Job Interview Training System using Multimodal Behavior Analysis

Abstract

The paper introduces our system that recognizes the nonverbal behaviors of an interviewee, namely gaze, facial expression, and posture using a Tobii eye tracker and cameras. The system compares the recognition results with those of models of exemplary nonverbal behaviors of an interviewee and highlights the behaviors that need improvement while playing back the interview recording. The development goal for our system was to construct an inexpensive and easy-to-use system using commercially available HWs, open-source code, and a CG agent that would provide feedback to the interviewee. The results of the initial evaluation of the system indicate that improvements in the recognition accuracy of nonverbal behaviors and the quality of the interaction with the CG agent are needed.