VOICE DIALOG DEVICE AND VOICE DIALOG METHOD

• US 20170345424A1
• Filed: 05/18/2017
• Published: 11/30/2017
• Est. Priority Date: 05/31/2016
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: IKENO, Atsushi, SHIMADA, Muneaki, HATANAKA, Kota, NISHIJIMA, Toshifumi, KATAOKA, Fuminori, TONEGAWA, Hiromi, UMEYAMA, Norihide
• Granted Patent: US 10,438,586 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/63 for estimating an emotional state

Abstract

A voice dialog device, comprises a voice processing unit configured to obtain a voice pronounced by a user and a result of recognizing the voice; a plurality of estimation units configured to estimate emotion of the user by different methods; and a response unit configured to create a response sentence, based on results of estimating the emotion of the user, and provide the response sentence to the user, wherein when a discrepancy exists between the results of estimating the emotion of the user by the plurality of estimation units, the response unit makes an inquiry to the user, and determines which estimation result is to be adopted, based on content of an obtained response.

Claims

1. A voice dialog device, comprising:

a voice processing unit configured to obtain a voice pronounced by a user and a result of recognizing the voice;

a plurality of estimation units configured to estimate emotion of the user by different methods; and

a response unit configured to create a response sentence, based on results of estimating the emotion of the user, and provide the response sentence to the user, wherein

when a discrepancy exists between the results of estimating the emotion of the user by the plurality of estimation units, the response unit makes an inquiry to the user, and determines which estimation result is to be adopted, based on content of an obtained response.

2. The voice dialog device according to claim 1, wherein

the plurality of estimation units include a first estimation unit configured to estimate the emotion of the user, based on content of a speech by the user, and a second estimation unit configured to estimate the emotion of the user by a method different from a method for the first estimation unit, and wherein

the response unit makes an inquiry to the user when a discrepancy exists between a result of estimating the emotion of the user by the first estimation unit and a result of estimating the emotion of the user by the second estimation unit.

3. The voice dialog device according to claim 2, wherein the inquiry is made to confirm actual emotion, after exhibiting that a discrepancy exists between the result of estimating the emotion of the user by the first estimation unit and the result of estimating the emotion of the user by the second estimation unit.

4. The voice dialog device according to claim 2, wherein the method different from the method for the first estimation unit is the method which estimates the emotion of the user, based on a captured image of a face of the user or the voice obtained from the user.

5. The voice dialog device according to claim 1, wherein the plurality of estimation units estimate the emotion of the user, based on at least one of a captured image of a face of the user, the voice obtained from the user, and content of a speech of the user.

6. The voice dialog device according to claim 5, wherein the inquiry includes information on the methods for estimating the emotion.

7. A voice dialog method executed by a voice dialog device,

the method comprising:

a voice processing step of obtaining a voice pronounced by a user and a result of recognizing the voice;

a plurality of estimating steps for estimating emotion of the user by different methods; and

a responding step of creating a response sentence, based on results of estimating the emotion of the user, and providing the response sentence to the user, wherein

in the responding step, when a discrepancy exists between the results of estimating the emotion of the user by the plurality of estimating steps, an inquiry to the user is made, and a specific estimation result to be adopted is determined, based on content of a response obtained from the user.

8. A non-transitory computer readable storing medium recording a computer program for causing a computer to perform the voice dialog method according to claim 7.

9. A voice dialog device, comprising:

a voice processing unit configured to obtain a voice pronounced by a user and a result of recognizing the voice;

a plurality of estimation units configured to estimate emotion of the user by different methods; and

a response unit configured to create a response sentence, based on results of estimating the emotion of the user, and provide the response sentence to the user, wherein

when a discrepancy exists between the results of estimating the emotion of the user which have been output by the plurality of estimation units, the response unit obtains an estimation history that is results of estimation of emotion performed in past, and resolves the discrepancy, based on the estimation history.

10. The voice dialog device according to claim 9, wherein

the estimation history includes true or false information regarding whether a correct result has been obtained as a result of executing estimation of emotion by the respective estimation units in past, and wherein,

in estimating emotion, the response unit performs weighting for the respective estimation units, based on the true or false information.