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-SpeechPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
GPR | 1 | 33.33% |
point cloud upsampling | 1 | 33.33% |
Text-To-Speech Synthesis | 1 | 33.33% |
Component | Type |
|
---|---|---|
Convolution
|
Convolutions | |
Dropout
|
Regularization | |
GLU
|
Activation Functions | |
Residual Connection
|
Skip Connections |