Method and apparatus for validating agreement between textual and spoken representations of words

• US 7,346,151 B2
• Filed: 06/24/2003
• Issued: 03/18/2008
• Est. Priority Date: 06/24/2003
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Skiba, David, Matula, Valentine C., Erhart, George W.
• Primary Examiner(s): Gauthier; Gerald
• Application Number:
  US10/602,168
• Publication Number:
  US 20040264652A1
• Time in Patent Office: 1,729 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/88.04, 379/88.14, 379/88.13, 379/265.06, 379/265.07, 704/231, 704/235, 704/239, 704/240, 704/252, 704/254, 704/256, 704/270, 704/277
• US Class Current: 379/88.14
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A method and apparatus are disclosed for validating agreement between textual and spoken representations of words. A voice input verification process monitors a conversation between an agent and a caller to validate the textual entry of the caller'"'"'s spoken responses or the agent'"'"'s spoken delivery of a textual script (or both). The audio stream corresponding to the conversation between the agent and the caller is recorded and the textual information that is entered into the workstation by the agent is evaluated. Speech recognition technology is applied to the recent audio stream, to determine if the words that have been entered by the agent can be found in the recent audio stream. The grammar employed by the speech recognizer can be based, for example, on properties of the spoken words or the type of field being populated by the agent. If there is a discrepancy between what was entered by the agent and what was recently spoken by the caller, the agent can be alerted and the error can optionally be corrected.

Claims

1. A method for validating a textual entry of spoken words of a caller, comprising:

receiving a telephone call from said caller;

obtaining a textual entry of said spoken words from a call agent;

converting said spoken words to text using a speech recognition technique to generate converted text; and

comparing said textual entry to said converted text to confirm an accuracy of said textual entry substantially during said telephone call.

2. The method of claim 1, further comprising the step of recording said spoken words.

3. The method of claim 2, further comprising the step of time-stamping said recording.

4. The method of claim 1, further comprising the step of constraining said comparing step to a recent audio stream.

5. The method of claim 1, further comprising the step of constraining said comparing step to a recent audio stream corresponding to a completed field in a user interface.

6. The method of claim 1, further comprising the step of constraining said comparing step to a recent audio stream since a previous field was completed.

7. The method of claim 1, further comprising the step of notifying an agent of an error.

8. The method of claim 1, further comprising the step of correcting a detected error.

9. The method of claim 1, further comprising the step of suggesting at least one alternative for a detected error.

10. The method of claim 1, further comprising the step of selecting said speech recognition technique based on properties of said spoken words.

11. The method of claim 1, wherein said accuracy is confirmed by comparing a confidence score to a threshold value.

24. The method of claim 1, wherein said converting step employs a field specific speech grammar.

12. An apparatus for validating a textual entry of spoken words of a caller, comprising:

a memory; and

at least one processor, coupled to the memory, operative to;

receive a telephone call from said caller;

obtain a textual entry of said spoken words from a call agent;

convert said spoken words to text using a speech recognition technique to generate converted text; and

compare said textual entry to said converted text to confirm an accuracy of said textual entry substantially during said telephone call.

13. The apparatus of claim 12, wherein said processor is further configured to constrain said comparison to a recent audio stream.

14. The apparatus of claim 12, wherein said processor is further configured to notify an agent of an error.

15. The apparatus of claim 12, wherein said processor is further configured to correct a detected error.

16. The apparatus of claim 12, wherein said processor is further configured to suggest at least one alternative for a detected error.

17. The apparatus of claim 12, wherein said processor is further configured to select said speech recognition technique based on properties of said spoken words.

18. An article of manufacture for validating a textual entry of spoken words of a caller, comprising a machine readable medium containing one or more programs which when executed on a machine implement the steps of:

receiving a telephone call from said caller;

obtaining a textual entry of said spoken words from a call agent;

converting said spoken words to text using a speech recognition technique to generate converted text; and

comparing said textual entry to said converted text to confirm an accuracy of said textual entry substantially during said telephone call.

19. A method for validating a spoken delivery of a textual script, comprising:

obtaining a spoken delivery of said textual script by a call agent;

converting said spoken delivery to text using a speech recognition technique to generate converted text; and

comparing said textual script to said converted text to confirm an accuracy of said spoken delivery substantially during said spoken delivery of said textual script.

20. The method of claim 19, further comprising the step of constraining said comparing step to a recent audio stream.

21. The method of claim 19, further comprising the step of notifying an agent of an error.

22. The method of claim 19, further comprising the step of selecting said speech recognition technique based on properties of said textual script.

23. The method of claim 19, wherein said accuracy is confirmed by comparing a confidence score to a threshold value.

25. The method of claim 19, wherein said converting step employs a field specific speech grammar.