Bridge-net is an audio model block used in the ClariNet text-to-speech architecture. Bridge-net maps frame-level hidden representation to sample-level through several convolution blocks and transposed convolution layers interleaved with softsign non-linearities.
Source: ClariNet: Parallel Wave Generation in End-to-End Text-to-SpeechPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Synthesis | 3 | 30.00% |
Domain Adaptation | 2 | 20.00% |
Unsupervised Domain Adaptation | 2 | 20.00% |
Melody Extraction | 1 | 10.00% |
Retrieval | 1 | 10.00% |
Text-To-Speech Synthesis | 1 | 10.00% |
Component | Type |
|
---|---|---|
Dense Connections
|
Feedforward Networks | |
DV3 Convolution Block
|
Audio Model Blocks | |
Softsign Activation
|
Activation Functions |