Simplified classification in multimodal affect detection using vocal and facial information
Aect detection or emotion recognition plays an important role in the interaction of multimedia and social media, especially in rapidly developing digital media. It is necessary and helpful to import emotional taste into the course of communications between human and digital media, including video game, videoconference, instant messenger (such as Twitter, Wechat and QQ) and intelligent personal assistant (such as Siri and Google Now). Digital media should be able to interact in a friendly manner with a human. If digital media understand the emotional state of a human and responds the need of a person, our society will be more enjoyable in the future. The goal of our research is to develop software and hardware architecture which can perceive human feelings or mental states.