Real-Time Emotion Recognition Using Echo State Networks

The goal of this work is the exploration of real-time emotion recognition from speech. In this approach a novel type of recurrent neural networks called echo state networks (ESN) are utilized. Biologically motivated features representing modulations of the speech signal are used as input to the ESNs. The standard Berlin Database of Emotional Speech is used to evaluate the performance of the proposed approach. However, in this paper ongoing work is being presented and the final architecture has yet to be determined.