Method for controlling speech-recognition text-generation system and method for controlling mobile terminal

Patent metadata

Field	Value
Publication number	US-10515633-B2
Application number	US-201715725906-A
Country	US
Kind code	B2
Filing date	Oct 5, 2017
Priority date	Jul 16, 2014
Publication date	Dec 24, 2019
Grant date	Dec 24, 2019

Abstract

A method is provided for controlling a device used in a speech-recognition system, in which the device captures speech. The method includes determining a presence or an absence of an object in proximity to the device. The method also includes controlling capturing speech or not capturing speech in accordance with the determination. In the method, the capturing of speech is performed using a microphone of the device.

First claim

What is claimed is:

1. A method for controlling a device used in a speech-recognition system, in which the device captures speech, the method comprising:
placing the device on a flat surface;
detecting whether the device is in a substantially horizontal position while the device is laying on the flat surface;
determining a presence or an absence of an object in proximity to the device while the device is laying on the flat surface in the substantially horizontal position; and
controlling capturing speech or not capturing speech in accordance with the determination,
wherein the capturing is performed using a microphone of the device,
wherein the device includes a light-emitting part emitting light; and
wherein when the controlling is changed from starting capturing to stopping capturing, or from stopping capturing to starting capturing, the light-emitting part emits visible light and changes color or luminosity of the emitting.

2. The method according to claim 1 ,
wherein the capturing is stopped when it is determined that an object is in proximity to the device, and
wherein the capturing is started when it is determined that no object is in proximity to the device.

3. The method according to claim 1 ,
wherein the capturing is started when it is determined that an object is in proximity to the device, and
wherein the capturing is stopped when it is determined that no object is in proximity to the device.

4. The method according to claim 1 ,
wherein the device includes a display displaying a speech recognition result, and
wherein the light-emitting part is the display.

5. The method according to claim 3 ,
wherein the device includes a display displaying a speech recognition result, and
wherein the light-emitting part is the display.

6. A method for controlling a device used in a speech-recognition system, in which the device captures speech, the method comprising:
placing the device on a flat surface;
detecting whether the device is in a substantially horizontal position while the device is laying on the flat surface;
determining a presence or an absence of an object in proximity to the device while the device is laying on the flat surface in the substantially horizontal position; and
controlling transmitting captured speech to an external device for recognizing the captured speech or not transmitting captured speech to an external device in accordance with the detecting and the determining,
wherein the captured speech is not transmitted to the external device while the object is determined to be in proximity to the device,
wherein the capturing is performed using a microphone of the device, and
wherein recognizing the captured speech is performed using a processor of the external device.

7. A method for controlling a device used in a speech-recognition system, in which the device captures speech, the method comprising:
placing the device on a flat surface;
detecting whether the device is in a substantially horizontal position while the device is laying on the flat surface;
determining a presence or an absence of an object in proximity to the device while the device is laying on the flat surface in the substantially horizontal position;
capturing speech using a microphone of the device,
wherein the captured speech is not transmitted to the external device while the object is determined to be in proximity to the device; and
controlling recognizing the captured speech or not in accordance with the detecting and the determining.

8. A method for controlling a device used in a speech-recognition system, in which the device captures speech, the method comprising,
placing the device on a flat surface;
detecting whether the device is in a substantially horizontal position while the device is laying on the flat surface;
determining a presence or an absence of a user's hand in proximity to the device while the device is laying on the flat surface in the substantially horizontal position; and
controlling capturing speech or not in accordance with the detecting and the determining,
wherein the capturing speech is stopped upon a determination that the user's hand is in proximity to the device, and
wherein the capturing is performed using a microphone of the device.

Assignees

• Panasonic Ip Corp America

Inventors

• Funase Kazuki
• Sakaguchi Atsushi

Classifications

• H04M2250/74

  with voice recognition means · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L2015/221

  Announcement of recognition results · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• H04M1/72522

  Electricity · mapped topic