Telecommunication call management and monitoring system with voiceprint verification

• US 9,143,610 B2
• Filed: 08/13/2013
• Issued: 09/22/2015
• Est. Priority Date: 08/08/2002
• Status: Expired due to Term

• Current Assignee: Global Tel-Link Corporation
• Original Assignee: Global Tel-Link Corporation
• Inventors: Hodge, Stephen Lee
• Primary Examiner(s): Gelin, Jean
• Application Number:
  US13/966,011
• Publication Number:
  US 20130329867A1
• Time in Patent Office: 770 Days
• Field of Search: 455/565, 455/405, 455/410, 455/411, 455/415, 455/418, 455/419, 455/420, 455/563, 455/569, 379/114, 379/118, 379/191, 379/93.02, 379/142.05, 379/88.26, 379/88.02, 379/200, 379/188, 704/244, 704/270, 704/207, 704/208, 704/246
• US Class Current: 1/1
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/083 Recognition networks G10L15/142, G10L15/16 take precedence
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: H04L 12/28 characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks] wireless communication networks H04W ; arrangements for dividing the transmission path H04W40/00
• CPC Class Codes: H04L 63/083 using passwords cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 63/126 the source of the received data
• CPC Class Codes: H04M 1/67 by electronic means
• CPC Class Codes: H04M 1/673 the user being required to key in a code
• CPC Class Codes: H04M 1/677 Preventing the dialling or sending of predetermined telephone numbers or selected types of telephone numbers, e.g. long distance numbers
• CPC Class Codes: H04M 17/305 Wireless codes, e.g. Bluetooth or RFID
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2201/41 using speaker recognition speaker recognition per se G10L17/00
• CPC Class Codes: H04M 2203/6054 Biometric subscriber identification
• CPC Class Codes: H04M 2242/12 Language recognition, selection or translation arrangements
• CPC Class Codes: H04M 3/2218 Call detail recording
• 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 3/38 Graded-service arrangements, i.e. some subscribers prevented from establishing certain connections queuing arrangements H04Q3/64
• CPC Class Codes: H04M 3/382 using authorisation codes or passwords
• CPC Class Codes: H04M 3/385 using speech signals
• CPC Class Codes: H04M 3/4211 : where the identifier is used to access a profile
• CPC Class Codes: H04M 3/42221 : Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 7/1295 : Details of dual tone multiple frequency signalling
• CPC Class Codes: H04W 12/06 : Authentication
• CPC Class Codes: H04W 12/08 : Access security
• CPC Class Codes: H04W 12/10 : Integrity
• CPC Class Codes: H04W 12/72 : Subscriber identity
• CPC Class Codes: H04W 28/18 : Negotiating wireless communication parameters

Abstract

A secure telephone call management system is provided for authenticating users of a telephone system in an institutional facility. Authentication of the users of the telephone call management system is accomplished by using a personal identification number, biometric means, and/or radio frequency means. The secure telephone call management system includes accounting software capable of limiting access to the system based on funds in a user'"'"'s account, and includes management software capable of implementing widespread or local changes to the system. The system monitors a conversation in the telephone call to detect a presence of a first characteristic in audio of the conversation, and terminates the telephone call if the first characteristic does not match a second characteristic of biometric information of a user or a called party.

Claims

1. A call management system for detecting an unauthorized party, comprising:

a control platform configured to;

store voiceprints including voiceprints of inmates and voiceprints of called parties;

monitor audio information of a telephone conversation between at least a local user and a remote user;

detect a first characteristic of the local user in the audio information;

search the stored voiceprints for a first matching voiceprint based on the first characteristic;

detect a second characteristic of the remote user in the audio information;

search the stored voiceprints for a second matching voiceprint based on the second characteristic;

detect a third characteristic in the audio information;

identify the third characteristic as belonging to a third party based on a comparison of the third characteristic to at least one of the first and second matching voiceprints;

determine an identity of the third party by searching the stored voiceprints for a third matching voiceprint based on the third characteristic.

2. The system of claim 1, wherein the control platform is further configured to analyze the audio information to detect the presence of the first characteristic.

3. The system of claim 1, wherein each of the first characteristic, the second characteristic is at least one of a pitch, a loudness, a frequency or a timbre.

4. The system of claim 1, Wherein the control platform is further configured to take an action based on a result of the search of the stored voiceprints.

5. The system of claim 1, wherein the control platform is further configured to request an audio sample from the called party, extract a current voiceprint from the audio sample and store the current voiceprint and an associated unique identifier.

6. The system of claim 1, wherein the control platform is further configured to authenticate the local user and the remote user before connecting the telephone conversation.

7. The system of claim 1, wherein the control platform is further configured to:

adjust a stored voiceprint using a sample of the audio information; and

store the adjusted voiceprint.

9. The method of claim 7, wherein the alert includes a possible location of the wanted criminal.

8. A method of tracking a wanted criminal, comprising:

monitoring audio information of a telephone conversation between a first user and a second user to detect a presence of a first characteristic;

searching a national voiceprint database including voiceprints of wanted criminals for a matching voiceprint containing a second characteristic that substantially matches the first characteristic; and

issuing an alert identifying the user associated with the first characteristic as a wanted criminal after the search finds a matching voiceprint.

10. The method of claim 8, further comprising analyzing the telephone conversation using speech recognition.

11. The method of claim 10, wherein the analyzing of the telephone conversation comprises determining an address spoken in the conversation.

12. A method of locating a stolen device, comprising:

monitoring audio information of a telephone conversation between a first user and a second user to detect a presence of a first characteristic;

receiving a device identifier for a device used by one of the first user or the second user to conduct the telephone conversation;

searching stored voiceprints including voiceprints of persons authorized to use the device for a matching voiceprint containing a second characteristic that substantially matches the first characteristic;

determining that the stored voiceprints do not include the matching voiceprint or that the matching voiceprint is not one of the voiceprints of person authorized to use the device;

issuing an alert identifying the device as stolen in response to the determination.

13. The method of claim 12, wherein the monitoring is performed in response to a stolen device being used to conduct the conversation.

14. The method of claim 12, wherein the alert includes a possible location of the stolen device.

15. The method of claim 12, further comprising analyzing the telephone conversation using speech recognition.

16. A call management system for detecting an unauthorized party, comprising:

a control platform configured to;

store voiceprints;

monitor audio information of a telephone conversation between a local user and a remote user to detect a presence of a first characteristic;

search of the stored voiceprints for a matching voiceprint containing a second characteristic that substantially matches the first characteristic; and

wherein the stored voiceprints include voiceprints of inmates and Voiceprints of called parties;

wherein the control platform is further configured to authenticate the local user and the remote user before connecting the telephone conversation; and

wherein the authentication comprises requesting a first identifier and a first voice sample from the local user and a second identifier and a second voice sample from the remote user and verifying that the first voice sample and first identifier match a first stored voiceprint and associated unique identifier, respectively, and that the second voice sample and second identifier match a second stored voiceprint and associated unique identifier, respectively.

17. A call management system for detecting an unauthorized party, comprising:

a control platform configured to;

store voiceprints;

monitor audio information of a telephone conversation between a local user and a remote user to detect a presence of a first characteristic;

search of the stored voiceprints for a matching voiceprint containing a second characteristic that substantially matches the first characteristic;

wherein the stored voiceprints include voiceprints of inmates and voiceprints of called parties;

adjust a stored voiceprint using a sample of the audio information; and

store the adjusted voiceprint;

wherein the adjusting comprises extracting a current voiceprint from the audio information and computing an average value of the current voiceprint and the stored voiceprint.