Universal Background Model (UBM);

instructions, that when executed, select a number of audio elements of the UBM that characterize the voice print of the unidentified caller relative to other audio elements of the UBM;

instructions, that when executed, select audio elements of the voice print that correspond to the selected audio elements of the UBM; and

instructions, that when executed, compare the selected audio elements of the voice print to matching audio elements of a plurality of recorded voice prints from a plurality of fraudulent speakers to determine whether the voice print belongs to a fraudulent speaker.

2. The system of claim 1, wherein the first portion comprises a pre-selected time period.

3. The system of claim 1, wherein the plurality of parameters are generated for each communication received.

4. The system of claim 1, wherein the instructions that, when executed, evaluate the non-silent segments comprise instructions to group all non-speech sounds together.

5. A non-transitory computer readable medium comprising a plurality of instructions stored therein, the plurality of instructions comprising:

instructions that, when executed, receive a telephonic communication from an unidentified caller;

instructions that, when executed, separate a first portion at the beginning of the communication into silent and non-silent segments;

instructions that, when executed, evaluate the non-silent segments to determine which portions are speech and non-speech;

instructions that, when executed, generate a plurality of parameters based on the evaluated non-silent segments that determine what is speech and non-speech;

instructions that, when executed, use the generated parameters to determine what is speech and non-speech for at least the remainder of the telephonic communication;

instructions, that when executed, create a voice print from the speech portions of the telephonic communication;

instructions, that when executed, compare the voice print to a Universal Background Model (UBM);

instructions, that when executed, select a number of audio elements of the UBM that characterize the voice print of the unidentified caller relative to other audio elements of the UBM;

instructions, that when executed, select audio elements of the voice print that correspond to the selected audio elements of the UBM; and

instructions that, when executed, compare the selected audio elements of the voice print to matching audio elements of a voice print associated with a caller from a previous communication to determine whether the voice print belongs to a fraudulent speaker.

6. The non-transitory computer readable medium of claim 5, wherein the first portion comprises a pre-selected time period.

7. The non-transitory computer readable medium of claim 5, wherein the plurality of parameters are generated for each communication received.

8. The non-transitory computer readable medium of claim 5, wherein the instructions that, when executed, evaluate the non-silent segments, comprise instructions to group all non-speech together.

9. A method of detecting a fraudulent speaker comprising:

receiving a telephonic communication from an unidentified caller;

separating a first portion of the telephonic communication into silent and non-silent segments;

evaluating the non-silent segments to determine which portions thereof are speech or non-speech;

generating a plurality of parameters that determine what is speech and non-speech in the non-silent segments;

using the generated parameters to determine what is speech and non-speech for at least the remainder of the telephonic communication;

comparing the speech of the unidentified caller to a Universal Background Model (UBM);

selecting a number of audio elements of the UBM that most characterize the creation of a voice print of the unidentified caller relative to other audio elements of the UBM;

selecting audio elements of the voice print that correspond to the selected audio elements of the UBM;

comparing the selected audio elements of the voice print to matching audio elements of voice prints stored in a fraudster database;

determining if the voice print matches any of the voice prints in a customer database; and

adding the voice print to the customer database if the selected audio elements of the voice print did not match any voice print in the fraudster database.

10. The method of claim 9 wherein the number of selected audio elements of the UBM is from about 10 to 30.

11. The method of claim 9, which further comprises identifying the gender of the speaker in a voice print.

12. The method of claim 11, which further comprises accessing a library of voice prints for the identified gender.

13. The method of claim 9, wherein the voice prints in the fraudster database comprise voice prints of at least a plurality of fraudulent speakers.

14. The method of claim 13, wherein determining if the voice print matches any of the voice prints in the customer database comprises:

scoring a group of telephonic communications within a range of probabilities that a match exists; and

isolating communications with a score above a pre-selected match-probability threshold.

15. An audible fraud detection system, comprising:

a node comprising a processor and a non-transitory computer readable medium operably coupled thereto, the non-transitory computer readable medium comprising a plurality of instructions stored therein and being accessible to, and executable by, the processor, where the plurality of instructions comprises;

instructions that, when executed, receive a voice audio communication from a telephonic communication from an unidentified caller via a network;

instructions that, when executed, separate a first portion of the voice audio communication into silent and non-silent segments;

instructions that, when executed, evaluate the non-silent segments to determine which portions are speech or non-speech;

instructions that, when executed, generate a plurality of parameters based on the evaluated non-silent segments that determine what is speech and non-speech;

instructions that, when executed, use the generated parameters to determine what is speech and non-speech for at least the remainder of the voice audio communication;

instructions that, when executed, compare the speech of the unidentified caller to a Universal Background Model (UBM);

instructions that, when executed, select a number of audio elements of the background model that most characterize creation of a voice print of the unidentified caller relative to other audio elements of the background model to create a voice print from the voice audio communication;

instructions that, when executed, select audio elements of the voice print that correspond to the selected audio elements of the UBM;

instructions that, when executed, compare a plurality of the selected audio elements of the voice print to matching audio elements of one or more stored voice prints stored in a fraudster database;

instructions that, when executed, determine if the voice print matches any stored voice print in the fraudster database; and

instructions that, when executed, add the voice print to the customer database if the selected elements of the voice print did not match any voice print in the fraudster database.

16. The system of claim 15, wherein the number of selected audio elements of the UBM is from about 10 to 30.

17. The system of claim 15, further comprising instructions that, when executed, identify the gender of the voice print.

18. The system of claim 15, wherein the stored voice prints in the database comprise at least voice prints of a plurality of fraudulent speakers.

19. The system of claim 15, wherein the instructions that, when executed, determine if the voice print matches any of the stored voice prints in the customer database, comprise:

instructions to score a group of telephonic communications within a range or probabilities that a match exists; and

isolate communications with a score above a pre-selected match-probability threshold.