Telecommunication call management and monitoring system with voiceprint verification

Patent metadata

Field	Value
Publication number	US-10230838-B2
Application number	US-201715683404-A
Country	US
Kind code	B2
Filing date	Aug 22, 2017
Priority date	Aug 8, 2002
Publication date	Mar 12, 2019
Grant date	Mar 12, 2019

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.

First claim

What is claimed is:

1. A call management system for controlling access to a public telephone network, the system comprising:
a telephone terminal;
a voice biometric sensor;
a central site server including a memory that stores a plurality of inmate data records, each inmate data record containing a corresponding first identifier and a corresponding voice biometric baseline sample of a corresponding inmate;
the central site server configured to, during each attempt to access the public telephone network by a user:
prompt the user to input a second identifier using the telephone terminal;
select an inmate data record from among the plurality of inmate data records whose first identifier matches the second identifier;
prompt the user to provide a voice biometric sample using the voice biometric sensor;
compare vocal characteristics of the voice biometric sample only to vocal characteristics of the voice biometric baseline sample of the selected inmate data record;
determine that the voice biometric sample matches the voice biometric baseline sample with a predetermined degree of similarity based on the comparison; and
grant the user access to the public telephone network to attempt to place a telephone call based on the determining,

wherein the voice biometric baseline sample is a spoken name of the inmate and the voice biometric sample is a spoken name of the user.

2. The system of claim 1 , wherein the voice biometric sensor is a microphone located within a telephone receiver of the telephone terminal, and
wherein the voice biometric baseline sample and the voice biometric sample are voiceprints.

3. The system of claim 1 , wherein the telephone terminal includes an input device, and
wherein the second identifier is input via the input device.

4. The system of claim 1 , wherein the central site server further includes a call recorder, and
wherein the call recorder is configured to, during each access attempt, record prompts provided by the central site server to the user, responses to the prompts provided by the user, and a conversation between the user and an outside party.

5. The system of claim 1 , further comprising a radio frequency (RF) receiver, wherein the second identifier is input via the RF receiver.

6. The system of claim 1 , wherein the plurality of inmate data records are indexed in the memory according to their respective first identifiers.

7. The system of claim 6 , wherein the central site server is configured to select the selected inmate data record using the second identifier as a key to the indexed plurality of inmate data records.

8. A call management system for controlling access to a public telephone network, the system comprising:
a memory that stores a plurality of inmate data records, each of the plurality of inmate data records containing a corresponding first identifier and a corresponding voice biometric baseline sample, and indexed according to their respective first identifier; and
a central site server configured to, during each attempt to access the public telephone network by a user:
receive a second identifier from the user;
select, using the second identifier as a key to the indexed plurality of inmate data records, a selected inmate data record from among the indexed plurality of inmate data records whose first identifier matches the second identifier;
receive a voice biometric sample from the user;
compare vocal characteristics of the voice biometric sample only to vocal characteristics of the voice biometric baseline sample of the selected inmate data record; and
grant or deny the user access to the public telephone network to attempt to place a telephone call based on the comparison,

wherein the voice biometric baseline sample is a spoken name of the inmate and the voice biometric sample is a spoken name of the user.

9. The system of claim 8 , further comprising a biometric sensor configured to obtain the voice biometric sample from the user.

10. The system of claim 9 , further comprising a telephone terminal configured to communicate with the central site server via a communication line,
wherein the biometric sensor is coupled to the telephone terminal, and
wherein the biometric sensor transmits the voice biometric sample to the central site server using the communication line.

11. The system of claim 10 , wherein the biometric sensor is integrated into the telephone terminal.

12. The system of claim 9 , wherein the vocal characteristics of the voice biometric sample include at least one of duration, loudness, mixed-frequencies, and timbre.

13. The system of claim 8 , wherein the central site server includes a voice recognition processor configured to analyze speech to identify words and individuals.

14. The system of claim 13 , wherein after the user has been granted access to the public telephone network for a call, the voice recognition processor is configured to perform voice recognition so as to identify parties to the call, and to detect whether an unauthorized participant is on the call.

15. A method for controlling access to a public telephone network, the method comprising:
storing a personal data record for a registered individual in a database, the personal data record containing a first numerical identifier and a biometric identifier associated with the registered individual;

during each attempt to access the public telephone network by a user:
first prompting the user to input a second numerical identifier;
selecting the personal data record based on a comparison between the first numerical identifier and the second numerical identifier;
second prompting the user to input a voice biometric sample;
comparing vocal characteristics of the voice biometric sample only to vocal characteristics of the biometric identifier of the selected personal data record;
granting or denying the user access to the public telephone network to attempt to place a telephone call based on the comparing,
wherein the first prompting, the selecting, the second prompting, the comparing and the granting or denying are performed by a central site sample, and
wherein the biometric identifier is a spoken name of the registered individual and the voice biometric sample is a spoken name of the user.

16. The method of claim 15 , further comprising storing a plurality of personal data records that includes the personal data record for the registered individual, each personal data record of the plurality of personal data records corresponding to a different registered individual and including a corresponding first numerical identifier and a corresponding biometric identifier,
wherein the plurality of personal data records are indexed in the database according to their respective first numerical identifier.

17. The method of claim 16 , wherein the selecting selects the personal data record using the second numerical identifier as a key to the indexed plurality of personal data records.

18. The method of claim 16 , further comprising, after the user has been granted access to the public telephone network:
analyzing speech of participants to a call; and
obtaining, based on the analyzing, a speech sample for each of the participants to the call.

19. The method of claim 18 , further comprising:
comparing a first speech sample from among the obtained speech samples to the plurality of personal data records until a match is found to within a predetermined similarity or until no match to within the predetermined similarity is found; and
repeating the comparing for each

Assignees

• Global Telstarlink Corp

Inventors

• Hodge Stephen Lee

Classifications

• H04M3/42221

  Conversation recording systems (at the subscriber's set H04M1/656) · CPC title

• H04M2201/40

  using speech recognition · CPC title

• H04M1/677

  Preventing the dialling or sending of predetermined telephone numbers or selected types of telephone numbers, e.g. long distance numbers · CPC title

• H04W28/18

  Negotiating wireless communication parameters · CPC title

• H04M3/2218

  Call detail recording · CPC title