Skip to main content

Table 1 Confusion matrix for the HMM-based system using pitch contours (S-I), ν i = s F 0 i , b F 0 i (overall accuracy 57.1%)

From: On the use of speech parameter contours for emotion recognition

  Neutral (%) Anger (%) Sad (%) Happy (%) Bored (%)
Neutral 59.6 0 19.2 6.4 14.9
Anger 0 78.9 2.8 16.9 1.4
Sad 13.1 1.6 49.2 14.8 21.3
Happy 1.4 32.9 16.4 43.8 5.5
Bored 6.5 0 28.6 10.4 54.6