Fig. 3
From: U2-VC: one-shot voice conversion using two-level nested U-structure
The comparison of 1-2-1 residual U-block and plain residual block. a The residual block. b The 1-2-1 residual U-block (1-2-1RSU). The constitution of the output feature from each block illustrates why the 1-2-1 residual U-block can preserve more details than plain residual block