Identical conversation detection method and apparatus

• US 10,645,214 B1
• Filed: 07/24/2018
• Issued: 05/05/2020
• Est. Priority Date: 04/01/2014
• Status: Active Grant

• Current Assignee: Securus Technologies Incorporated (Securus Special Investments LLC)
• Original Assignee: Securus Technologies Incorporated (Securus Special Investments LLC)
• Inventors: Gainsboro, Jay, Weinstein, Lee
• Primary Examiner(s): Bezuayehu, Solomon G
• Application Number:
  US16/043,741
• Time in Patent Office: 651 Days
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04M 3/2281 Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656

Abstract

An automated system is disclosed for detecting situations in which identical segments of conversation appear within two different recordings. The system automatically detects where within each of two audio recordings an identical conversation segment begins and ends, thus enabling detection of conversations where multiple prison inmates participated in a conference call.

Claims

1. A method for detecting unauthorized communications by a first resident of a correctional facility, comprising:

embedding first identifying data within an audio signal generated by a first voice communication by the first resident utilizing a first communication device provided by the first correctional facility, wherein the first identifying data uniquely identifies the first correctional facility;

monitoring a second voice communication by a second resident utilizing a second communication device;

detecting the first identifying data within the audio signal of the second voice communication by the second resident;

generating a recording-point invariant data set of the audio signal of the second voice communication, wherein the recording-point invariant data set specifies the detected first identifying data that identifies the first correctional facility and further specifies times of the detected first identifying data within the data set; and

issuing a notification if the first identifying data is detected in the monitored second voice communication, wherein the notification indicates an unauthorized communication between the first resident and the second resident.

2. The method of claim 1, wherein the first identifying data is embedded within the audio signal by steganographically encoding the first identifying data in the audio signal.

3. The method of claim 1, wherein the first communication device is issued to the first resident by the first correctional facility.

4. The method of claim 2, wherein the second resident is a resident of a second correctional facility.

5. The method of claim 4, wherein the first identifying data further uniquely identifies the first communication device provided by the first correctional facility.

6. The method of claim 1, further comprising:

embedding second identifying data within the audio signal generated by the first voice communication, wherein the second identifying data uniquely identifies the communication device provided to the first resident by the first correctional facility.

7. The method of claim 6, further comprising:

detecting the second identifying data within the audio signal of a second voice communication by the second resident; and

augmenting the notification if the second identifying data is detected in the second voice communication, wherein the augmented notification indicates an unauthorized communication between the first resident and the second resident using the first communication device.

8. The method of claim 1, wherein the first resident and the second resident are residents of the same correctional facility.

9. A system for detecting unauthorized communications by a first resident of a correctional facility, the system comprising:

one or more processors; and

a memory device coupled to the one or more processors, the memory device storing computer-readable instructions that, upon execution by the one or more processors, cause the system to;

embed first identifying data within an audio signal generated by a first voice communication by the first resident utilizing a first communication device provided by the first correctional facility, wherein the first identifying data uniquely identifies the first correctional facility;

monitor a second voice communication by a second resident utilizing a second communication device;

detect the first identifying data within the audio signal of the second voice communication by the second resident;

generate a recording-point invariant data set of the audio signal of the second voice communication, wherein the recording-point invariant data set specifies the detected first identifying data that identifies the first correctional facility and further specifies times of the detected first identifying data within the data set; and

issue a notification if the first identifying data is detected in the monitored second voice communication, wherein the notification indicates an unauthorized communication between the first resident and the second resident.

10. The system of claim 9, wherein the first identifying data is embedded within the audio signal by steganographically encoding the first identifying data in the audio signal.

11. The system of claim 9, wherein the first communication device is issued to the first resident by the first correctional facility.

12. The system of claim 9, wherein the second resident is a resident of a second correctional facility.

13. The system of claim 12, wherein the first identifying data further uniquely identifies the first communication device provided by the first correctional facility.

14. The system of claim 9, the memory device storing additional computer-readable instructions that, upon execution by the one or more processors, further cause the system to:

embed second identifying data within the audio signal generated by the first voice communication, wherein the second identifying data uniquely identifies the communication device provided to the first resident by the first correctional facility.

15. The system of claim 14, the memory device storing additional computer-readable instructions that, upon execution by the one or more processors, further cause the system to:

detect the second identifying data within the audio signal of a second voice communication by the second resident; and

augmenting the notification if the second identifying data is detected in the second voice communication, wherein the augmented notification indicates an unauthorized communication between the first resident and the second resident using the first communication device.

16. The system of claim 9, wherein the first resident and the second resident are residents of the same correctional facility.