Controlling speech recognition functionality in a computing device

• US 7,369,997 B2
• Filed: 08/01/2001
• Issued: 05/06/2008
• Est. Priority Date: 08/01/2001
• Status: Active Grant

• Current Assignee: Zhigu Holdings Limited
• Original Assignee: Microsoft Corporation
• Inventors: Lui, Charlton E., Chambers, Robert
• Primary Examiner(s): OPSASNICK, MICHAEL N
• Application Number:
  US09/918,723
• Publication Number:
  US 20030028382A1
• Time in Patent Office: 2,470 Days
• Field of Search: 704/235, 704/270, 704/275, 345/348, 345/978, 345/533, 345163-168
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

A system and method for use in computing systems that employ speech recognition capabilities is provided. Where recognized speech can be dictation and commands, one or more buttons may be used to change modes of said computing systems to accept spoken words as dictation, or to accept spoken words as commands, as well as activate a microphone used for the speech recognition. The change in mode may occur responsive to the manner in which a button is pressed, where the manner may include such depressions as taps, press and holds, thumbwheel slides, and other forms of button manipulation.

Claims

1. A method for use in a computing device having a microphone and a button, comprising the steps of:

activating said microphone;

receiving a user input on said button,

placing said device in an operating mode corresponding to a dictation mode when said user input is of a first type;

modifying the operating mode to place said device in a command mode when said user input is of a second type;

wherein said device identifies spoken words as text in said dictation mode, and as commands in said command mode; and

providing an indication either visually or audibly to a user of said device as to whether said device is in said dictation mode or said command mode prior to identifying spoken words as text or commands,

wherein the user can enter a temporary mode, which is one of either a dictation mode or a command mode, different from the mode the user is currently presiding by pressing and holding down said button, where the user stays in the temporary mode for the duration the button is held down and exits the temporary mode upon releasing of the button, which causes the user to enter back into the current mode.

2. The method of claim 1, wherein said first type of user input actuating said button is a tap of said button.

3. The method of claim 1, wherein said first type of user input actuating said button is a rotation of said button.

4. The method of claim 1, wherein said button is a graphical user interface button.

5. The method of claim 1, wherein said indication is provided on a display of said device.

6. The method of claim 1, wherein said indication is provided by a lighting element of said device external to a display area.

7. The method of claim 1, wherein said indication is provided as an audible signal.

8. The method of claim 1, wherein said button has multiple states of depression, and said first and second types of user input actuating said button are first and second states of depression of said button.

9. The method of claim 1, further comprising the step of deactivating said microphone responsive to a manner in which said button is depressed.

10. The method of claim 1, further comprising the step of deactivating said microphone upon the expiration of a predetermined time period during which no spoken words are identified.

11. A computer-readable medium having computer-executable instructions for performing the steps recited in claim 1.

12. The method of claim 1, wherein after a predetermined amount of time, if spoken words are note detected, the microphone is deactivated and the system exits the current mode.

13. The method of claim 1, wherein said first type of user input actuating said button is a press and release of said button.

14. The method of claim 13, wherein said second type of user input actuating said button is a press and hold of said button.

15. The method of claim 1, wherein said device is toggled between said dictation mode and said command mode if said button is actuated by pressing and releasing.

16. The method of claim 15, wherein said device identifies spoken words while said button is actuated by pressing and holding.

17. A personal computing device, comprising:

a processor;

a memory;

a display, communicatively coupled to said processor;

a microphone, communicatively coupled to said processor;

a button, communicatively coupled to said processor;

a speech-recognition program, stored in said memory, for causing said processor to recognize audible sounds detected by said microphone;

a first program module, stored in said memory, for causing said processor to activate said microphone;

a second program module, stored in said memory, for causing said processor to enter an operating mode corresponding to a command mode responsive to said button being pressed in a first manner and notifying a user either audibly or visually of entering said command mode; and

a third program module, stored in said memory, for causing said processor to modify the operating mode to correspond to a dictation mode responsive to said button being pressed in a second manner, and notifying a user either audibly or visually of entering said dictation mode, wherein spoken words recognized in said dictation mode are handled by said processor as textual data, and spoken words recognized in said command mode are handled by said processor as commands requiring execution of one or more additional functions,

wherein the user can enter a temporary mode, which is one of either a dictation mode or a command mode, different from the mode the user is currently presiding by pressing and holding down said button, where the user stays in the temporary mode for the duration the button is held down and exits the temporary mode upon releasing of the button, which causes the user to enter back into the current mode.

18. The device of claim 17, wherein said first speech-recognition program, first program module, second program module, and third program module, are all part of a single computer program.

19. The device of claim 17, wherein said second program module causes said processor to enter said command mode if said button is pressed and held.