Skip to main content

Advertisement

Table 8 Scenario 2: perplexities of the adapted linguistic models. The baseline system (linguistic models are trained on Ohm_base) is given in column "Ohm_base". "" denotes the arithmetic (unweighted) mean. The average of the four subsets weighted by the prior probabilities of the four classes is given in row "Mont."

From: On the Impact of Children's Emotional Speech on Acoustic and Language Models

  Linguistic models trained on
  Ohm_base Ohm_base + Ohm_base + Ohm_base + Ohm_base +
Test set (baseline) 2x Ohm_M 1x Ohm_N 3x Ohm_E 2x Ohm_A
Mont_M 24.4 20.8 24.3 32.3 29.0
Mont_N 14.9 18.5 14.8 17.2 16.8
Mont_E 10.2 14.1 10.2 8.28 9.77
Mont_A 9.87 12.7 9.86 9.64 7.66
14.8 16.5 14.8 16.9 15.8
Mont 14.2 17.8 14.2 15.9 15.6