espnet2.enh.layers.mask_estimator.MaskEstimator

source

class espnet2.enh.layers.mask_estimator.MaskEstimator(type, idim, layers, units, projs, dropout, nmask=1, nonlinear='sigmoid')

Bases: Module

Initialize internal Module state, shared by both nn.Module and ScriptModule.

forward(xs: Tensor | ComplexTensor, ilens: LongTensor) → Tuple[Tuple[Tensor, ...], LongTensor]

Mask estimator forward function.

• Parameters:
  • xs – (B, F, C, T)
  • ilens – (B,)
• Returns: The hidden vector (B, F, C, T) masks: A tuple of the masks. (B, F, C, T) ilens: (B,)
• Return type: hs (torch.Tensor)