Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 1 Augmentation hyperparameters

From: Comparison of semi-supervised deep learning algorithms for audio classification

 

Param.

Weak range

Strong range

Occlusion

Max size

[0.25, 0.25]

[0.75, 0.75]

CutOut

Scale

[0.10, 0.50]

[0.50, 1.00]

Speed perturb.

Rate

[0.50, 1.50]

[0.25, 1.75]

Back to article page