Computer-implemented system and method for identifying special information within a voice recording

• US 10,446,134 B2
• Filed: 01/29/2018
• Issued: 10/15/2019
• 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:
  US15/882,958
• Publication Number:
  US 20180151174A1
• Time in Patent Office: 624 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 within a voice recording is provided. Training to identify a speaker is performed. A voice recording including utterances by at least two speakers is processed to identify segments of the voice recording provided by the speaker. Remaining segments of the voice recording are designated as provided by another speaker. A text element that corresponds to a request for information is identified in at least one of the segments of the voice recording provided by the speaker. A predetermined duration associated with the identified text element is applied to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element. The utterances from the other speaker occurring within the predetermined duration are identified as special information and rendered unintelligible.

Claims

1. A computer-implemented system for identifying special information within a voice recording comprising:

a database to store voice recordings each comprising utterances by at least two speakers;

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

perform training to identify a regular speaker;

process one of the stored voice recordings based on the training and identify segments of the voice recording provided by the regular speaker;

designate the remaining segments of the voice recording as provided by another speaker;

identify a text element that corresponds to a request for special information in at least one of the segments of the voice recording provided by the regular speaker;

locate the identified text element on a stored list, wherein the text element is associated with a predetermined duration;

apply the predetermined duration associated with the identified text element to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element;

identify the utterances in the voice recording from the other speaker occurring within the voice recording during the predetermined duration as special information; and

render the special information unintelligible,

wherein the central processing unit transmits the voice recording with the special information rendered unintelligible to a recipient.

2. A system according to claim 1, wherein the central processing unit assigns an identifier to the voice recording, wherein the identifier provides one of special information is included in the voice recording or special information is not included in the voice recording.

3. A system according to claim 1, wherein the central processing unit places a marker over at least a portion of the segments provided by one of the speakers in the voice recording.

4. A system according to claim 3, wherein the marker comprises a tone that is above an audible range.

5. A system according to claim 1, wherein the special information is rendered unintelligible comprising one of recording a masking signal over the special information in the voice recording or encrypting the special information in the voice recording.

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

a display to display a translation of at least one of the utterances from the voice recording segments of the other speaker via a data field on the display.

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

controls comprising one or more of a delete function, an encrypt function, and a decrypt function for the displayed translation.

8. A system according to claim 1, wherein the central processing unit receives notice that too much of the voice recording is rendered unintelligible;

and a processing module to reprocess the voice recording by rendering smaller portions of the special information in the voice recording unintelligible.

9. A system according to claim 1, wherein the central processing unit renders the unintelligible special information intelligible.

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

performing training on a computer to identify a regular speaker;

processing by the computer a voice recording comprising utterances by at least two speakers based on the training and identifying segments of the voice recording provided by the regular speaker;

designating the remaining segments of the voice recording as provided by another speaker;

identifying a text element that corresponds to a request for special information in at least one of the segments of the voice recording provided by the regular speaker;

locating the identified text element on a stored list, wherein the text element is associated with a predetermined duration;

applying the predetermined duration associated with the identified text element to one of the segments of the voice recording of the other speaker occurring immediately after the segment of the voice recording from the regular speaker with the identified text element;

identifying the utterances from the other speaker occurring within voice recording during the predetermined duration as special information;

rendering the special information unintelligible; and

transmitting the voice recording with the special information rendered unintelligible to a recipient.

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

assigning an identifier to the voice recording, wherein the identifier provides one of special information is included in the voice recording or special information is not included in the voice recording.

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

placing a marker over at least a portion of the segments provided by one of the speakers in the voice recording.

13. A method according to claim 12, wherein the marker comprises a tone that is above an audible range.

14. A method according to claim 10, wherein the special information is rendered unintelligible, comprising at least one of:

recording a masking signal over the special information in the voice recording;

or

encrypting the special information in the voice recording.

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

displaying a translation of at least one of the utterances from the voice recording segments of the other speaker via a data field on a display.

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

providing controls comprising one or more of a delete function, an encrypt function, and a decrypt function for the displayed translation.

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

receiving notice that too much of the voice recording is rendered unintelligible; and

reprocessing the voice recording by rendering smaller portions of the special information in the voice recording unintelligible.

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

rendering the unintelligible special information intelligible.