(b) Scenario 2: "adaptation of neutral ASR engine"
From: On the Impact of Children's Emotional Speech on Acoustic and Language Models
M | E | A | |
|---|---|---|---|
Baseline system | 65.0 | 81.0 | 79.2 |
Adapted systems | |||
Acoustic models | 64.5 | 83.1 | 83.6 |
Linguistic models | 65.9 | 81.6 | 81.6 |
Both | 65.9 | 84.4 | 85.1 |
- Levels of significance (adjusted according to [34]):
0.05 
0.01 
0.005 
0.002 
0.001.
0.05 
0.01 
0.005 
0.002 
0.001.