Method and system for a recognition system having a verification recognition system

• US 7,756,706 B2
• Filed: 01/23/2008
• Issued: 07/13/2010
• Est. Priority Date: 10/11/2001
• Status: Expired due to Term

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Palm, Inc. (TCL Technology Group Corp.)
• Inventors: Wong, Yoon Kean
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US12/018,432
• Publication Number:
  US 20080255836A1
• Time in Patent Office: 902 Days
• Field of Search: 704/231
• US Class Current: 704/231
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

A method and system for performing computer implemented recognition is disclosed. In one method embodiment, the present invention first accesses user input stored in a memory of a mobile device. On the mobile device, the present invention performs a coarse recognition process on the user input to generate a coarse result. The coarse process may operate in real-time. The embodiment then displays a portion of the coarse result on a display screen of the mobile device. The embodiment further performs a detailed recognition process on the user input to generate a detailed result. The detailed process has more recognition patterns and computing resources available to it. The present embodiment performs a comparison of the detailed result and the coarse result. The present embodiment displays a portion of the comparison on the display screen.

Claims

1. A method of performing computer-implemented input recognition, comprising:

accessing user input to be recognized;

on a mobile device, generating a first input recognition result based on said user input to be recognized;

receiving a second input recognition result based on said user input to be recognized, wherein said second input recognition result is more detailed than said first user input recognition result;

comparing said first and said second input recognition result to generate a input recognition result comparison; and

causing a portion of said input recognition result comparison to be accessible for display on a display screen of said mobile device.

2. A method as described in claim 1 further comprising generating said second input recognition result using a computing system that is separate from said mobile device.

3. A method as described in claim 2 further comprising:

transferring said user input from said mobile device to said computing system that is separate from said mobile device for generating said second input recognition result.

4. A method as described in claim 1 further comprising:

transferring said user input from said mobile device to a computing system that is separate from said mobile device for generating said second input recognition result.

5. A method as described in claim 2 further comprising:

transferring said first input recognition result to said computing system that is separate from said mobile device in conjunction with said user input.

6. A method as described in claim 4 wherein said transferring is performed wirelessly over a wireless communications channel.

7. A method as described in claim 1 further comprising generating said second input recognition result by performing a detailed input recognition process on said user input wherein said detailed input recognition process is performed on said mobile device.

8. A method as described in claim 7 wherein said detailed input recognition process is performed during background processing of said mobile device.

9. A method as described in claim 1 wherein said user input is speech data and wherein said first input recognition result and said second input recognition result are generated from coarse and detailed speech recognition processes respectively.

10. A method as described in claim 1 wherein said user input is handwriting data and wherein said first input recognition result and said second input recognition result are generated from coarse and detailed handwriting recognition processes respectively.

11. A method of performing computer-implemented input recognition, comprising:

accessing user input to be recognized;

on a mobile device, generating a first input recognition result based on said user input to be recognized;

on said mobile device, generating a second input recognition result based on said user input to be recognized, wherein said second input recognition result is more detailed than said first input recognition result,

on said mobile device, comparing said first and said second input recognition result to generate an input recognition result comparison; and

on said mobile device, causing a portion of said input recognition result comparison to be accessible for display on a display screen of said mobile device.

12. A method as described in claim 11 wherein said second input recognition result is generated from an input recognition process performed during background processing of said mobile device.

13. A method as described in claim 11 wherein said user input is speech data and wherein said first input recognition result and said second input recognition result are generated from coarse and detailed speech recognition processes respectively.

14. A method as described in claim 11 wherein said user input is handwriting data and wherein said first input recognition result and said second input recognition result are generated from coarse and detailed handwriting recognition processes respectively.

15. A method as described in claim 11 further comprising displaying a portion of said first input recognition result on said display screen.

16. A system for performing computer-implemented input recognition, comprising:

a user input accessing component, of a mobile device, for accessing a user input to be recognized;

a first input recognition result generating component for generating a first input recognition result based on said user input to be recognized;

a second input recognition result generating component for generating a second input recognition result based on said user input to be recognized, wherein said second input recognition result is more detailed than said first input recognition result;

an input recognition result comparing component for comparing said first input recognition result and said second input recognition result to generate an input recognition result comparison; and

an access providing component for causing a portion of said input recognition result comparison to be accessible for display on a display screen of said mobile device.

17. A system as described in claim 16 wherein said second input recognition result generating component generates said second input recognition result on a computing system that is separate from said mobile device.

18. A system as described in claim 17 wherein said mobile device transfers said user input to said computing system that is separate from said mobile device and thereafter said mobile device receives said second input recognition result from said computing system that is separate from said mobile device.

19. A system as described in claim 16 wherein said mobile device transfers said user input to a computing system that is separate from said mobile device and thereafter said mobile device receives said second input recognition result from said computing system that is separate from said mobile device.

20. A system as described in claim 19 wherein said mobile device transfers said first input recognition result to said computing system that is separate from said mobile device in conjunction with said user input.

21. A system as described in claim 19 wherein said mobile device transfers said first input recognition result to said computing system that is separate from said mobile device wirelessly over a wireless communications channel.

22. A system as described in claim 16 wherein said second input recognition result generating component generates said first input recognition result using a detailed input recognition process that is performed on said mobile device.

23. A system as described in claim 22 wherein said detailed recognition process is performed during background processing of said mobile device.