Presentation 2021-05-25
Development of a Job Interview Training System with Multi-modal Behavior Analysis
Nao Takeuchi, Tomoko Koda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper introduces a job interview training system that recognizes the nonverbal behaviors of the interviewee, namely, gaze, facial expression, and posture. The proposed system uses a Tobii eye tracker for gaze recognition, and camera images for facial expression and posture recognition. The system compares the recognition results with the models of the interviewee's exemplary nonverbal behaviors and point out the non-verbal behaviors that need improvement while playing back the interview recording. Our development policy of the system is to construct an inexpensive and easy system using commercially available HWs and open source, and utilization of a CG agent that gives feedback to the interviewee. Most of the current interview training systems require high-end HW and SW and are not designed for general users, and there are few systems using CG agents to give feedback. The results of the initial evaluation of the system indicate improvements are needed in terms of recognition accuracy of non-verbal behaviors and quality of the interaction with the CG agent.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) gaze recognition / posture recognition / facial expression recognition / job interview training / nonverbal behaviors / CG agent / multi-modal interaction
Paper # HCS2021-10,HIP2021-10
Date of Issue 2021-05-17 (HCS, HIP)

Conference Information
Committee HCS / HIP / HI-SIGCE
Conference Date 2021/5/24(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Communication Enhancing, Human Communications, and Human Information Processing
Chair Tomoo Inoue(Univ. of Tsukuba) / Shuichi Sakamoto(Tohoku Univ.)
Vice Chair Yugo Hayashi(Ritsumeikan Univ.) / Tomoko Kanda(Osaka Inst. of Tech.) / Yuji Wada(Ritsumeikan Univ.) / Sachiko Kiyokawa(U. Tokyo)
Secretary Yugo Hayashi(Kanazawa Inst. of Tech.) / Tomoko Kanda(KDDI Research) / Yuji Wada(Osaka Univ. of Economic) / Sachiko Kiyokawa(NICT) / (NTT)
Assistant Kazunori Terada(Gifu Univ.) / Atsushi Kimura(Nihon Univ.) / HUANG HUNGHSUAN(Univ. of Fukuchiyama) / Shigeyoshi Iizuka(Kanagawa Univ.) / Masashi Komori(Osaka Electro-Comm. Univ.) / Kazuki Takashima(Tohoku Univ.) / Hidetoshi Kanaya(Ritsumeikan Univ.) / Yuki Yamada(Kyushu Univ.)

Paper Information
Registration To Technical Committee on Human Communication Science / Technical Committee on Human Information Processing / Special Interest Group on Communication Enhancement
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Development of a Job Interview Training System with Multi-modal Behavior Analysis
Sub Title (in English)
Keyword(1) gaze recognition
Keyword(2) posture recognition
Keyword(3) facial expression recognition
Keyword(4) job interview training
Keyword(5) nonverbal behaviors
Keyword(6) CG agent
Keyword(7) multi-modal interaction
1st Author's Name Nao Takeuchi
1st Author's Affiliation Osaka Institute of Technology(OIT)
2nd Author's Name Tomoko Koda
2nd Author's Affiliation Osaka Institute of Technology(OIT)
Date 2021-05-25
Paper # HCS2021-10,HIP2021-10
Volume (vol) vol.121
Number (no) HCS-37,HIP-38
Page pp.pp.50-54(HCS), pp.50-54(HIP),
#Pages 5
Date of Issue 2021-05-17 (HCS, HIP)