Распознавание эмоций диктора по его голосу

Abstract

An algorithm for automatic emotion recognition from the speaker's voice has been developed. The classification efficiency for different acoustic features was estimated and a very small set of the most reliable characteristics was extracted in order to obtain a robust and quick emotion state classification. Using the classifier with quadratic kernel and this feature set provides the recognition accuracy of approximately 96 % between “anger” and “neutral” emotional states.