The goal of this work is to investigate real-time emotion recognition in noisy environments. Our approach is to solve this problem using novel recurrent neural networks called echo state networks (ESN). ESNs utilizing the sequential characteristics of biologically motivated modulation spectrum features are easy to train and robust towards noisy real world conditions. The standard Berlin Database of Emotional Speech is used to evaluate the performance of the proposed approach. The experiments reveal promising results overcoming known difficulties and drawbacks of common approaches.
展开▼
