TOP > 外国特許検索 > Voice interaction apparatus and automatic interaction method using voice interaction apparatus

Voice interaction apparatus and automatic interaction method using voice interaction apparatus UPDATE

外国特許コード F180009591
整理番号 5559
掲載日 2018年11月16日
出願国 アメリカ合衆国
出願番号 201715695090
公報番号 20180068660
出願日 平成29年9月5日(2017.9.5)
公報発行日 平成30年3月8日(2018.3.8)
優先権データ
  • 特願2016-173862 (2016.9.6) JP
発明の名称 (英語) Voice interaction apparatus and automatic interaction method using voice interaction apparatus UPDATE
発明の概要(英語) Provided is a voice interaction apparatus including an estimation unit configured to estimate whether to wait a next user's speech or to execute an output of an output speech by the voice interaction apparatus based on a user's speech input by an input unit; and the response control unit configured to, when the estimation unit could not estimate whether to wait for the user's next speech or to execute the output of the output speech by the voice interaction apparatus, respond by executing at least one of a filler output and a nodding action, the filler output being an output of a filler, i.e., a connecting utterance irrelevant to an interaction content, from the output unit, and the nodding action being an action of swinging a pseudo head part back and forth.
従来技術、競合技術の概要(英語) BACKGROUND
The present disclosure relates to a voice interaction apparatus and an automatic interaction method using the voice interaction apparatus.
The technique for enabling users to enjoy everyday conversations with voice interactive robots is becoming widespread.For example, as a technique for realizing a conversation with no unnatural impression, a technique is known in which an interactive robot makes a backchannel response at appropriate timings by analyzing prosody of a user's speech (see Japanese Unexamined Patent Application Publication No. 2009-3040).Further, studies have been conducted on seeking timings at which a speaker is changed between a user and a robot (see Cognitive Science Research Paper Vol. 7 (2000) No. 1, pp. 93-106).
特許請求の範囲(英語) [claim1]
1. A voice interaction apparatus comprising:
an input unit configured to input an input speech spoken by a user;
an output unit configured to output an output speech spoken to the user;
an estimation unit configured to estimate whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit based on the input speech input by the input unit; and
the response control unit configured to, when the estimation unit could not estimate whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit, respond by executing at least one of a filler output and a nodding action, the filler output being an output of a filler from the output unit, the filler being a connecting utterance irrelevant to an interaction content, and the nodding action being an action of swinging a pseudo head part back and forth.
[claim2]
2. The voice interaction apparatus according to claim 1, further comprising an analysis unit configured to analyze prosody of the input speech input by the input unit, wherein the estimation unit is configured to estimate whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit based on the prosody analyzed by the analysis unit.
[claim3]
3. The voice interaction apparatus according to claim 2, wherein
the estimation unit calculates an estimation value for estimating whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit based on the prosody analyzed by the analysis unit, and
when the estimation value calculated by the estimation unit falls within a predetermined range where it is not possible to estimate whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit, the response control unit responds by executing at least one of the filler output and the nodding action.
[claim4]
4. The voice interaction apparatus according to claim 3, wherein when the estimation value falls within the predetermined range of a probability specifying that the output of the output speech should be executed and is smaller than a first threshold set in the predetermined range, the response control unit responds by executing the nodding action, while when the estimation value is greater than a second threshold that is set in the predetermined range and that is greater than or equal to the first threshold, the response control unit responds by executing the filler output.
[claim5]
5. The voice interaction apparatus according to claim 1, wherein when the response control unit continuously executes the filler output without executing the output of the output speech by the output unit, the estimation unit is more likely to estimate that the output of the output speech should be executed.
[claim6]
6. The voice interaction apparatus according to claim 1, wherein when the input of the input speech by the input unit is detected while executing the filler output, the estimation unit is more likely to estimate that the input of the input speech is being waited for.
[claim7]
7. An automatic interaction method using a voice interaction apparatus comprising an input unit configured to input an input speech spoken by a user and an output unit configured to output an output speech spoken to the user, the automatic interaction method comprising:
estimating whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit based on the input speech input by the input unit; and
responding by executing, when it could not have been estimated in the estimating whether to wait for the input of the input speech by the input unit or to execute the output of the output speech by the output unit, at least one of a filler output and a nodding action, the filler output being an output of a filler from the output unit, the filler being a connecting utterance irrelevant to an interaction content, and the nodding action being an action of swinging a pseudo head part back and forth.
  • 発明者/出願人(英語)
  • Kawahara Tatsuya
  • Takanashi Katsuya
  • Nakanishi Ryosuke
  • Watanabe Narimasa
  • KYOTO UNIVERSITY
  • TOYOTA MOTOR
国際特許分類(IPC)
ライセンスをご希望の方、特許の内容に興味を持たれた方は、下記までご連絡ください。

PAGE TOP

close
close
close
close
close
close