espnet2.enh.layers.dnn_beamformer.AttentionReference

source

class espnet2.enh.layers.dnn_beamformer.AttentionReference(bidim, att_dim, eps=1e-06)

Bases: Module

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

forward(psd_in: Tensor | ComplexTensor, ilens: LongTensor, scaling: float = 2.0) → Tuple[Tensor, LongTensor]

Attention-based reference forward function.

• Parameters:
  • psd_in (torch.complex64/ComplexTensor) – (B, F, C, C)
  • ilens (torch.Tensor) – (B,)
  • scaling (float)
• Returns: (B, C) ilens (torch.Tensor): (B,)
• Return type: u (torch.Tensor)