Conditional DBlock

Introduced by Bińkowski et al. in High Fidelity Speech Synthesis with Adversarial Networks

Conditional DBlock is a residual based block used in the discriminator of the GAN-TTS architecture. They are similar to the GBlocks used in the generator, but without batch normalization. Unlike the DBlock, the Conditional DBlock adds the embedding of the linguistic features after the first convolution.

Source: High Fidelity Speech Synthesis with Adversarial Networks

Read Paper See Code