Emotion recognition from speech signals via a probabilistic echo-state network

The paper presents a probabilistic echo-state network (pi-ESN) for density estimation over variable-length sequences of multivariate random vectors. The pi-ESN sterns from the combination of the reservoir of an ESN and a parametric density model based on radial basis functions. A constrained maximum likelihood training algorithm is introduced, suitable for sequence classification. Extensions of the algorithm to unsupervised clustering and semi-supervised learning (SSL) of sequences are proposed. Experiments in emotion recognition from speech signals are conducted on the WaSeP (c) dataset. Compared with established techniques, the pi-ESN yields the highest recognition accuracies, and shows interesting clustering and SSL capabilities.