FEATURE SELECTION FOR SPEAKER’S EMOTION RECOGNITION

A. V. Sholokhov


Read the full article 

Abstract

The article deals with the problem of the most informative features selecting for automatic emotional speaker’s state recognition. Genetic algorithm was used to obtain the optimal subset of features for a given quality criterion of recognition.


Keywords: emotion recognition, speech features, genetic algorithms
Copyright 2001-2017 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика