The effects of listening agent in speech-based on-line test system

Speech-based test is a one of the best ways to train students´ level of proficiency. However, in e-learning it is difficult for students to maintain their concentration when speaking to a monitor. We propose speech-based online test system employing a human-likely embodied graphical agent as a listener. The developed system consists of three modules, user recognition, agent´s non-verbal behavior realization, and learning controller. The system is developed with HTML5, Javascript, and WebGL, so that it should be compatible with any modern Web-browsers. To investigate the effects of the use of the listener agent in speech-based test on learning efficacy and naturalness of speech, we will conduct a one-way between-subject design experiment with three groups. In experimental group, participants speech to a listening agent with listener behavior depicted on a monitor during a speech-based test. On the other hand, in first control group, participants take the test with the listening agent but the agent does not move while the participants´ speech. In second control group, participants take the test without the listening agent. Then, the result of listening scores will be statistically tested.