Skip to main content

Table 2 Audio scene classification performance under different positive constraints

From: Discriminative frequency filter banks learning with neural networks

Initialization Constraint F-B T-I
   Accuracy MCC Accuracy MCC
N(0, 0.1) Exponent 77.21 75.85 71.20 69.48
  Sigmoid 77.87 76.60 70.75 68.97
  ReLU 77.37 76.05 76.92 75.59
  Square 77.89 76.63 75.96 74.62
N(− 3.0, 2.0) Exponent 77.97 76.70 73.52 72.04
  Sigmoid 77.16 75.82 71.44 69.81
  1. F-B represents the parameters with fixed frequency center and bandwidth; T-I represents the totally independent parameters; N means Gaussian distribution