Skip to main content

Advertisement

Table 1 Reconstruction SDR under different positive constraints in decibel

From: Discriminative frequency filter banks learning with neural networks

Initialization Constraint M = 32 M = 64
   F-B T-I F-B T-I
N(0, 0.1) Exponent 8.57 6.72 13.10 6.74
  Sigmoid 8.54 8.89 12.84 9.43
  ReLU 8.45 14.44 12.84 18.54
  Square 8.57 14.44 12.84 18.24
N(− 3.0, 2.0) Exponent 9.02 14.44 13.25 17.70
  Sigmoid 8.36 14.31 12.84 17.97
  1. F-B represents the parameters with fixed frequency center and bandwidth; T-I represents the totally independent parameters; M represents the number of filters; N means Gaussian distribution