EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology
2nd INTERSPEECH Event

Aalborg, Denmark
September 3-7, 2001

                 

Classifying Emotions in Speech: A Comparison of Methods

Noam Amir (1), Ori Kerret (2), Dimitry Karlinski (2)

(1) Holon Academic Institute of Technology, Israel
(2) Academic College of Tel Aviv, Yaffo, Israel

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.

Full Paper

Bibliographic reference.  Amir, Noam / Kerret, Ori / Karlinski, Dimitry (2001): "Classifying emotions in speech: a comparison of methods", In EUROSPEECH-2001, 127-130.