Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People
As agents, social robots are expected to increase opportunities for dialogue with the elderly. However, it is difficult to sustain a dialogue with an elderly user because speech recognition frequently fails during the dialogue. Here, to overcome this problem, regardless of speech recognition failure...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/4/1522 |
| _version_ | 1818863568050716672 |
|---|---|
| author | Takamasa Iio Yuichiro Yoshikawa Mariko Chiba Taichi Asami Yoshinori Isoda Hiroshi Ishiguro |
| author_facet | Takamasa Iio Yuichiro Yoshikawa Mariko Chiba Taichi Asami Yoshinori Isoda Hiroshi Ishiguro |
| author_sort | Takamasa Iio |
| collection | DOAJ |
| description | As agents, social robots are expected to increase opportunities for dialogue with the elderly. However, it is difficult to sustain a dialogue with an elderly user because speech recognition frequently fails during the dialogue. Here, to overcome this problem, regardless of speech recognition failure, we developed a question−answer−response dialogue model. In this model, a robot took initiative in the dialogue by asking the user various questions. Moreover, to improve user experience during dialogue, we extended the model such that two robots could participate in the dialogue. Implementing these features, we conducted a field trial in a nursing home to evaluate the twin-robot dialogue system. The average word error rate of speech recognition was 0.778. Despite the frequently high number of errors, participants talked for 14 min in a dialogue with two robots and felt slightly strange during the dialogue. Although we found no significant difference between a dialogue with one robot and that with two robots, the effect size of the difference in the dialogue time with one robot and that with two robots was medium (Cohen’s d = −0.519). The results suggested that the presence of two robots might likely encourage elderly people to sustain the talk. Our results will contribute to the design of social robots to engage in dialogues with the elderly. |
| first_indexed | 2024-12-19T10:17:49Z |
| format | Article |
| id | doaj.art-02948102ab364dc3ba326cf9f0d7d610 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-19T10:17:49Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-02948102ab364dc3ba326cf9f0d7d6102022-12-21T20:26:09ZengMDPI AGApplied Sciences2076-34172020-02-01104152210.3390/app10041522app10041522Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly PeopleTakamasa Iio0Yuichiro Yoshikawa1Mariko Chiba2Taichi Asami3Yoshinori Isoda4Hiroshi Ishiguro5Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba 305-8573, JapanGraduate School of Engineering Science, Osaka University, Toyonaka 560-0043, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanNTT DOCOMO, Inc., Tokyo 100-6150, JapanGraduate School of Engineering Science, Osaka University, Toyonaka 560-0043, JapanAs agents, social robots are expected to increase opportunities for dialogue with the elderly. However, it is difficult to sustain a dialogue with an elderly user because speech recognition frequently fails during the dialogue. Here, to overcome this problem, regardless of speech recognition failure, we developed a question−answer−response dialogue model. In this model, a robot took initiative in the dialogue by asking the user various questions. Moreover, to improve user experience during dialogue, we extended the model such that two robots could participate in the dialogue. Implementing these features, we conducted a field trial in a nursing home to evaluate the twin-robot dialogue system. The average word error rate of speech recognition was 0.778. Despite the frequently high number of errors, participants talked for 14 min in a dialogue with two robots and felt slightly strange during the dialogue. Although we found no significant difference between a dialogue with one robot and that with two robots, the effect size of the difference in the dialogue time with one robot and that with two robots was medium (Cohen’s d = −0.519). The results suggested that the presence of two robots might likely encourage elderly people to sustain the talk. Our results will contribute to the design of social robots to engage in dialogues with the elderly.https://www.mdpi.com/2076-3417/10/4/1522dialogue systemelderly peopletwo robots |
| spellingShingle | Takamasa Iio Yuichiro Yoshikawa Mariko Chiba Taichi Asami Yoshinori Isoda Hiroshi Ishiguro Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People Applied Sciences dialogue system elderly people two robots |
| title | Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People |
| title_full | Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People |
| title_fullStr | Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People |
| title_full_unstemmed | Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People |
| title_short | Twin-Robot Dialogue System with Robustness against Speech Recognition Failure in Human-Robot Dialogue with Elderly People |
| title_sort | twin robot dialogue system with robustness against speech recognition failure in human robot dialogue with elderly people |
| topic | dialogue system elderly people two robots |
| url | https://www.mdpi.com/2076-3417/10/4/1522 |
| work_keys_str_mv | AT takamasaiio twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople AT yuichiroyoshikawa twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople AT marikochiba twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople AT taichiasami twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople AT yoshinoriisoda twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople AT hiroshiishiguro twinrobotdialoguesystemwithrobustnessagainstspeechrecognitionfailureinhumanrobotdialoguewithelderlypeople |