Skip Connection Blocks

ParaNet Convolution Block

Introduced by Peng et al. in Non-Autoregressive Neural Text-to-Speech

A ParaNet Convolution Block is a convolutional block that appears in the encoder and decoder of the ParaNet text-to-speech architecture. It consists of a 1-D convolution with a gated linear unit (GLU) and a residual connection. It is similar to the DV3 Convolution Block.

Source: Non-Autoregressive Neural Text-to-Speech


Paper Code Results Date Stars


Task Papers Share
GPR 1 50.00%
Text-To-Speech Synthesis 1 50.00%