Table 5 Performance of different methods on the test set
From: Neural network-based non-intrusive speech quality assessment using attention pooling function
| Methods | R | RMSE |
|---|---|---|
| P.563 | 0.610 | 1.430 |
| Autoencoder-SVR [16] | 0.954 | 0.308 |
| Cnn-LSTM-attention | 0.967 | 0.269 |