Voice dialog device and voice dialog method

Patent metadata

Field	Value
Publication number	US-10395653-B2
Application number	US-201715598504-A
Country	US
Kind code	B2
Filing date	May 18, 2017
Priority date	May 27, 2016
Publication date	Aug 27, 2019
Grant date	Aug 27, 2019

Abstract

A voice dialog device, comprises a sight line detection unit configured to detect a sight line of a user; a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice; a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and an answer generation unit configured to generate an answer, based on a result of recognizing the voice, wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice.

First claim

What is claimed is:

1. A voice dialog device, comprising:
a sight line detection unit configured to detect a sight line of a user;
a state determination unit configured to determine a state of the user;
a voice processing unit configured to obtain voice pronounced by the user and a result of recognizing the voice;
a dialog determination unit configured to determine whether or not the voice dialog device has a dialog with the user; and
an answer generation unit configured to generate an answer, based on a result of recognizing the voice,
wherein the dialog determination unit determines whether or not the user has started the dialog, based on both the sight line of the user and the obtained voice by:
when the determined state of the user is driving a vehicle, the detected sight line of the user is in a vehicle forward direction, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog,
when the determined state of the user is driving a vehicle and either the detected sight line of the user is not in the vehicle forward direction or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog,
when the determined state of the user is not driving a vehicle, the detected sight line of the user is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice, the dialog determination unit determines that the user has started a dialog, and
when the determined state of the user is not driving a vehicle and either the detected sight line of the user is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the dialog determination unit determines that the user has not started a dialog.

2. The voice dialog device according to claim 1 , wherein
when the voice dialog device has the dialog with the user and a termination keyword has been detected from the voice, the dialog determination unit determines that the dialog has been terminated.

3. A voice dialog method performed by a voice dialog device, comprising:
a sight line detecting step of detecting a sight line of a user;
a state determining step of determining a state of the user;
a voice processing step of obtaining voice pronounced by the user and a result of recognizing the voice;
a dialog determining step of determining whether or not the voice dialog device has a dialog with the user; and
an answer generating step of generating an answer, based on a result of recognizing the voice,
wherein, the dialog determining step includes determining whether or not the user has started the dialog based on both the sight line of the user and the obtained voice by:
when state of the user determined by the state determining step is driving a vehicle, the sight line of the user detected by the sight line detecting step is in a vehicle forward direction, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog,
when the state of the user determined by the state determining step is driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the vehicle forward direction or the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog,
when the state of the user determined by the state determining step is not driving a vehicle, the sight line of the user detected by the sight line detecting step is in a direction toward the voice dialogue device, and a start keyword has been detected from the voice by the voice processing step, the dialog determining step determines that the user has started a dialog, and
when the state of the user determined by the state determining step is not driving a vehicle and either the sight line of the user detected by the sight line detecting step is not in the direction toward the voice dialogue device or the start keyword has not been detected from the voice, the start keyword has not been detected from the voice by the voice processing step, the dialog determining step determines that the user has not started a dialog.

4. A non-transitory computer readable storing medium recording a computer program for causing a computer to perform the voice dialog method according to claim 3 .

Assignees

• Toyota Motor Co Ltd

Inventors

• Ikeno Atsushi
• Shimada Muneaki
• HATANAKA Kota
• Nishijima Toshifumi
• Kataoka Fuminori
• Tonegawa Hiromi
• Umeyama Norihide

Classifications

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06F2203/0381

  Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer · CPC title

• G06F3/0304

  Detection arrangements using opto-electronic means (constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042) · CPC title

• G10L15/22 Primary

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

• G10L15/08

  Speech classification or search · CPC title