Algorithm for intelligent speech recognition

• US 20050049859A1
• Filed: 08/27/2003
• Published: 03/03/2005
• Est. Priority Date: 08/27/2003
• Status: Active Grant

• Current Assignee: General Motors LLC (General Motors Company)
• Original Assignee: General Motors Corporation (Motors Liquidation Co. GUC Trust)
• Inventors: Arun, Uma
• Granted Patent: US 8,244,536 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for intelligent speech recognition for premature enunciators is disclosed. The method allows for speech recognition systems to adjust to commands of premature enunciators, who speak before the system is ready receive speech input. The method comprises activating the speech recognition system, informing the user that the speech recognition system is ready to receive speech input, and initiating a listening period. The method further comprises receiving input from a user before the system is ready to receive such input, identifying the user as a premature enunciator, and adjusting the system to allow for earlier detection of user speech input.

Claims

1. A method for a speech recognition system to adjust to premature enunciator commands, the method comprising:

activating the speech recognition system;

receiving speech input from a user before the system is ready to receive speech input; and

adjusting the system to allow for earlier detection of user speech input.

2. The method of claim 1 wherein the speech recognition system is activated selectively by the user.

3. The method of claim 1 wherein the activation of the speech recognition system is followed by informing the user that the system is ready to receive input and a listening period wherein the speech recognition system is able to receive speech input.

4. The method of claim 1, further comprising the speech recognition system receiving user voice input before the system has started the listening period, determining the user as a premature enunciator and starting the listening period at an earlier predetermined time interval.

5. The method of claim 4 wherein the earlier listening period begins 50 to 100 ms before the speech recognition system informs the user of its readiness to receive input.

6. The method of claim 1, wherein the speech recognition system filters sound overlays from user commands.

7. The method of claim 6 further comprising processing filtered speech input through the speech recognition system.

8. A computer readable medium storing a computer program for a speech recognition system to adjust to premature enunciator commands comprising:

computer readable code for activating the speech recognition system;

computer readable code for receiving speech input from a user before the system is ready to receive speech input; and

computer readable code for adjusting the system to allow for earlier detection of user input.

9. The computer readable medium of claim 8 further comprising computer readable code to activate the speech recognition system selectively by the user.

10. The computer readable medium of claim 8 further comprising computer readable code for informing the user that the system is ready to receive input, and computer readable code for determining a listening period wherein the speech recognition system is able to receive speech input.

11. The computer readable medium of claim 8 further comprising computer readable code for the speech recognition system to determine the user as a premature enunciator and to start a listening period at an earlier predetermined time interval.

12. The computer readable medium of claim 11 further comprising computer readable code to begin the earlier listening period 50 to 100 ms before the speech recognition system informs the user of its readiness to receive input.

13. The computer readable medium of claim 8 further comprising computer readable code for filtering sound overlays from user commands.

14. The computer readable medium of claim 8 further comprising computer readable code to process filtered speech input through the speech recognition system.

15. A system for speech recognition that adjusts to premature enunciator commands, the system comprising:

means for activating the speech recognition system;

means for receiving speech input from a user before the system is ready to receive speech input; and

means for adjusting the system to allow for earlier detection of user input.

16. The system of claim 15 further comprising means for the user to selectively activate the speech recognition system.

17. The system of claim 15 wherein the means to activate the speech recognition system comprise means to inform the user that the system is ready to receive input, and means for a listening period wherein the speech recognition system is able to receive speech input.

18. The system of claim 15 further comprising the means for the speech recognition system to determine the user as a premature enunciator and start the listening period at an earlier predetermined time interval.

19. The system of claim 18 further comprising means for the earlier listening period to begin 50 to 100 ms before the speech recognition system informs the user of its readiness to receive input.

20. The system of claim 15 further comprising the means for the speech recognition system to filter sound overlays from user commands.