Research Article

Reordering Features with Weights Fusion in Multiclass and Multiple-Kernel Speech Emotion Recognition

Table 3

Emotion recognition accuracies of different feature selection methods with the best feature number.

Selection methodsFeature numberSER accuracies (%)
TotalAngryFearHappyNeutralSad

DISR3988.61493.65179.41297.14374.35996.774
MRMR3990.09992.06367.64797.14394.87296.774
RFWF MK1590.59490.47679.41297.14387.179100
RFWF SK3979.20895.23873.52928.57187.179100