Speech processing apparatus and control method thereof

• US 8,046,231 B2
• Filed: 10/03/2007
• Issued: 10/25/2011
• Est. Priority Date: 10/06/2006
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Hirota, Makoto, Fukada, Toshiaki
• Primary Examiner(s): Neway; Samuel G
• Application Number:
  US11/866,604
• Publication Number:
  US 20080086306A1
• Time in Patent Office: 1,483 Days
• Field of Search: 704231-257, 704270-278
• 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 2015/228 of application context
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

An speech processing apparatus comprises a setting unit that sets an association between a speech recognition target vocabulary and the shortcut data for transitioning to a state to which a transition is made, when a user makes a transition to a state among the plurality of states using an operation input unit, an speech input unit that inputs an audio, a speech recognition unit that employs the speech recognition target vocabulary to recognize the audio that is input via the speech input unit, and a control unit that employs the shortcut data that corresponds to the speech recognition target vocabulary that is a recognition result of the speech recognition unit to transition to the state, in order to improve speech recognition accuracy for audio shortcuts, while also preserving the convenience of the audio shortcuts.

Claims

1. A speech processing apparatus adapted to display a plurality of screens of a hierarchical menu and set shortcut data that provides a shortcut to each respective screen, the speech processing apparatus comprising:

a selecting unit adapted to select a screen from among the plurality of screens;

a determination unit adapted to determine whether the selected screen corresponds to a level which is deeper than a predetermined depth from a root level of the hierarchical menu;

a storing unit adapted to register, in a case where it is determined that the selected screen corresponds to the level which is deeper than the predetermined depth, a speech recognition target vocabulary corresponding to the selected screen to a speech recognition grammar, and to associate and store the registered speech recognition target vocabulary and a shortcut data for transitioning to the selected screen;

a speech input unit adapted to input a speech;

a speech recognition unit adapted to recognize the speech that is input via the speech input unit using the speech recognition grammar; and

a control unit adapted to display, by using the shortcut data corresponding to the recognized speech recognition target vocabulary, the screen corresponding to the recognized speech recognition target vocabulary,

wherein, in a case where it is determined that the selected screen does not correspond to the level which is deeper than the predetermined depth, the storing unit does not register the speech recognition target vocabulary corresponding to the selected screen, and does not associate and store the registered speech recognition target vocabulary and the shortcut data for transitioning to the selected screen.

2. A method for a speech processing apparatus adapted to display a plurality of screens of a hierarchical menu and set shortcut data that provides a shortcut to each respective screen, the method comprising:

selecting screen from among the plurality of screens;

determining whether the selected screen corresponds to a level which is deeper than a predetermined depth from a root level of the hierarchical menu;

registering, in a case where it is determined that the selected screen corresponds to the level which is deeper than the predetermined depth, a speech recognition target vocabulary corresponding to the selected screen to a speech recognition grammar, and associating and storing the registered speech recognition target vocabulary and a shortcut data for transitioning to the selected screen;

inputting a speech;

recognizing the input speech using the speech recognition grammar; and

displaying, using a control unit and by using the shortcut data corresponding to the recognized speech recognition target vocabulary, the screen corresponding to the recognized speech recognition target vocabulary,

wherein, in a case where it is determined that the selected screen does not correspond to the level which is deeper than the predetermined depth, registering does not include registering the speech recognition target vocabulary corresponding to the selected screen, and does not include associating and storing the registered speech recognition target vocabulary and the shortcut data for transitioning to the selected screen.

3. A non-transitory computer-readable storage medium storing a program that causes a speech processing apparatus adapted to perform a method to display a plurality of screens of a hierarchical menu and set shortcut data that provides a shortcut to each respective screen, the method comprising:

selecting a screen from among the plurality of screens;

determining whether the selected screen corresponds to a level which is deeper than a predetermined depth from a root level of the hierarchical menu;

registering, in a case where it is determined that the selected screen corresponds to the level which is deeper than the predetermined depth, a speech recognition target vocabulary corresponding to the selected screen to a speech recognition grammar, and associating and storing the registered speech recognition target vocabulary and a shortcut data for transitioning to the selected screen;

inputting a speech;

recognizing the input speech using the speech recognition grammar; and

displaying, using a control unit and by using the shortcut data corresponding to the recognized speech recognition target vocabulary, the screen corresponding to the recognized speech recognition target vocabulary,

wherein, in a case where it is determined that the selected screen does not correspond to the level which is deeper than the predetermined depth, registering does not include registering the speech recognition target vocabulary corresponding to the selected screen, and does not include associating and storing the registered speech recognition target vocabulary and the shortcut data for transitioning to the selected screen.