Voice filter for normalizing an agent's emotional response

• US 7,003,462 B2
• Filed: 09/30/2004
• Issued: 02/21/2006
• Est. Priority Date: 07/13/2000
• Status: Expired due to Term

• Current Assignee: Rockwell Electronics Commerce Technologies LLC
• Original Assignee: Rockwell Electronics Commerce Technologies LLC
• Inventors: Shambaugh, Craig R., Dezonno, Anthony, Martin, Jim F., Power, Mark J., Hymel, Darryl, Williams, Laird C., Bluestein, Jared, Venner, Kenneth
• Primary Examiner(s): Azad, Abul K.
• Application Number:
  US10/955,880
• Publication Number:
  US 20050119893A1
• Time in Patent Office: 509 Days
• Field of Search: None
• US Class Current: 704/270
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 2021/0135 Voice conversion or morphing
• 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 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/51 Centralised call answering arrangements requiring operator intervention , e.g. call or contact centers for telemarketing

Abstract

A method and apparatus are provided for adjusting a content of an oral presentation provided by an agent of an organization and perceived by a human target of the organization based upon an objective of the organization. The method includes the steps of detecting a content of the oral presentation provided by the agent and modifying the oral presentation provided by the agent to produce the oral presentation perceived by the human target based upon the detected content and the organizational objective.

Claims

1. A method of adjusting a content of an oral presentation provided by an agent of an organization and perceived by a human target of the organization during a call between the agent and the human target based upon an objective of the organization, such method comprising the steps of:

selecting an objective of the organization for use during the call based upon a context of the call;

retrieving a predetermined set of call content parametric values based upon the determined objective of the call;

detecting a content of the oral presentation provided by the agent; and

modifying the oral presentation provided by the agent to avoid improper emotional or linguistic overtones based upon the predetermined set of call content parametric values to produce the oral presentation perceived by the human target based upon the detected content and the organizational objective wherein said agent and human target are different and said human target only hears the modified oral presentation and not the oral presentation of the agent.

2. The method of adjusting a content of an oral presentation as in claim 1 further comprising determining a set of organization objectives for controlling modification of the oral presentation to the target.

3. The method of adjusting a content of an oral presentation as in claim 2 wherein the step of determining the organization objective for the target further comprises retrieving call associated information relating to the target.

4. The method of adjusting a content of an oral presentation as in claim 1 wherein the step of detecting a content further comprises detecting an emotion content.

5. The method of adjusting a content of an oral presentation as in claim 4 wherein the step of detecting the emotional content of the oral presentation further comprises detecting a pitch of the oral presentation.

6. The method of adjusting a content of an oral presentation as in claim 1 wherein the step of detecting the content of the oral presentation further comprises recognizing a spoken word content.

7. The method of adjusting a content of an oral presentation as in claim 6 wherein the step of detecting a spoken word content of the oral presentation further comprises comparing the recognized spoken word content with a set of verbal templates.

8. The method of adjusting a content of an oral presentation as in claim 7 wherein the step of comparing the recognized spoken word content with a set of verbal templates further comprises selecting a template of the set of templates with a nearest match.

9. The method of adjusting a content of an oral presentation as in claim 8 further comprising determining an emotional state from indicia of emotional state stored with the matching template.

10. The method of adjusting a content of an oral presentation as in claim 7 wherein the step of comparing the recognized spoken word content with a set of verbal templates further comprises substituting a less objectionable word for at least a portion of the recognized spoken word content.

11. The method of adjusting a content of an oral presentation as in claim 7 wherein the step of comparing the recognized spoken word content with a set of verbal templates further comprises substituting an equivalent word of a different dialect for the recognized word content.

12. The method of adjusting a content of an oral presentation as in claim 1 wherein the step of modifying the detected content of the presentation further comprises adjusting a parameter of the presentation in small detail to alter a perception of an emotional state of a presenter of the presentation.

13. The method of adjusting a content of an oral presentation as in claim 12 wherein the step of adjusting the parameter of the presentation in small detail further comprises comparing an objective measure of contact results using the adjusted parameter with an objective measure of contact results using an unadjusted parameter.

