Classifying emotions in speech: a comparison of methods
Noam Amir, Ori Kerret, Dimitry Karlinski · 2001
A number of recent studies have attempted classification of emotional speech using various methods. In this paper we compare the performance of two algorithms: a classification algorithm based on euclidean distances, and a classification algorithm based on the use of neural networks. Both perform the classification using an identical feature set, on a database of emotional speech which has been validated through subjective listening tests.