espnet2.enh.layers.bsrnn.BandSplit

source

class espnet2.enh.layers.bsrnn.BandSplit(input_dim, target_fs=48000, subbands=None, channels=128, norm_type='GN')

Bases: Module

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

static convert_size_to_indices(subbands, input_dim)

Convert subband sizes to the corresponding start and end indices.

forward(x, fs=None)

BandSplit forward.

• Parameters:
  • x (torch.Tensor) – input tensor of shape (B, T, F, 2)
  • fs (int , optional) – sampling rate of the input signal. if not None, the input signal will be truncated to only process the effective frequency subbands. if None, the input signal is assumed to be already truncated to only contain effective frequency subbands.
• Returns: output tensor of shape (B, N, T, K’) : K’ might be smaller than len(self.subbands) if fs < self.target_fs.
• Return type: z (torch.Tensor)

static validate_subbands(subbands, input_dim, target_fs=48000)

Validate the subbands.