Speech recognition and verification system enabling authorized data transmission over networked computer systems

• US 6,292,782 B1
• Filed: 09/09/1996
• Issued: 09/18/2001
• Est. Priority Date: 09/09/1996
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Philips Electronics North America Corporation (Koninklijke Philips N.V.)
• Inventors: Weideman, William Edward
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/709,584
• Time in Patent Office: 1,835 Days
• Field of Search: 704/273, 704/231, 704/200, 704/270, 704/275, 704/272
• US Class Current: 704/273
• CPC Class Codes: G06Q 20/425 using two different networks, one for transaction and one for security confirmation
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition
• CPC Class Codes: G10L 15/142 Hidden Markov Models [HMMs]
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

A system and apparatus for using speech recognition and verification to provide secure and authorized data transmissions between networked computer systems is provided. The system includes first and second network computer systems wherein a request for a transaction by user of the first computer system causes the user to be prompted to enter a spoken identifier such as a credit card number, PIN number or password. This spoken identifier is converted from speech data into speech feature data using either a resident software application or a downloaded application from the second computer system. The speech feature data is transmitted to the second computer system wherein speech recognition and verification engines identify the spoken identifier and determine whether or not the user who spoke the identifier is properly associated with the spoken identifier. Upon successful completion of this recognition and verification process, the requested transaction is completed.

Claims

1. A system for providing secure data transmissions between networked computer systems, comprising:

at least one server computer connected to a plurality of client computers through a computer communications link for receiving transaction requests and speech feature data from the client computers;

means within the server computer for prompting one of the client computers to request a spoken identifier from the user of the one client computer in response to the transaction request;

a recognition engine for deriving speech feature data from the spoken identifier;

a verification engine for verifying the spoken identifier represented by the speech feature data is associated with a user speaking the identifier; and

means for completing the transaction request upon verification of the association of the user with the spoken identifier.

2. The system of claim 1 wherein the speech recognition engine is on the server computer.

3. The system of claim 1 wherein the verification engine comprises:

a database for storing the speech feature data for previously received spoken identifiers;

a comparator for comparing the speech feature data to the speech feature data stored in the database for a user, said verification engine rejecting access when an exact match is detected between the speech feature data and the speech feature data stored in the database for a user.

4. The system of claim 1 wherein the computer communications link comprises the Internet.

5. The system of claim 1 further including means for decrypting speech feature data received from the client computer.

6. A method for securely transmitting data between computer systems on a computer communications link, comprising the steps of:

prompting a user at a first computer system to enter a spoken identifier in response to a transaction request by the user on the first computer;

converting the spoken identifier from speech data to speech feature data using a speech transformation engine;

transmitting the speech feature data to a second computer system;

identifying the spoken identifier using a speech recognition engine;

verifying the spoken identifier was entered by a user associated with the spoken identifier using a speech verification engine; and

providing the requested transaction from the second computer to the first computer if the identified spoken identifier was spoken by the associated user.

7. The method of claim 6 further including the step of confirming the spoken identifier was correctly identified by the speech recognition engine.

8. The method of claim 7 further including the step of re-prompting the user to enter a spoken identifier if the spoken identifier is not correctly identified.

9. The method of claim 6 further including the step of transferring a speech feature extraction engine to the first computer system in response to the transaction request.

10. The method of claim 9 further including the step of decrypting the speech feature data prior to identifying the spoken identifier.

11. The method of claim 6 further including the steps of:

comparing the speech feature data received from the first computer system to previously received speech feature data to determine if any identical matches exist; and

identifying the speech feature data as suspect if the received speech feature data exactly matches previously received speech feature data.

12. The method of claim 6 further including the step of encrypting the speech feature data prior to transmission to the second computer system.

13. The method of claim 6 further including the step of prompting the user at the first computer system to enter a first identifier containing sensitive information and wherein the spoken identifier comprises verifying information.

14. A method for securely transmitting between computer systems on a computer communications link, comprising the steps of:

prompting a user at a first computer system to speak a character string beginning with a first character and ending with a last character thereof in response to a transaction request by the user on the first computer;

generating speech feature data for each spoken character of the character string;

transmitting the speech feature data to a second computer system over the computer communications link;

applying the speech feature data of the character string and voice recognition transformation data to a voice recognition feature transformation to generate a first set of parameters for each spoken character of the first character string, the first set of parameters for use in a voice recognition system;

applying the speech feature data and voice verification feature transformation data to a voice verification feature transformation to generate a second set of parameters for each spoken character of the first character string, the second set of parameters for use in a voice verification system;

recognizing the character string using the first set of parameters;

verifying the user is associated with the character string using the second set of parameters; and

providing the requested transaction over the computer communications link from the second computer to the first computer if the user is verified and the character string is recognized.

15. The method of claim 14 further including the step of transferring a speech feature extraction engine to the first computer system in response to the transaction request.

16. The method of claim 14 wherein the step of verifying further includes the steps of:

comparing the speech feature data received from the first computer system to previously received speech feature data to determine if any identical matches exist; and

identifying the received speech feature data as suspect if the speech feature data exactly matches previously received speech feature data.

17. The method of claim 14 further including the step of encrypting the speech feature data prior to transmission to the second computer system.

18. The system of claim 17 further including the step of decrypting the speech feature data prior to identifying the spoken identifier.

19. A system for the providing secure data transmissions between networked computer systems comprising:

at least one server computer including a processor for receiving transaction requests and speech feature data;

a plurality of client computers connected to the at least one server through a computer communications link, each of the client computers including a processor;

wherein the server computer prompts one of the client computers to request a spoken identifier from the user of the one client computer in response to the transaction request;

a recognition engine for deriving speech feature data from the spoken identifier;

a verification engine for verifying the spoken identifier represented by the speech feature data is associated with a user speaking the identifier; and

means for completing the transaction request upon verification of the association of the user with the spoken identifier.

20. A server computer for use in a system for the providing secure data transmissions between networked computer systems, the server computer comprising:

a processor for receiving transaction requests and speech feature data from a plurality of client computers connected to the server through a computer communications link,

wherein the server computer prompts one of the client computers to request a spoken identifier from the user of the one client computer in response to the transaction request;

a verification engine for verifying the spoken identifier associated with a user speaking the identifier.

21. The server computer of claim 20 further including a recognition engine for deriving speech feature data from the spoken identifier and wherein the verification engine used the speech feature data for verifying the spoken identifier.

22. The server computer of claim 21 further including means for completing the transaction request upon verification of the association of the user with the spoken identifier.

23. A client computer for use in a system for the providing secure data transmissions between networked computer systems comprising:

a processor connected to at least one server computer through a computer communications link, the processor for sending a transaction requests and speech feature data to the at least one server computer and for receiving a request from the server computer for a spoken identifier from a user of the client computer in response to the transaction request.

24. The client computer of claim 23 further including a recognition engine for deriving speech feature data from the spoken identifier.