Speech recognition method and speech recognition apparatus

• US 20070005371A1
• Filed: 06/22/2006
• Published: 01/04/2007
• Est. Priority Date: 06/30/2005
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Hirota, Makoto, Nakagawa, Kenichiro
• Granted Patent: US 7,668,719 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

In an interactive process using speech recognition together with a graphical user interface comprising a plurality of settable graphical user interface items, the recognition rate is improved by reducing recognition target vocabulary. A settable graphical user interface item not displayed on the display screen is detected, and the received speech information is recognized using a speech recognition grammar corresponding to the detected item, and data is set to the item using the recognition result.

Claims

1. An information processing method for setting data to each of a plurality of settable graphical user interface items, the method comprising:

detecting a settable graphical user interface item not displayed on a display screen;

selecting a speech recognition grammar corresponding to the detected item;

recognizing received speech information using the selected speech recognition grammar; and

setting data to the detected item using a recognition result of the recognizing step.

2. The information processing method according to claim 1, wherein the selected speech recognition grammar is speech recognition grammar which is limited to a subset of the speech recognition grammar used in a case where the item is displayed.

3. The information processing method as according to claim 1, wherein the setting step sets data to the detected item by inputting the recognition result into an input field corresponding to the detected item.

4. The information processing method according to claim 1, wherein the setting step sets data to the detected item by selecting from objects to be selected that correspond to the detected item using the recognition result.

5. The information processing method as according to claim 2, wherein the selecting step selects a speech recognition grammar corresponding to a settable graphical user interface item displayed on a display screen, and wherein the recognizing step recognizes received speech information using a limited speech recognition grammar corresponding to the settable graphical user interface item not displayed and a speech recognition grammar corresponding to the displayed settable graphical user interface item.

6. The information processing method as according to claim 2, wherein the speech recognition grammar includes a recognition vocabulary corresponding to the detected settable graphical user interface item and a recognition vocabulary corresponding to data to be set to the detected item, and the limited speech recognition grammar is a speech recognition grammar in which a recognition grammar corresponding to data to be set to the settable graphical user interface item has been precluded from a recognition target.

7. The information processing method according to claim 2, wherein the limited speech recognition grammar is a speech recognition grammar in which a specific vocabulary set has been deleted.

8. An information processing method for setting data to each of a plurality of settable graphical user interface items, the method comprising:

recognizing received speech information using speech recognition grammar corresponding to a settable graphical user interface item which is not displayed in a case where an instruction from an instruction unit which instructs to start speech recognition makes a settable graphical user interface item not displayed on a display screen effective; and

setting the settable graphical user interface item using a recognition result of the recognizing step.

9. An information processing method according to claim 8, wherein the speech recognition grammar corresponding to the settable graphical user interface item which is not displayed is speech recognition grammar which is limited to a subset of the speech recognition grammar used in a case where the settable graphical user interface item is displayed.

10. An information processing method according to claim 9, wherein the recognizing step recognizes received speech information using speech recognition grammar corresponding to a settable graphical user interface item which is displayed, in the case where an instruction from the instruction unit which instructs to start speech recognition, makes a settable graphical user interface item that is displayed on a display screen effective.

11. An information processing method according to claim 10, wherein the instruction unit which instructs to start speech recognition is a button, and wherein there are at least two buttons, one of which makes a settable graphical user interface item displayed on a display screen effective, and another of which makes a settable graphical user interface item which is not displayed on a display screen effective.

12. An information processing method as according to claim 10, wherein the instruction unit which instructs to start speech recognition is at least one of an instruction unit which instructs to start speech recognition upon detecting speech, and an instruction unit which instructs to start speech recognition upon detecting depression of a button.

13. An information processing method comprising:

detecting a settable graphical user interface item not displayed on a display screen;

recognizing received speech information after precluding recognition vocabulary corresponding to the detected settable graphical user interface item as non-recognition target from speech recognition grammar that has one-to-one correspondence with each settable graphical user interface item and includes a recognition vocabulary corresponding to the item and data to be set to the item; and

performing control to display the item in a case where the recognition result of the recognizing step is a recognition vocabulary corresponding to an item that is not displayed.

14. A computer readable medium containing computer-executable instructions for setting data to each of a plurality of settable graphical user interface items, the medium comprising:

computer-executable instructions for detecting a settable graphical user interface item not displayed on a display screen;

computer-executable instructions for selecting a speech recognition grammar corresponding to the detected item;

computer-executable instructions for recognizing received speech information using the selected speech recognition grammar; and

computer-executable instructions for setting data to the detected item using a recognition result of the recognizing step.

15. A computer readable medium containing computer-executable instructions for setting data to each of a plurality of settable graphical user interface items, the medium comprising:

computer-executable instructions for recognizing received speech information using speech recognition grammar corresponding to a settable graphical user interface item which is not displayed in a case where an instruction from an instruction unit which instructs to start speech recognition makes a settable graphical user interface item not displayed on a display screen effective; and

computer-executable instructions for setting the settable graphical user interface item using a recognition result of the recognizing step.

16. A computer readable medium containing computer-executable instructions for implementing information processing control, the medium comprising:

computer-executable instructions for detecting a settable graphical user interface item not displayed on a display screen;

computer-executable instructions for recognizing received speech information after precluding recognition vocabulary corresponding to the detected settable graphical user interface item as non-recognition target from speech recognition grammar that has one-to-one correspondence with each settable graphical user interface item and includes a recognition vocabulary corresponding to the item and data to be set to the item; and

computer-executable instructions for performing control to display the item in a case where the recognition result of the recognizing step is a recognition vocabulary corresponding to an item that is not displayed.

17. An information processing apparatus configured to set data to each of a plurality of settable graphical user interface items, the apparatus comprising:

a detecting unit configured to detect a settable graphical user interface item not displayed on a display screen;

a selecting unit configured to select speech recognition grammar corresponding to the item detected by the detecting unit;

a recognizing unit configured to recognize received speech information using the selected speech recognition grammar; and

a setting unit configured to set data to the detected item using a recognition result from the recognizing unit.

18. An information processing apparatus configured to set data to each of a plurality of settable graphical user interface item, the apparatus comprising:

a detecting unit configured to detect a settable graphical user interface item not displayed on a display screen;

a recognizing unit configured to recognize received speech information using a speech recognition grammar corresponding to a settable graphical user interface item which is not displayed in a case where an instruction from an instruction unit which instructs to start a speech recognition makes a settable graphical user interface item not displayed on a display screen effective; and

a setting unit configured to set the detected item using a recognition result obtained by the recognizing unit.

19. An information processing apparatus comprising:

a detecting unit configured to detect a settable graphical user interface item not displayed on a display screen;

a recognizing unit configured to recognize received speech information after precluding recognition vocabulary corresponding to the data for the detected item as non-recognition target from a speech recognition grammar that has one-to-one correspondence with each settable graphical user interface item and includes a recognition vocabulary corresponding to the settable graphical user interface item and data to be set to the item; and

a display controlling unit configured to perform control to display a settable graphical user interface item not displayed in the case where a recognition result obtained by the recognizing unit is a recognition vocabulary corresponding to the settable graphical user interface item not displayed.