Activation control of a speech recognizer through use of a pointing device

• US 5,857,172 A
• Filed: 07/31/1995
• Issued: 01/05/1999
• Est. Priority Date: 07/31/1995
• Status: Expired due to Term

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Rozak, Michael J.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/506,999
• Time in Patent Office: 1,254 Days
• Field of Search: 395/2.84, 395/2.82, 395/2, 704/270
• US Class Current: 704/275
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A speech recognition system includes a facility for toggling the state of the speech recognition system solely in response to a user using a pointing input device, such as a mouse. In one embodiment of the present invention, a user designates a predetermined area of a display surface on a video display to be a hot region. When a mouse cursor points to a location within the hot region, the speech recognition system is put in a listening state wherein the speech recognition system is listening for and processing audio input. When the mouse cursor is moved so as to no longer lie within the designated hot region, the state of the speech recognition system is changed back to the state that immediately preceded the listening state. The previous state may be a not listening state where an audio input is not processed by the speech recognition system or a standing-by state wherein only selected audio input is processed by the speech recognition system.

Claims

1. In a computer system having a video display, an audio input device for receiving audio input, an input device for positioning a cursor on the video display and a speech recognizer for recognizing components of speech in the audio input, a method of comprising the computer-implemented steps of:

providing a designated hot region on the video display for activating the speech recognizer;

positioning the cursor over the hot region in response to a user using the input device for positioning the cursor; and

activating the speech recognizer so that the speech recognizer processes audio input that is received through the audio input device, the activation of the speech recognizer being caused by the cursor being positioned over the hot region.

2. The method of claim 1 further comprising the step of changing the hot region to be a new region on the video display in response to a request by a user.

3. The method of claim 1 further comprising the step of providing at least one additional hot region on the video display for activating the speech recognizer.

4. The method of claim 1 further comprising the steps of:

positioning the cursor so that it is no longer over the hot region in response to the user using the input device for positioning the cursor; and

deactivating the speech recognizer so that the speech recognizer does not process the audio input that is received through the audio input device, the deactivation of the speech recognizer being caused by the cursor no longer being over the hot region.

5. The method of claim 1 wherein immediately before the cursor is positioned over the hot region, the speech recognizer is in a non-listening state wherein the speech recognizer is not processing audio input received from the audio input device.

6. The method of claim 1 wherein the computer system further comprises a voice command unit for identifying and responding to voice commands in the components of speech that are recognized by the speech recognizer, and wherein before the cursor is positioned over the hot region, the speech recognizer processes audio input and the voice command unit only responds to voice commands that are prefaced by a trigger phrase.

7. The method of claim 1 wherein the input device for positioning the cursor on the video display is a mouse.

8. A computer system comprising:

a pointing input device;

an audio input device for receiving audio input;

a speech recognizer for recognizing components of speech in the audio input received by the audio input device;

a triggering mechanism for triggering the speech recognizer so that the speech recognizer is active and processing the audio input;

a video display;

a cursor that moves on the video display in response to the user using the pointing input device; and

a hot region on the video display wherein the triggering mechanism automatically triggers the speech recognizer to be active when at least a portion of the cursor is over the hot region.

9. The computer system of claim 8 wherein the pointing input device is a mouse.

10. The computer system of claim 8 further comprising a deactivating mechanism for deactivating the speech recognizer so that the speech recognizer does not process the audio input when no portion of the cursor remains over the hot region.

11. The computer system of claim 8 further comprising an additional hot region that causes the trigger mechanism to automatically trigger the speech recognizer to be active when at least a portion of the cursor is over the additional hot region.

12. The computer system of claim 8 further comprising a hot region modifier for changing the hot region to occupy a different portion of the video display.

13. The computer system of claim 12 wherein the hot region modifier provides a user interface that enables the user to select the different portion of the video display that the hot region is to occupy.

14. The computer system of claim 8 further comprising a deactivating mechanism for deactivating the speech recognizer in response to the user using the pointing input device so that the speech recognizer does not process audio input.

15. A computer readable storage medium for use with a computer system that includes a video display, an audio input device for receiving audio input and a pointing input device, said storage medium storing:

a speech recognizer for recognizing components of speech in audio input from the audio input device; and

a triggering mechanism for automatically triggering the speech recognizer to be active so that the speech recognizer processes audio input from the audio input device when a user uses the pointing input device to point at a hot region on the video display.

16. The storage medium of claim 15 further storing a deactivating mechanism for deactivating the speech recognizer in response to the user using the pointing input device such that the speech recognizer does not process the audio input.