Research on Objective Evaluation of Recording Audio Restoration Based on Deep Learning Network

Table 2

Correct rate of test set under different dropout.

Dropout	0.3	0.4	0.5	0.6	0.7	0.8	0.9	1.0
correct rate	0.828	0.834	0.855	0.863	0.847	0.853	0.802	0.799