14. An apparatus for adjusting a content of an oral presentation provided by an agent of an organization and perceived by a human target of the organization based upon an objective of the organization during a call between the agent and the human target, such apparatus comprising:

means for selecting an objective of the organization for use during the call based upon a context of the call;

means for retrieving a predetermined set of call content parametric values based upon the determined objective of the call;

means for detecting a content of the oral presentation provided by the agent; and

means for modifying the oral presentation provided by the agent on a word by word basis using the predetermined set of call content parametric values to avoid any improper emotional or linguistic overtones and to produce the oral presentation perceived by the human target based upon the detected content and the organizational objective wherein said agent and human target are different and said human target only hears the modified oral presentation and not the oral presentation of the agent.

15. The apparatus for adjusting a content of an oral presentation as in claim 14 further comprising means for determining the organization objective for controlling modification of the oral presentation to the target.

16. The apparatus for adjusting a content of an oral presentation as in claim 15 wherein the means for determining the organization objective for the target further comprises means for retrieving call associated information relating to the target.

17. The apparatus for adjusting a content of an oral presentation as in claim 14 wherein the means for detecting a content further comprises means for detecting an emotion content.

18. The apparatus for adjusting a content of an oral presentation as in claim 17 wherein the means for detecting the emotional content of the oral presentation further comprises means for detecting a pitch of the oral presentation.

19. The apparatus for adjusting a content of an oral presentation as in claim 14 wherein the means for detecting the content of the oral presentation further comprises means for recognizing a spoken word content.

20. The apparatus for adjusting a content of an oral presentation as in claim 19 wherein the means for detecting a spoken word content of the oral presentation further comprises means for comparing the recognized spoken word content with a set of verbal templates.

21. The apparatus for adjusting a content of an oral presentation as in claim 20 wherein the means for comparing the recognized spoken word content with a set of verbal templates further comprises means for selecting a template of the set of templates with a nearest match.

22. The apparatus for adjusting a content of an oral presentation as in claim 21 further comprising means for determining an emotional state from indicia of emotional state stored with the matching template.

23. The apparatus for adjusting a content of an oral presentation as in claim 20 wherein the means for comparing the recognized spoken word content with a set of verbal templates further comprises means for substituting a less objectionable word for at least a portion of the recognized spoken word content.

24. The apparatus for adjusting a content of an oral presentation as in claim 20 wherein the means for comparing the recognized spoken word content with a set of verbal templates further comprises means for substituting an equivalent word of a different dialect for the recognized word content.

25. The apparatus for adjusting a content of an oral presentation as in claim 14 wherein the means for modifying the detected content of the presentation further comprises means for adjusting a parameter of the presentation to alter a perception of an emotional state of a presenter of the presentation.

26. An apparatus for adjusting a content of an oral presentation provided by an agent of an organization and perceived by a human target of the organization based upon an objective of the organization during a call between the agent and the human target, such apparatus comprising:

a call processor adapted to select an organization objective based upon a context of the call;

a predetermined set of call content parametric values that are identified by the context and selected organizational objective of the call;

a speech processor adapted to detect a content of the oral presentation provided by the agent; and

a content processor adapted to modify the oral presentation provided by the agent based upon the predetermined set of call content parametric values to produce the oral presentation perceived by the human target based upon the detected content and the organizational objective wherein said agent and human target are different and said human target only hears the modified oral presentation and not the oral presentation of the agent.

27. The apparatus for adjusting a content of an oral presentation as in claim 26 further comprising call associated information that defines a context of the call.

28. The apparatus for adjusting a content of an oral presentation as in claim 27 wherein the call processor further comprises a memory adapted to contain call associated information relating to the target.

29. The apparatus for adjusting a content of an oral presentation as in claim 26 wherein the content processor further comprises a parametric comparator adapted to detect an emotion content.

30. The apparatus for adjusting a content of an oral presentation as in claim 26 wherein the means for parametric comparator further comprises a pitch comparator adapted to compare a detected pitch of the oral presentation with a threshold value associated with the organizational objective.

31. The apparatus for adjusting a content of an oral presentation as in claim 26 wherein the speech processor further comprises a word recognition processor adapted to recognize a spoken word content.

32. The apparatus for adjusting a content of an oral presentation as in claim 31 wherein the content processor further comprises a comparison processor adapted to compare the recognized spoken word content with a set of verbal templates.

33. The apparatus for adjusting a content of an oral presentation as in claim 32 wherein the comparison processor further comprises a selection processor adapted to select a template of the set of templates with a nearest match.