Study on the Application of Improved Audio Recognition Technology Based on Deep Learning in Vocal Music Teaching

Table 2

Humming recognition neural network hyperparameters.

Hyperparameters	Value
Convolution kernel size	(4,4)
Pooling kernel size	(2,2)
Number of training cycles	60
Batch size	190
Learning rate	0.03
Momentum factor	0.9
Dropout rate	0.4