Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing
Figure 15 | EURASIP Journal on Audio, Speech, and Music Processing

Figure 15

From: Evaluation of influence of spectral and prosodic features on GMM classification of Czech and Slovak emotional speech

Figure 15

Influence of incorrectly chosen GMM model of gender type on stability of the emotion classification; obtained scores (upper set of graphs), determined class of emotion (bottom set); feature set P3, N gmix = 6, N iter = 1200; tested sentence expressed in neutral speaking style by the male speaker (left two graphs), and by the female speaker (right graphs).

Back to article page