Providing gender to embodied conversational agents

Communication, along with other factors, varies with gender. Significant work as been done around embodied conversational agents (ECAs) verbal and non-verbal behaviour but gender issue has often been ignored. Yet, together with personality, culture and other factors, gender is a feature that impacts the perception and thus the believability of the characters. The main goal of this work is to understand how gender can be provided to ECAs, and provide a very simple model that allows for existing tools to overcome such limitation. The proposed system was developed around SAIBA Framework using SmartBody as the behavior realizer and tries to address this problem by adding a set of involuntary gender specific movements to the agents behaviour in an automatic manner. This is achieved by revising and complementing the work done by the existing non-verbal behaviour generators. Focusing mainly on nonverbal behaviour, our agents with gender were tested to see if users were able to perceive the gender bias of the behaviours being performed. Results have shown that gender is correctly perceived, and also has effects when paired with an accurate gender appearance.