Quations reagrding Decoder

[PrashantChaudhari08]

Hi,

Thank you for an awesome, well-organized repository.
I have a question regarding the Decoder block. The paper states, they use a 1-D transposed convolution operation for the generating the decoder basis functions. paper

However, I see you use a linear dense layer in the decoder

Conv-TasNet/src/conv_tasnet.py

Line 126 in 94eac10

self.basis_signals = nn.Linear(N, L, bias=False)

Could you explain the reason for this choice?

[tky823]

linear dense layer + overlap-add is the same as a transposed convolution.

Conv-TasNet/src/conv_tasnet.py

Lines 140 to 141 in 94eac10

	est_source = self.basis_signals(source_w) # [M, C, K, L]
	est_source = overlap_and_add(est_source, self.L//2) # M x C x T