Table 1 Recognition results of the above three speech emotion recognition models
From: Black-box adversarial attacks through speech distortion for speech emotion recognition
Model | UA (%) | WA (%) | ACC (%) |
|---|---|---|---|
CNN-LSTM | 63.23 | 65.36 | 64.30 |
GCN | 77.54 | 79.34 | 78.44 |
CNN-MAA | 77.05 | 79.11 | 78.08 |