System and method for remote speech recognition

• US 20040093211A1
• Filed: 11/13/2002
• Published: 05/13/2004
• Est. Priority Date: 11/13/2002
• Status: Active Grant

• Current Assignee: Chiharu Technologies LLC
• Original Assignee: SBC Properties, L.P.
• Inventors: Knott, Benjamin Anthony, Reynolds, Douglas F., Bushey, Robert Randal
• Granted Patent: US 7,421,389 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A system and method for remote speech recognition includes one or more customer premise equipment, a speech engine, and a communication engine. The customer premise equipment interfaces with a host from which the customer premise equipment is remotely located. The speech engine, remotely located from the host, recognizes a plurality of speech spoken by a user of the customer premise equipment and translates the speech into the language of the host. The speech engine further converts the recognized speech into one or more text data packets where the text data packets include the recognized speech as data instead of voice. The communication engine encrypts the text data packets and transmits the text data packets to the host. Transmitting data instead of voice to the host reduces the computational demands on the host. Additionally, the communication engine receives a plurality of information from the host.

Claims

1. A system for remote speech recognition utilizing voice over Internet Protocol, the system comprising:

a host including one or more ports and a host language;

one or more customer premise equipment remote from the host, the customer premise equipment operable to interface with the host;

a speech recognition engine disposed within the customer premise equipment, the speech engine operable to be customized based on one or more characteristics of a user of the customer premise equipment;

a communication engine associated with the speech engine and located within the customer premise equipment;

the speech engine operable to recognize and verify an identify of the user of the customer premise equipment;

the speech recognition engine further operable to recognize a plurality of speech from the user;

the speech engine further operable to translate the speech of the user into the host language;

the speech engine further operable to convert the recognized and translated speech into one or more text data packets;

the communication engine operable to encrypt the text data packets;

the communication engine further operable to transmit the encrypted text data packets from the customer premise equipment to the host;

the host operable to receive the encrypted text data packets and route the encrypted text data packets based on a plurality of user information; and

the host further operable to download to the customer premise equipment a plurality of information.

2. A method for remote speech recognition, the method comprising:

recognizing a plurality of speech from a user of a customer premise equipment;

converting the recognized speech into one or more text data packets at the customer premise equipment;

transmitting the text data packets from the customer premise equipment to a host; and

receiving a plurality of information from the host based on the speech of the user.

3. The method of claim 2 wherein receiving a plurality of information from the host comprises downloading to the customer premise equipment a menu hierarchy.

4. The method of claim 2 wherein receiving a plurality of information from the host comprises downloading to the customer premise equipment one or more speech recognition aides.

5. The method of claim 2 wherein recognizing the speech of the user of the customer premise equipment comprises recognizing the speech at the customer premise equipment and not at the host.

6. The method of claim 2 further comprising customizing the customer premise equipment utilizing one or more characteristics of the user.

7. The method of claim 6 wherein customizing the customer premise equipment comprises eavesdropping on the user interacting with the host and the customer premise equipment in order to obtain one or more of the characteristics of the user.

8. The method of claim 6 wherein customizing the customer premise equipment comprises initializing the customer premise equipment with the characteristics of the user.

9. The method of claim 2 further comprising:

recognizing the identity of the user of the customer premise equipment; and

verifying the identify of the user of the customer premise equipment.

13. The method of claim 2 wherein transmitting the text data packets from the customer premise equipment to a host comprises encrypting the text data packets before transmission to the host.

14. The method of claim 2 further comprising routing a call from the customer premise equipment based on a plurality of user information.

15. The method of claim 2 wherein recognizing the speech of the user of the customer premise equipment comprises translating the user speech from a user language into a host language.

16. The method of claim 2 wherein transmitting the text data packets to the host and receiving the information from the host comprises transmitting and receiving utilizing voice over Internet Protocol.

10. The method of claim 10 further comprising transmitting to the host a plurality of user information once the identity of the user has been verified.

11. The method of claim 10 further comprising utilizing biometrics to recognize and verify the identity of the user of the customer premise equipment.

12. The method of claim 10 wherein verifying the identity of the user of the customer premise equipment comprises:

receiving a password from the user; and

comparing the password with a previously provided password.

17. A system for remote speech recognition, the system comprising:

a host including one or more ports;

one or more customer premise equipment remote from the host and operable to interface with the host;

a speech engine remotely located from the host, the speech engine operable to recognize a plurality of speech from a user of the customer premise equipment and convert the recognized speech into one or more text data packets; and

a communication engine associated with the speech engine, the communication engine operable to transmit the text data packets from the customer premise equipment to the host and receive a plurality of information from the host.

18. The system of claim 17 wherein the host comprises a computer located in a call center.

19. The system of claim 17 wherein the customer premise equipment comprises a telephone.

20. The system of claim 17 wherein the speech engine is disposed within the customer premise equipment.

21. The system of claim 17 wherein the information received from the host comprises one or more grammars.

22. The system of claim 17 wherein the communication engine transmits the text data packets to the host and receives the information from the host utilizing voice over Internet Protocol.

23. The system of claim 17 wherein the communication engine is further operable to encrypt the text data packets before transmitting the text data packets to the host from the customer premise equipment.

24. The system of claim 17 wherein the speech engine is further operable to recognize and verify the identify of the user of the customer premise equipment.

25. The system of claim 24 wherein the communication engine is operable to transmit to the host a plurality of user information once the identity of the user has been verified.

26. The system of claim 17 wherein the host is further operable to route a call from the customer premise equipment based on a plurality of user information.

27. The system of claim 17 wherein the host is further operable to download to the customer premise equipment a menu hierarchy.

28. The system of claim 27 wherein the user interacts with the customer premise equipment in place of the host.

29. The system of claim 17 wherein the speech engine is further operable to translate a user language into a host language.

30. The system of claim 17 wherein the speech engine is further operable to be customized based on one or more characteristics of the user.

31. The system of claim 17 wherein the host is further operable to receive the text data packets and route the text data packets.

32. The system of claim 17 wherein the host comprises an interactive voice response unit.

33. The system of claim 17 wherein the host is further operable to speculate as to a purpose for the customer premise equipment accessing the host based on a plurality of user information.

34. A customer premise equipment comprising:

a speech engine disposed within the customer premise equipment, the speech engine operable to recognize a plurality of speech from a user of the customer premise equipment and convert the recognized speech into one or more text data packets;

a communication engine associated with the speech engine, the communication engine operable to encrypt the text data packets and transmit the encrypted text data packets from the customer premise equipment to a host; and

wherein the speech engine is operable to be customized based on one or more characteristics of the user of the customer premise equipment.

35. A host for remote speech recognition, the host comprising:

one or more processors;

one or more memory modules associated with the processors, the memory modules operable to store a plurality of speech recognition aides;

one or more ports associated with the processors and the memory modules, the ports operable to communicate with one or more customer premise equipment and receive a plurality of text data packets from the customer premise equipment; and

wherein the host is operable to process the text data packets from the customer premise equipment independent of a plurality of languages used by a plurality of users of the customer premise equipment.