Skip to main content

Table 13 Comparison of computational complexity for different lengths of the feature vector

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

Feature vector length/mean CPU time (ms)

Models creation and training

Classification

Summarized CPU time

  

Neutral

Joy

Sadness

Anger

 

NFEAT = 8

296

153

163

214

195

482

NFEAT = 16

336

162

173

220

208

529

NFEAT = 32

387

166

179

226

212

622