Unfolding sometimes results into concatenated channels

https://github.com/asteroid-team/asteroid/blob/c72227e5e31f6c13ba9c9da1d0d380cc75b91fbd/asteroid/dsp/overlap_add.py#L92

/We can see how torch 1.10.2 does concatenates the windows of all channels after unfold./

The expected behavior, in the code, would be to handle `(batch, chans, win_size)` per chunk
$\rightarrow$ `(batch, chans, win_size, n_chunks)`.

Thus it has to be reshaped before handling to the NN, from my perspective.
`unfolded = unfolded.reshape(batch, channels, self.window_size, -1)`

Start in asteroid/dsp/overlap_add.py at line 92 and inspect the shape produced by unfold for multiple channels. Confirm that each chunk preserves the channel dimension and that the downstream neural network receives the expected (batch, chans, win_size, n_chunks) shape.

Written by the indexing model from the issue text.