System and method for identifying special information

• US 9,881,604 B2
• Filed: 02/09/2015
• Issued: 01/30/2018
• Est. Priority Date: 07/13/2005
• 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: Lee, Howard M., Lutz, Steven, Odinak, Gilad
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US14/617,823
• Publication Number:
  US 20150302849A1
• Time in Patent Office: 1,086 Days
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• 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: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: H04L 2209/04 Masking or blinding
• CPC Class Codes: H04L 2209/56 Financial cryptography, e.g. electronic payment or e-cash
• CPC Class Codes: H04L 9/3231 Biological data, e.g. fingerprint, voice or retina network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861

Abstract

A system and method for identifying special information is provided. Endpoints are defined within a voice recording. One or more of the endpoints are identified within the voice recording and the voice recording is partitioned into segments based on the identified endpoints. Elements of text are identified by applying speech recognition to each of the segments and a list of prompt list candidates are applied to the text elements. The segments with text elements that match one or more prompt list candidates are identified. Portions of the voice recording following the prompt list candidates that include special information are identified and the special information is rendered unintelligible within the voice recording.

Claims

1. A computer-implemented system for identifying special information comprising:

a database storing a voice recording;

a data processing system comprising memory, an input/output interface, and a central processing unit, wherein the central processing unit is configured to;

define endpoints within the voice recording, identify one or more of the endpoints within the voice recording, and partition the voice recording into segments based on the identified endpoints;

identify elements of text in each of the segments using automatic speech recognition;

apply a list of prompt list elements to the text elements, wherein the prompt list elements each identify a prompt for special information;

identify the segments with text elements that match one or more prompt list elements from the applied list;

for each text element that matches one of the prompt list elements, determine a predetermined duration of the voice recording following that prompt list element, wherein the predetermined duration is dependent on a type of special information associated with that prompt list element; and

identifying the special information within the predetermined duration of the voice recording; and

a masking module to render unintelligible on a special purpose digital recorder the special information within the voice recording; and

a delivery module to provide the voice recording to a third party with the identified special information rendered unintelligible.

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

a special information determination module to determine the special information by estimating an appropriate amount of time necessary for an utterance of the special information.

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

a special information determination module to determine the special information using speech recognition.

4. A system according to claim 1, wherein the endpoints are defined as pauses in the voice recording.

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

an assignment module to assign a confidence score to the identified special information.

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

a threshold module to apply a threshold value to the confidence score of the special information; and

the masking module to render the special information unintelligible when the confidence score exceeds the threshold.

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

an identifier module to associate an identifier with the special information.

8. A system according to claim 7, wherein the identifier identifies that the special information is included in the voice recording or that the special information is not included in the voice recording.

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

a request module to receive a request for the special information and to access the unintelligible special information;

a reverse rendering module to reverse the rendering of the special information as unintelligible; and

a display to display the special information.

10. A computer-implemented method for identifying special information comprising:

maintaining a voice recording in a database;

defining endpoints within the voice recording via a data processing system comprising a central processing unit;

identifying via the central processing unit one or more of the endpoints within the voice recording and partitioning the voice recording into segments based on the identified endpoints;

identifying elements of text using automatic speech recognition;

applying via the central processing unit a list of prompt list elements to the text elements, wherein the prompt list elements each identify a prompt for special information;

identifying the segments with text elements that match one or more prompt list elements from the applied list;

for each text element that matches one of the prompt list elements, determining a predetermined duration of the voice recording following that prompt list element based on a type of special information associated with that prompt list element;

rendering unintelligible on a special purpose digital recorder the special information within the voice recording via the central processing unit; and

providing the voice recording to a third party with the identified special information rendered unintelligible.

11. A method according to claim 10, further comprising:

determining the special information by estimating an appropriate amount of time necessary for an utterance of the special information.

12. A method according to claim 10, further comprising:

determining the special information using speech recognition.

13. A method according to claim 10, wherein the endpoints are defined as pauses in the voice recording.

14. A method according to claim 10, further comprising:

assigning a confidence score to the identified special information.

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

applying a threshold value to the confidence score of the special information; and

rendering the special information unintelligible when the confidence score exceeds the threshold.

16. A method according to claim 10, further comprising:

associating an identifier with the special information.

17. A method according to claim 16, wherein the identifier identifies that the special information is included in the voice recording or that the special information is not included in the voice recording.

18. A method according to claim 10, further comprising:

determining a predetermined duration of the voice recording following that prompt list element based on a type of special information associated with that prompt list candidate for each text element that matches one of the prompt list elements;

receiving a request for the special information and accessing the unintelligible special information;

reversing the rendering of the special information as unintelligible; and

displaying the special information.