Selective security masking within recorded speech

• US 8,433,915 B2
• Filed: 06/28/2006
• Issued: 04/30/2013
• Est. Priority Date: 06/28/2006
• Status: Active Grant

• Current Assignee: Avaya LLC (Avaya Incorporated), Avaya Management L.P. (Avaya Incorporated)
• Original Assignee: Intellisist, Inc. dba Spoken Communications (Avaya Incorporated)
• Inventors: Doren, G. Kevin
• Primary Examiner(s): Truong, Thanhnga B
• Application Number:
  US11/477,899
• Publication Number:
  US 20080037719A1
• Time in Patent Office: 2,498 Days
• Field of Search: 726/26, 713/182, 713/183, 704/273, 705/51, 379/85, 379/88.04, 379/88.18, 379/93.02, 380/236, 380/237, 340/5.52
• US Class Current: 713/182
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/6263 during internet communication, e.g. revealing personal data from cookies
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656

Abstract

A marker is derived from an interaction between a person and an agent of a business and the agent'"'"'s user interface. A part of a speech signal that corresponds to a portion of the person'"'"'s special information is located with the marker. The speech signal results from the interaction between the person and the agent. The part of the speech signal that corresponds to the portion of the person'"'"'s special information is rendered unintelligible.

Claims

1. A method comprising:

identifying an activity performed in an area of a user interface during a voice recording of a verbal interaction comprising a speech signal, wherein the activity comprises motion of a pointing device associated with the area;

evaluating the motion of the pointing device by correlating the activity with at least a part of the speech signal that corresponds with special information and determining a correlation value for the special information;

applying a threshold to the correlation value and rendering the special information unintelligible when the correlation value satisfies the threshold; and

analyzing the voice recording to provide feedback to a business based on the interaction.

2. The method of claim 1, wherein the activity comprises entry of the special information into the area.

3. The method of claim 1, wherein the activity comprises making the area active.

4. The method of claim 3, wherein making the area active indicates a voice activated field for input of the special information.

5. The method of claim 1, wherein the activity comprises a keystroke associated with the area.

6. The method of claim 1, wherein the pointing device is located within the area.

7. The method of claim 1, wherein the feedback is in a form selected from the group consisting of print, audio, video, electronic, and multimedia.

8. A non-transitory computer readable medium containing executable computer program instructions, which when executed by a data processing system, cause the data processing system to perform a method comprising:

correlating first image data from a user interface with second image data from the user interface to detect activity within an area of the user interface during a verbal interaction comprising a speech signal;

correlating the activity in the user interface with at least a part of the speech signal that corresponds with special information and determining a correlation value for the special information; and

applying a threshold to the correlation value and rendering at least a portion of the special information unintelligible, wherein a guard band is utilized to identify an amount of the special information for rendering intelligible and a width of the guard band is determined based on the activity in the user interface.

9. The computer readable medium, as set forth in claim 8, wherein the data processing system further comprises assigning an identifier to the special information to identify the part of the speech signal comprising the special information for rendering unintelligible.

10. An apparatus comprising:

a user interface;

a system bus, the system bus is coupled to the user interface; and

a processor coupled to the system bus and programmed to;

identify an activity performed in an area of the user interface during a verbal interaction comprising a speech signal;

correlate the activity with at least a part of the speech signal that corresponds with special information, utilize a guard band to identify the part of the speech signal that corresponds with the person'"'"'s special information, and determine a correlation value for the special information; and

apply a threshold to the correlation value and render the special information unintelligible when the correlation value satisfies the threshold, wherein an identifier is assigned to the special information to identify the part of the speech signal comprising the special information for rendering unintelligible.

11. The apparatus of claim 10, wherein the speech signal is stored in an analog form.

12. The apparatus of claim 10, wherein the speech signal is stored in a digital form.

13. The apparatus of claim 10, wherein the unintelligible rendering of the special information is performed on a textual representation of the speech signal.

14. A system to protect special information during an interaction, comprising:

a communications device;

a communications network configured to provide communications between the communications device and a user interface;

a data processing system configured to;

identify an activity performed in an area of the user interface during a verbal interaction comprising a speech signal;

utilize a guard band to identify a part of the speech signal that corresponds with special information, correlate the activity with the part of the speech signal that corresponds with the special information, and determine a correlation value for the special information; and

apply a threshold to the correlation value and render the special information unintelligible when the correlation value satisfies the threshold; and

an identifier, which is assigned to the special information to identify the part of the speech signal comprising the special information for rendering unintelligible.

15. The system of claim 14, wherein the activity is entry of information into the area.

16. The system of claim 14, wherein the activity is pointing device activity.

17. The system of claim 14, wherein correlation of the activity includes evaluating motion of a pointing device or a keystroke sequence.

18. The system of claim 14, wherein the special information is selected from the group consisting of confidential information, sensitive information, and private information.

19. The system of claim 14, wherein the communication device is selected from the group consisting of a telephone, a cellular telephone, a computing device, and an Internet communications device.

20. The system of claim 14, wherein the user interface is controlled by a live person.

21. The system of claim 14, wherein the user interface includes an automated process.

22. The system of claim 14, wherein the speech signal is in a form of a voice recording.

23. The system of claim 14, wherein the speech signal is received as a data input apart from a voice recording.

24. The system of claim 23, wherein the data input is of a type selected from the group consisting of real-time, nearly real-time, and time delayed.