Method and apparatus for correcting misinterpreted voice commands in a speech recognition system

• US 6,327,566 B1
• Filed: 06/16/1999
• Issued: 12/04/2001
• Est. Priority Date: 06/16/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Lewis, James R., Ortega, Kerry A., Wang, Huifang, Vanbuskirk, Ronald E.
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Nolan, Daniel A.
• Application Number:
  US09/333,698
• Time in Patent Office: 902 Days
• Field of Search: 704/9, 704/270, 704/251, 704/231, 704/275
• US Class Current: 704/257
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

An efficient method and system, particularly well-suited for correcting natural language understanding (NLU) commands, corrects spoken commands misinterpreted by a speech recognition system. The method involves a series of steps, including: receiving the spoken command from a user; parsing the command to identify a paraphrased command; displaying the paraphrased command; and accepting corrections of the paraphrased command from the user. The paraphrased command is segmented according to command language categories, which include a command action category, an action object category, and an action and/or object modifying category. The paraphrased command is displayed in a user interface window segmented into these command language categories. The user interface window also contains alternative commands for each segment of the paraphrased command.

Claims

1. In a computer system adapted for speech recognition, a method for correcting an incorrectly recognized spoken command, comprising the steps of:

receiving said command from a user;

parsing said command to identify a paraphrased command;

displaying said paraphrased command to the user in a segmented format; and

accepting corrections of said paraphrased command from said user on a per segment basis without requiring said user to re-dictate said command entirely.

2. The method according to claim 1, wherein said computer system is adapted to recognize natural language and said spoken command is a natural language command.

3. The method according to claim 1, wherein said paraphrased command is segmented according to command language categories.

4. The method according to claim 3, wherein said command language categories include at least one of:

a command action category indicating an action to be performed;

an action object category indicating an application element subjected to said event; and

a modifier category indicating modifications to said action or said application element.

5. The method according to claim 3, wherein each command language segment of said paraphrased command is displayed in a user interface window.

6. The method according to claim 3, further comprising the step of identifying alternative voice commands for each command language segment of said paraphrased command.

7. The method according to claim 6, wherein said alternative voice commands are displayed in a user interface window as one of a pop-up text window, a floating text window and a drop-down menu in response to prompting by an input device.

8. A computer speech recognition system having a simple means for correcting an incorrectly recognized spoken command, comprising:

means for receiving said command from a user;

process means for recognizing and parsing said command to identify a paraphrased command;

monitor means for displaying said paraphrased command to the user in a segmented format; and

input means for accepting corrections of said paraphrased command from said user on a per segment basis without requiring said user to re-dictate said command entirely.

9. The system as recited in claim 8, wherein said computer system is adapted to recognize natural language and said spoken command is a natural language command.

10. The system as recited in claim 8, wherein said paraphrased command is segmented according to command language categories.

11. The system as recited in claim 10, wherein said command language categories include at least one of:

a command action category indicating an action to be performed;

an action object category indicating an application element subjected to said event; and

a modifier category indicating modifications to said action or said application element.

12. The system as recited in claim 10, wherein each command language segment of said paraphrased command is displayed in a user interface window.

13. The system as recited in claim 10, further comprising the step of identifying alternative voice commands for each command language segment of said paraphrased command.

14. The system as recited in claim 13, wherein said alternative voice commands are displayed in a user interface window as one of a pop-up text window, a floating text window and a drop-down menu in response to prompting by an input device.

15. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

receiving a spoken command from a user;

parsing said command to identify a paraphrased command;

displaying said paraphrased command to the user in a segmented format; and

accepting corrections of said paraphrased command from said user on a per segment basis without requiring said user to re-dictate said command entirely.