System and method for three-way call detection

• US 9,621,732 B2
• Filed: 01/23/2015
• Issued: 04/11/2017
• Est. Priority Date: 02/15/2007
• Status: Active Grant

• Current Assignee: DSI-ITI, Inc.
• Original Assignee: Digital Solutions Incorporated (DLH Holdings Corp.)
• Inventors: Olligschlaeger, Andreas M.
• Primary Examiner(s): Phan, Joseph T
• Application Number:
  US14/604,388
• Publication Number:
  US 20150201083A1
• Time in Patent Office: 809 Days
• CPC Class Codes: H04M 1/656 for recording conversations
• CPC Class Codes: H04M 11/10 with dictation recording and playback systems
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00
• 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 system for detecting three-way calls in a monitored telephone conversation includes a speech recognition processor that transcribes the monitored telephone conversation and associates characteristics of the monitored telephone conversation with a transcript thereof, a database to store the transcript and the characteristics associated therewith, and a three-way Call detection processor to analyze the characteristics of the conversation and to detect therefrom the addition of one or more parties to the conversation. The system preferably includes at least one domain-specific language model that the speech recognition processor utilizes to transcribe the conversation. The system may operate in real-time or on previously recorded conversations. A query and retrieval system may be used to retrieve and review call records from the database.

Claims

1. A system for detecting a presence of a third party participating in a monitored telephone conversation, the system comprising:

a speech recognition module configured to detect a first characteristic of the monitored telephone conversation and a second characteristic of the monitored telephone conversation;

a speech analysis module configured to calculate a three-way calling score for the monitored telephone conversation, the calculating including;

assigning a first score of the first characteristic based on a predefined importance of the first characteristic;

assigning a second score of the second characteristic based on a predefined importance of the second characteristic; and

calculating the three-way calling score by summing the first score and the second score; and

a three-way call detection module configured to detect the presence of the third party based on a comparison of the three-way calling score to a predetermined threshold.

2. The system of claim 1, further comprising a database that stores the first score and the second score.

3. The system of claim 1, wherein the calculating further includes normalizing the sum to a value between 0 and 1 using a refining function.

4. The system of claim 3, wherein the refining function includes:

calculating a first value as the natural log of the negative of the sum;

adding 1 to the first value to obtain a second value; and

inverting the second value.

5. The system of claim 1, wherein the first characteristic represents the detection of a spoken phone number during the monitored telephone conversation, and

wherein the second characteristic represents a gap in speech during the monitored telephone conversation.

6. The system of claim 5, wherein a value of the second score increases according to a proximity of the second characteristic to the first characteristic within the monitored telephone conversation.

7. A method for detecting a presence of a third party participating in a monitored telephone conversation, the method comprising:

detecting a first characteristic of the monitored telephone conversation and a second characteristic of the monitored telephone conversation;

calculating a three-way calling score for the monitored telephone conversation, the calculating including;

assigning a first score of the first characteristic based on a predefined importance of the first characteristic;

assigning a second score of the second characteristic based on a predefined importance of the second characteristic; and

calculating the three-way calling score by summing the first score and the second score; and

detecting the presence of the third party based on a comparison of the three-way calling score to a predetermined threshold.

8. The method of claim 7, further comprising storing the first score and the second score in a database.

9. The method of claim 7, wherein the calculating further includes normalizing the sum to a value between 0 and 1 using a refining function.

10. The method of claim 9, wherein the refining function includes:

calculating a first value as the natural log of the negative of the sum;

adding 1 to the first value to obtain a second value; and

inverting the second value.

11. The method of claim 7, wherein the first characteristic represents the detection of a spoken phone number during the monitored telephone conversation, and

wherein the second characteristic represents a gap in speech during the monitored telephone conversation.

12. The method of claim 11, wherein a value of the second score increases according to a proximity of the second characteristic to the first characteristic within the monitored telephone conversation.

13. A system for detecting a presence of a third party participating in a monitored telephone conversation, the system comprising:

a speech recognition module configured to detect a plurality of characteristics of the monitored telephone conversation;

a scoring module configured to score the monitored telephone conversation based on the plurality of characteristics, the scoring including;

accessing a scoring database that stores scores of detectable characteristics;

looking up a corresponding score for each of the plurality of characteristics; and

assigning each of the plurality of characteristics the corresponding scores;

a three-way call detection module configured to detect the presence of the third party based on a comparison of the score to a predetermined threshold; and

a tagging module configured to associate additional information with the monitored telephone call following the detection of the presence of the third party.

14. The system of claim 13, wherein the scoring module is further configured to score the monitored telephone conversation by:

summing the assigned scores.

15. The system of claim 13, wherein the scoring module is configured to score the monitored telephone conversation, and the three-way call detection module is configured to compare the score to the predetermined threshold, after each detection by the speech recognition module of one of the plurality of characteristics of the monitored telephone conversation.

16. The system of claim 13, wherein the tagging module is configured to add a tag identifying an approximate starting point of the presence of the third party in the monitored telephone conversation.

17. The system of claim 15, wherein the tagging module is configured to add a tag identifying an approximate starting point of the presence of the third party in the monitored telephone conversation based on a first score to exceed the predetermined threshold.

18. The system of claim 16, wherein the approximate starting point is represented by a timestamp indicating a number of seconds into the monitored telephone call in which the presence of the third party was detected.