Spoken dialog system, spoken dialog device, user terminal, and spoken dialog method, retrieving past dialog for new participant

Patent metadata

Field	Value
Publication number	US-11024286-B2
Application number	US-201716348471-A
Country	US
Kind code	B2
Filing date	Nov 6, 2017
Priority date	Nov 8, 2016
Publication date	Jun 1, 2021
Grant date	Jun 1, 2021

Abstract

In order to solve a conventional problem that, after a series of dialog between a user and a spoken dialog device has progressed to some extent, that user or another user cannot see or recognize a previous dialog status, a cross-lingual spoken dialog system is provided wherein, in a case in which an instruction from a user terminal is received by a pairing server, dialog information stored in a storage medium is transmitted to the user terminal. Accordingly, even after a series of dialog between a user and the spoken dialog device has progressed to some extent, that user or another user can see or recognize a previous dialog status.

First claim

The invention claimed is:

1. A cross-lingual spoken dialog system, comprising:
a storage medium; and
a processor and a memory storing a program, wherein the program, wherein:
dialog information, which is information of a series of dialog, is being accumulated in the storage medium, the dialog information having:
an input speech text that is a speech recognition result of an input speech input by a user,
one or more input speech translation results that are generated from the input speech text,
a response text that is a response from the system to the input speech text, and
a response translation result that is generated from the response text, and

during a progress of a dialog in the cross-lingual spoken dialog system, the program when executed by the processor, causes the processor to operate such that, in a case in which a pairing instruction is received from a user terminal of a new user who has not participated in the dialog, pairing processing with the user terminal is performed, and the dialog information accumulated in the storage medium is transmitted to the user terminal.

2. A spoken dialog device comprising:
a dialog information storage medium; and
a processor and a memory storing a program, wherein the program, when executed by the processor, causes the processor to perform:
accepting an input speech that is input by a user and can be input in two or more different languages;
performing speech recognition on the input speech, thereby generating an input speech text that is a speech recognition result;
generating a response text that is a response to the input speech text, using the input speech text;
generating one or more input speech translation results from the input speech text, and generating one or more response translation results from the response text;
acquiring an audio speech according to the response text;
outputting the audio speech;
accumulating, in the dialog information storage medium, dialog information, which is information of a series of dialog, the dialog information comprising the input speech text and the response text;
receiving a pairing instruction from a user terminal of a new user who has not participated in the series of dialog; and
transmitting, in a case in which the pairing instruction from the user terminal is received, the dialog information accumulated in the dialog information storage medium, which is the information of the series of dialog, to the user terminal.

3. The spoken dialog device according to claim 2 ,
wherein in the accepting, an input speech from the user terminal is accepted as well, and
the program, when executed by the processor, further causes the computer to perform, in a case in which an input speech from the user terminal is accepted, generating a response text that is a response to an input speech text corresponding to the input speech from the user terminal, from the input speech text, and transmitting the response text to the user terminal.

4. The spoken dialog device according to claim 3 ,
wherein the program, when executed by the processor, causes the computer to perform accepting point information indicating one point in the dialog information of the series of dialog, and generating a response text that is a response to the input speech text corresponding to the input speech from the user terminal, from the input speech text, using information of a dialog in the dialog information, the information being information of a dialog up to a point corresponding to the point information.

5. A spoken dialog method using a storage medium in which dialog information, which is information of a series of dialog, is accumulated, the dialog information having an input speech text that is a speech recognition result of an input speech input by a user, one or more input speech translation results that are generated from the input speech text, a response text that is a response from a system to the input speech text, and a response translation result that is generated from the response text, the method comprising:
a step of receiving a pairing instruction from a user terminal of a new user who has not participated in the series of dialog, during a progress of the series of dialog in a cross-lingual spoken dialog system;
a step of performing pairing processing with the user terminal in a case of receiving the pairing instruction; and
a step of transmitting the dialog information accumulated in the storage medium, which is the information of the series of dialog, to the user terminal.

Assignees

• Nat Inst Inf & Comm Tech

Inventors

• Hiroe Atsuo
• Okamoto Takuma
• Kidawara Yutaka

Classifications

• H04W4/06

  Selective distribution of broadcast services, e.g. multimedia broadcast multicast service [MBMS]; Services to user groups; One-way selective calling services · CPC title

• G06F40/58

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G10L15/28

  Constructional details of speech recognition systems · CPC title

• H04W4/00

  Services specially adapted for wireless communication networks; Facilities therefor · CPC title

• G10L13/00 Primary

  Speech synthesis; Text to speech systems · CPC title