Voice recognition system and method thereof

• US 7,957,972 B2
• Filed: 02/07/2007
• Issued: 06/07/2011
• Est. Priority Date: 09/05/2006
• Status: Active Grant

• Current Assignee: Fortemedia, Inc.
• Original Assignee: Fortemedia, Inc.
• Inventors: Zhang, Ming, Hou, Zhen, Bai, Bo-Ren, Huang, Yen-Son Paul, Lu, Younan
• Primary Examiner(s): Chawan; Vijay B
• Application Number:
  US11/672,472
• Publication Number:
  US 20080059193A1
• Time in Patent Office: 1,581 Days
• Field of Search: 704/270, 704/275, 704/270.1, 704/233, 704/257, 704/260, 704/235, 379/67.1, 379/216.01, 379/88.01, 379/218.01, 381/110
• US Class Current: 704/260
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A voice recognition system and method thereof. The communication system comprises a setup controller, a voice recognition controller, and an application controller. The setup controller receives a voice keyword table including a voice recognizable keyword and a corresponding application instruction. The voice recognition controller, coupled to the setup controller, receives the voice keyword table from the setup controller, receives a first voice input, and matches a first voice input to the voice recognizable keyword to determine the corresponding application instruction. The application controller, coupled to the voice recognition controller, receives and performs the corresponding application instruction. The setup controller, the voice recognition controller, and the application controller communicate through wireless communication.

Claims

1. A communication system, comprising:

a setup controller, receiving a voice keyword table including a voice recognizable keyword and a corresponding application instruction;

a voice recognition controller, coupled to the setup controller, receiving the voice keyword table from the setup controller, receiving a first voice input and matching the first voice input to the voice recognizable keyword to determine the corresponding application instruction; and

an application controller, coupled to the voice recognition controller, receiving and performing a corresponding application instruction,

wherein the setup controller shares phonemes between Text-to-Speech (TTS) voice prompt and voice recognition models, and generates pronunciation according to the phonemes.

2. The communication system of claim 1, wherein the setup controller, the voice recognition controller, and the application controller communicate through wireless or wired communication.

3. The communication system of claim 1, wherein the voice recognition controller further transmits the first voice input to the application controller, if the first voice input does not match to any voice recognizable keyword in the voice keyword table.

4. The communication system of claim 3, wherein the application controller further determines a corresponding application instruction based on the first voice input, and transmits the first voice input and the corresponding application instruction to the voice recognition controller.

5. The communication system of claim 1, wherein the voice keyword table is a phonebook, the voice recognizable keyword is a pronunciation of a name entry, and the corresponding application instruction is dialing a predetermined number.

6. The communication system of claim 1, wherein the voice recognizable keyword is a pronunciation of a command entry, and the corresponding application instruction controls or receives information.

7. The communication system of claim 1, wherein the voice recognizable keyword is a pronunciation of a digit entry, and the corresponding application instruction is dialing the digit.

8. The communication system of claim 1, wherein the setup controller further receives a second voice input, and validates the voice recognizable keyword if the second voice input matches the voice recognizable keyword.

9. The communication system of claim 1, wherein the setup controller further changes the voice recognizable keyword by a user.

10. The communication system of claim 1, wherein the voice recognition controller comprises:

a first transceiver, downloading the voice keyword table from the setup controller;

a second transceiver, transmitting the corresponding application instruction to the application controller;

a voice input device, receiving the first voice input;

an analog to digital converter (ADC), coupled to the voice input device, converting the first voice input to digital;

memory, coupled to the first and the second transceivers, storing the voice keyword table; and

a voice recognition module, coupled to the ADC and the memory, matching the first voice input to the voice recognizable keyword to determine the corresponding application instruction.

11. The communication system of claim 1, configured such that a user can edit the pronunciation phonemes under the guide of the TTS prompt, and an updated voice recognition model is generated according to the edited pronunciation phonemes.

12. A method of voice recognition in a communication system, comprising:

a setup controller receiving a voice keyword table including a voice recognizable keyword and a corresponding application instruction;

a voice recognition controller receiving the voice keyword table, and matching a first voice input to the voice recognizable keyword to determine the corresponding application instruction;

an application controller receiving and performing the corresponding application instruction; and

the setup controller sharing phonemes between Text-to-Speech (TTS) voice prompt and voice recognition models, and generating pronunciation according to the phonemes.

13. The method of claim 12, wherein the setup controller, the voice recognition controller, and the application controller communicate through wireless or wired communication.

14. The method of claim 12, further comprising the voice recognition controller transmitting the first voice input to the application controller if the first voice input does not match any voice recognizable keyword in the voice keyword table.

15. The method of claim 14, further comprising the application controller determining a corresponding application instruction based on the first voice input, and transmitting the first voice input and the corresponding application instruction to the voice recognition controller.

16. The method of claim 12, wherein the voice keyword table is a phonebook, the voice recognizable keyword is a pronunciation of a name entry, and the corresponding application instruction is dialing a predetermined number.

17. The method of claim 12, wherein the voice keyword table is a phonebook, the voice recognizable keyword is a pronunciation of a name entry, and the corresponding application instruction is dialing a predetermined number.

18. The method of claim 12, wherein the voice recognizable keyword is a pronunciation of a command entry, and the corresponding application instruction controls or receives information.

19. The method of claim 12, further comprising the setup controller receiving a second voice input, and validating the voice recognizable keyword if the second voice input matches the voice recognizable keyword.

20. The method of claim 12, further comprising the steps of a user editing the pronunciation phonemes under the guide of the TTS prompt, and generating an updated voice recognition model according to the edited pronunciation phonemes.