Telecommunication call management and monitoring system with voiceprint verification
Disclosed is a secure telephone call management system for authenticating users of a telephone system in an institutional facility. Authentication of the users is accomplished by using a personal identification number, preferably in conjunction with speaker independent voice recognition and speaker dependent voice identification. When a user first enters the system, the user speaks his or her name which is used as a sample voice print. During each subsequent use of the system, the user is required to speak his or her name. Voice identification software is used to verify that the provided speech matches the sample voice print. The secure system includes accounting software to limit access based on funds in a user's account or other related limitations. Management software implements widespread or local changes to the system and can modify or set any number of user account parameters.
1. A computer-implemented method for restricting access to a telephone call management system, said method comprising the steps of:
during a registration process by a user of said telephone call management system:
prompting the user to speak one or more predetermined keywords;
receiving a first speech sample from said user;
verifying said first speech sample is indicative of said one or more predetermined keywords using speaker independent voice recognition; and
associating said verified first speech sample with said user and storing said verified first speech sample in a database; and
during each subsequent access attempt by said user to said telephone call management system to place a telephone:
prompting said user for a second speech sample;
determining whether a voice characteristic of said second speech sample matches a voice characteristic of said verified first speech sample;
allowing said telephone call to be completed when the voice characteristic of said second speech sample matches the voice characteristic of said verified first speech sample; and
after the allowing said telephone call to be completed, sampling voice data from said telephone call to detect if an unauthorized person has spoken based on the voice characteristic of the verified first speech sample.
2. A method according to claim 1 , further comprising:
during the registration process by said user of said telephone call management system:
assigning an identification to said user;
associating said identification with said first speech sample in said database;
during the each subsequent access attempt by said user to said telephone call management system to place said telephone call:
receiving said identification from said user; and
locating said first speech sample in said database using said identification.
3. A method according to claim 2 , wherein said identification is a radio frequency identification (RFID) number.
4. A method according to claim 3 , said method further comprising the steps of:
during each access attempt by said user to said telephone call management system:
reading an RFID number from an RFID transmitter provided to said user;
locating said first speech sample in said database using said RFID number.
5. A method according to claim 2 , wherein allowing said telephone call to be completed further comprises:
querying said database with said identification to determining whether said user is authorized to place said call; and
allowing said telephone call to be completed when said user is authorized to place said telephone call and when a voice characteristic of a second speech sample matches a voice characteristic of said first speech sample.
6. A method according to claim 2 , wherein said identification is a personal identification number.
7. A method according to claim 2 further comprising taking a control action when detecting that the unauthorized person has spoken.
8. A method according to claim 1 , wherein said one or more predetermined keywords include said user's name.
9. A method according to claim 1 , said method further comprising the step of: monitoring said access to said telephone call management system by updating said database.
10. A method according to claim 1 , wherein said prompting is implemented with an interactive voice response (IVR) system.
11. An apparatus for restricting access to a telephone call management system, said apparatus comprising:
a registration module configured to, during a registration process by a user of said telephone call management system, prompt said user to speak one or more predetermined keywords and receive a first speech sample from said user;
a database including said first speech sample associated with said user;
a prompting module configured to prompt said user to provide a second speech sample when said user subsequently attempts to access said telephone call management system;
a speaker independent voice recognition module configured to verify said first speech sample is indicative of said one or more predetermined keywords; and
a speaker dependent voice identification module configured to determine whether a voice characteristic of said second speech sample matches a voice characteristic of said first speech sample,
wherein said telephone call management system authorizes said user to complete a telephone call using said telephone call management system when a voice characteristic of said second speech sample matches a voice characteristic of said first speech sample, and
wherein said telephone call management system, after authorizing said user to use said telephone management system, samples voice data from said telephone call to detect if an unauthorized person has spoken based on the voice characteristic of the verified first speech sample.
12. An apparatus according to claim 11 , wherein said prompting module comprises an interactive voice response (IVR) system.
13. An apparatus according to claim 11 , wherein said identification is an RFID number.
14. An apparatus according to claim 11 , wherein said database further includes an identification provided by said caller and wherein said identification is associated with said caller and said first speech sample in said database; and
wherein said speaker dependent voice identification module locates said first speech sample using said identification.
15. An apparatus according to claim 14 , wherein said identification includes personal identification number.
16. An apparatus according to claim 14 , wherein said identification includes an RFID number and said apparatus further comprises:
an RFID signal detect module configured to receive said RFID number from an RFID transmitter provide to said user.
17. An apparatus according to claim 11 , wherein said telephone call management system takes a control action when detecting that the unauthorized person has spoken.