The authors have developed a robot called “Robovie” that has unique mechanisms designed for communication with humans. Robovie can generate human‐like behaviors by using human‐like actuators and vision and audio sensors. Software is a key element in the systems development. Two important ideas in human‐robot communication through research from the viewpoint of cognitive science have been obtained – one is importance of physical expressions using the body and the other is the effectiveness of the robot’s autonomy in the robot’s utterance recognition by humans. Based on these psychological experiments, a new architecture that generates episode chains in interactions with humans is developed. The basic structure of the architecture is a network of situated modules. Each module consists of elemental behaviors to entrain humans and a behavior for communicating with humans.
Emotion recognition in speech is a topic on which little research has been done to-date. In this paper, we discuss why emotion recognition in speech is a significant and applicable research topic, and present a system for emotion recognition using oneclass-in-one neural networks. By using a large database of phoneme balanced words, our system is speaker-and context-independent. We achieve a recognition rate of approximately 50% when testing eight emotions.
Recognizing human facial expression and emotion by computer is an interesting and challenging problem. Many have investigated emotional contents in speech alone, or recognition of human facial expressions solely from images. However, relatively little has been done in combining these two modalities for recognizing human emotions. De Silva et al. 4 studied human subjects' ability to recognize emotions from viewing video clips of facial expressions and listening to the corresponding emotional speech stimuli. They found that humans recognize some emotions better by audio information, and other emotions better by video. They also proposed an algorithm to integrate both kinds of inputs to mimic human's recognition process. While attempting to implement the algorithm, we encountered di culties which led us to a di erent approach. We found these two modalities to be c omplimentary. By using both, we show it is possible to achieve higher recognition rates than either modality alone.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.