Voice interaction apparatus and automatic interaction method using voice interaction apparatus

• US 10,339,930 B2
• Filed: 09/05/2017
• Issued: 07/02/2019
• Est. Priority Date: 09/06/2016
• Status: Active Grant

• Current Assignee: Kyoto University, Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Kawahara, Tatsuya, Takanashi, Katsuya, Nakanishi, Ryosuke, Watanabe, Narimasa
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US15/695,090
• Publication Number:
  US 20180068660A1
• Time in Patent Office: 665 Days
• Field of Search: None
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

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.

Claims

1. A voice interaction apparatus comprising:

an interactive robot comprising;

a pseudo head;

a microphone configured to detect an input speech spoken by a user;

a speaker configured to output an output speech spoken to the user; and

a processor configured to;

estimate a change probability that indicates whether to wait for the input of the input speech by the microphone, or to execute the output of the output speech by the speaker, based on the input speech detected by the microphone; and

if the change probability falls within a predetermined subset range, control the voice interaction apparatus to respond by executing at least one of a filler output and a nodding action,

wherein the filler output is an output of a filler from the speaker, the filler being a connecting utterance irrelevant to an interaction content, and

wherein the nodding action is an action of swinging the pseudo head back and forth.

2. The voice interaction apparatus according to claim 1, wherein the processor is further configured to analyze prosody of the input speech detected by the microphone, wherein the processor is configured to estimate whether to wait for the input of the input speech by the microphone or to execute the output of the output speech by the speaker based on the prosody analyzed by the processor.

3. The voice interaction apparatus according to claim 1, wherein when the change probability falls within the predetermined subset range and is smaller than a first threshold set in the predetermined subset range, the processor responds by executing the nodding action, while when the change probability is greater than a second threshold that is set in the predetermined subset range and that is greater than or equal to the first threshold, the processor responds by executing the filler output.

4. The voice interaction apparatus according to claim 1, wherein when the processor continuously executes the filler output without executing the output of the output speech by the speaker, the processor is more likely to estimate that the output of the output speech should be executed.

5. The voice interaction apparatus according to claim 1, wherein when the input of the input speech by the microphone is detected while executing the filler output, the processor is more likely to estimate that the input of the input speech is being waited for.

6. An automatic interaction method using a voice interaction apparatus including a microphone configured to detect an input speech spoken by a user and a speaker configured to output an output speech spoken to the user, the automatic interaction method comprising:

estimating, with a processor, a change probability that indicates whether to wait for the input of the input speech by the microphone or to execute the output of the output speech by the speaker based on the input speech detected by the microphone;

determining, with the processor, that the change probability falls within a predetermined subset range; and

responding by executing, when the change probability falls within the predetermined subset range, at least one of a filler output and a nodding action, the filler output being an output of a filler from the speaker,

wherein the voice interaction apparatus is an interactive robot that further includes a pseudo head,

wherein the filler is a connecting utterance irrelevant to an interaction content, and

wherein the nodding action is an action of swinging the pseudo head back and forth.