Method and apparatus for providing an event-based “What-Can-I-Say?;” window

• US 6,308,157 B1
• Filed: 06/08/1999
• Issued: 10/23/2001
• Est. Priority Date: 06/08/1999
• 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, Nassiff, Amado, Vanbuskirk, Ronald E.
• Primary Examiner(s): Korzuch, William
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/328,095
• Time in Patent Office: 868 Days
• Field of Search: 704/275, 704/270, 704/251, 704/231, 704/276, 704/258, 704/240, 704/256
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method and system efficiently identifies voice commands for a user of a speech recognition system. The method involves a series of steps including: receiving input from a user; monitoring the computer system to log system events and ascertain a current system state; predicting a probable next event according to the current system state and logged events; and identifying acceptable voice commands to perform the next event. The system events include commands, system control activities, timed activities, and application activation. These events are statistically analyzed in light of the current system state to determine the probable next event. The voice commands for performing the probable next event are displayed to the user.

Claims

1. In a computer system adapted for speech recognition, a method for efficiently identifying voice commands for controlling a speech-enabled application running on said system, comprising the steps of:

receiving input from a user;

monitoring said system to log system events and ascertain a current system state;

predicting a probable next event according to said current system state and said logged events; and

identifying acceptable voice commands to perform said next event.

2. The method according to claim 1, further comprising the step of notifying said user of said acceptable voice commands.

3. The method according to claim 2, wherein a dialog window is displayed to notify said user of said acceptable voice commands.

4. The method according to claim 1, wherein said system events include at least one of commands, system control activities, timed activities, and application activation.

5. The method according to claim 1, wherein said probable next event is predicted using a statistical model to analyze said events.

6. The method according to claim 5, wherein past events are used to modify said statistical model.

7. A computer speech recognition system for efficiently identifying voice commands for controlling a speech-enabled application, comprising:

interface means for receiving input from a user;

monitoring means for monitoring said system to log system events and ascertain a current system state;

processor means for predicting a probable next event according to said current system state and said logged events; and

identification means for identifying acceptable voice commands to perform said next event.

8. The system as recited in claim 7, further comprising a display means for notifying said user of said acceptable voice commands.

9. The system as recited in claim 8, wherein a dialog window is displayed to notify said user of said acceptable voice commands.

10. The system as recited in claim 7, wherein said system events include at least one of commands, system control activities, timed activities, and application activation.

11. The system as recited in claim 7, wherein said probable next event is predicted using a statistical model to analyze said events.

12. The system as recited in claim 11, wherein past events are used to modify said statistical model.

13. 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 input from a user;

monitoring said machine to log system events and ascertain a current system state;

predicting a probable next event according to said current system state and said logged events; and

identifying acceptable voice commands to perform said next event.