DigiHuman: A Converstational Digital Human with Facial Expressions

Recently, Artificial Intelligence (AI)-powered chatbots and virtual humans have assumed significant roles in various domains due to their ability to interact with users and perform tasks based on their intended purpose. Virtual humans have received considerable attention in various industries due to their lifelike human appearance, behaviour, and ability to convey emotions, especially in virtual reality contexts. Conversely, chatbots are finding use in a wide range of applications and represent a promising feature of human-computer interaction due to their efficient communication with humans. Therefore, this study aims to develop a real-time chatbot that can effectively convey emotions through facial expressions, thereby promoting realistic communication. To achieve this, several advanced AI models were employed to address different aspects, including speech recognition, emotion synthesis, and response generation. The methodology, models used, components, and results are explained in detail, and the results of the user study are also presented.