espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference

source

class espnet.nets.pytorch_backend.frontends.dnn_beamformer.AttentionReference(bidim, att_dim)

Bases: Module

Attention Reference class.

Initialize Attention Reference.

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

Calculate AttentionReference forward propagation.

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