Multi-party conversation analyzer and logger

• US 9,300,790 B2
• Filed: 06/26/2006
• Issued: 03/29/2016
• Est. Priority Date: 06/24/2005
• Status: Active Grant

• Current Assignee: Securus Technologies Incorporated (Securus Special Investments LLC)
• Original Assignee: Securus Technologies Incorporated (Securus Special Investments LLC)
• Inventors: Gainsboro, Jay Loring, Weinstein, Lee Davis
• Primary Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US11/475,541
• Publication Number:
  US 20070071206A1
• Time in Patent Office: 3,564 Days
• Field of Search: 37914204-14206, 379 8801- 8819
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 21/12 by displaying time domain information
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04M 2201/41 using speaker recognition
• 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
• CPC Class Codes: H04M 3/568 audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30

Abstract

A multi-party conversation analyzer and logger uses a variety of techniques including spectrographic voice analysis, absolute loudness measurements, directional microphones, and telephonic directional separation to determine the number of parties who take part in a conversation, and segment the conversation by speaking party. In one aspect, the invention monitors telephone conversations in real time to detect conditions of interest (for instance, calls to non-allowed parties or calls of a prohibited nature from prison inmates). In another aspect, automated prosody measurement algorithms are used in conjunction with speaker segmentation to extract emotional content of the speech of participants within a particular conversation, and speaker interactions and emotions are displayed in graphical form. A conversation database is generated which contains conversation recordings, and derived data such as transcription text, derived emotions, alert conditions, and correctness probabilities associated with derived data. Investigative tools allow flexible queries of the conversation database.

Claims

1. A method, in an inmate telephone monitoring system, for detecting the voice of an unauthorized person in a conversation on a phone call between an incarcerated inmate on a calling-party side of a phone line and at least one called party on a called-party side of the phone line, comprising:

initially verifying, by the inmate telephone monitoring system, the authorization of an inmate voice on the calling-party side of the line;

setting the frequency of an automatic periodic voice verification based on the incarcerated inmate or the called party;

subsequently performing the automatic periodic voice verification, by the inmate telephone monitoring system, on at least one side of the line during the conversation to detect the voice of an unauthorized conversation participant, wherein the voice verification utilizes spectral analysis of a digitized representation of the conversation;

generating an electronic signal indicative of the detection of the voice of an unauthorized person within said conversation; and

Automatically increasing the frequency of said periodic voice verification, by the inmate telephone monitoring system, subsequent to the detection of one of an unauthorized voice during said conversation, wherein the frequency increase includes varying of frequency of the periodic voice verification based on the system computational load.

2. The method of claim 1, further comprising:

varying the frequency of said periodic voice verification in response to detection of specified interaction characteristics between parties of said conversation.

3. An inmate telephone monitoring system for detecting the voice of an unauthorized person in a conversation on a phone call between an incarcerated inmate on a calling-party side of a phone line and at least one called party on a called-party side of the phone line, the system comprising:

a processor; and

a memory coupled to the processor, the memory storing computer-readable instructions that, upon execution by the processor, cause the system to;

initially verify the authorization of an inmate voice on the calling-party side of the line;

set the frequency of an automatic periodic voice verification based on the incarcerated inmate or the called party;

subsequently perform the automatic periodic voice verification on at least one side of the line during the conversation to detect the voice of an unauthorized conversation participant, wherein the voice verification utilizes spectral analysis of a digitized representation of the conversation;

generate an electronic signal indicative of the detection of the voice of an unauthorized person within said conversation; and

automatically increase the frequency of said periodic voice verification subsequent to the detection of an unauthorized voice during said conversation, wherein the frequency increase includes varying of frequency of the periodic voice verification based on the computational load of the monitoring system.

4. The system of claim 3, the memory storing additional computer-readable instructions that, upon execution by the processor, cause the system to:

vary the frequency of said periodic voice verification in response to detection of specified interaction characteristics between parties of said conversation.