Computer-Implemented System And Method For Identifying And Masking Special Information Within Recorded Speech

• US 20130231936A1
• Filed: 04/26/2013
• Published: 09/05/2013
• 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
• Granted Patent: US 8,731,938 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• 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 computer-implemented system and method for identifying and masking special information within recorded speech is provided. A field for entry of special information is identified. Movement of a pointer device along a trajectory towards the field is also identified. A correlation of the pointer device movement and entry of the special information is determined based on a location of the trajectory in relation to the field. A threshold is applied to the correlation. The special information is received as verbal speech. A recording of the special information is rendered unintelligible when the threshold is satisfied.

Claims

1. A computer-implemented system for identifying and masking special information within recorded speech, comprising:

a field for entry of special information;

a movement module to identify movement of a pointer device along a trajectory towards the field;

a correlation module to determine a correlation of the pointer device movement and entry of the special information based on a location of the trajectory in relation to the field;

a threshold module to apply a threshold to the correlation;

a speech module to receive the special information as verbal speech; and

a masking module to render a recording of the special information unintelligible when the threshold is satisfied.

2. A system according to claim 1, further comprising:

a trajectory identification module to determine the trajectory, comprising;

at least two offset distances around the field;

a monitor to monitor the movement of the pointer device in relation to the offset distances;

the movement module to identify the movement of the pointer device around one of the offset distances further from the field at a first time and to identify the movement of the pointer device around one of the offset distances nearer to the field at a second time; and

a determination module to designate the movement of the pointer device with respect to the two offset distances as the trajectory.

3. A system according to claim 1, further comprising:

a location module to locate the unintelligible information in the recording, comprising;

a time determination module to determine a time at which the special information was provided as verbal speech;

a time identification module to identify the corresponding time in the recording; and

a designation module to designate speech signals of the recording at the corresponding time as containing the special information.

4. A system according to claim 1, further comprising:

an identifier module to associate an identifier within the recording as an indicator that special information is included.

5. A system according to claim 1, further comprising:

a speech receipt module to receive the verbalized special information from a caller during a call with an agent; and

a data receipt module to populate the field with the special information during the call based on instructions from the agent.

6. A system according to claim 1, wherein rendering the special information unintelligible comprises one or more of recording a masking signal over a segment of the recording in a location of the special information, recording the masking signal in place of the special information, and encrypting the segment of the recording corresponding to the special information.

7. A system according to claim 1, wherein the unintelligible special information is at least one of reversible or non-reversible.

8. A system according to claim 1, further comprising:

a window determination module to determine a window for the recording of the sensitive information based on a type of the sensitive information; and

the masking module to render a segment of the window corresponding to the sensitive information unintelligible.

9. A system according to claim 8, further comprising:

a marker placed within the recording at a time consistent with one or more of a beginning of the window and an end of the window.

10. A system according to claim 1, further comprising at least one of:

a distribution module to provide the recording with unintelligible information to a party that is unauthorized to access the special information.

11. A computer-implemented method for identifying and masking special information within recorded speech, comprising:

identifying a field for entry of special information;

identifying movement of a pointer device along a trajectory towards the field;

determining a correlation of the pointer device movement and entry of the special information based on a location of the trajectory in relation to the field;

applying a threshold to the correlation;

receiving the special information as verbal speech; and

rendering a recording of the special information unintelligible when the threshold is satisfied.

12. A method according to claim 11, further comprising:

determining the trajectory, comprising;

designating at least two offset distances around the field;

monitoring the movement of the pointer device in relation to the offset distances;

identifying the movement of the pointer device around one of the offset distances further from the field at a first time;

identifying the movement of the pointer device around one of the offset distances nearer to the field at a second time; and

designating the movement of the pointer device with respect to the two offset distances as the trajectory.

13. A method according to claim 11, further comprising:

locating the unintelligible information in the recording, comprising;

determining a time at which the special information was provided as verbal speech;

identifying the corresponding time in the recording; and

designating speech signals of the recording at the corresponding time as containing the special information.

14. A method according to claim 11, further comprising:

associating an identifier within the recording as an indicator that special information is included.

15. A method according to claim 11, further comprising:

receiving the verbalized special information from a caller during a call with an agent; and

populating the field with the special information received during the call based on instructions from the agent.

16. A method according to claim 11, wherein rendering the special information unintelligible comprises one or more of recording a masking signal over a segment of the recording in a location of the special information, recording the masking signal in place of the special information, and encrypting the segment of the recording corresponding to the special information.

17. A method according to claim 11, wherein the unintelligible special information is at least one of reversible or non-reversible.

18. A method according to claim 11, further comprising:

determining a window for the recording of the sensitive information based on a type of the sensitive information; and

rendering a segment of the window corresponding to the sensitive information unintelligible.

19. A method according to claim 18, further comprising:

placing a marker within the recording at a time consistent with one or more of a beginning of the window and an end of the window.

20. A method according to claim 11, further comprising at least one of:

providing the recording with unintelligible information to a party that is unauthorized to access the special information.