A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by skipping input values with a certain step. A dilated causal convolution effectively allows the network to have very large receptive fields with just a few layers.
Source: WaveNet: A Generative Model for Raw AudioPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Synthesis | 53 | 20.08% |
Decoder | 20 | 7.58% |
Text-To-Speech Synthesis | 15 | 5.68% |
Voice Conversion | 13 | 4.92% |
Time Series Analysis | 9 | 3.41% |
Audio Generation | 8 | 3.03% |
Speech Enhancement | 7 | 2.65% |
Time Series Forecasting | 6 | 2.27% |
Traffic Prediction | 5 | 1.89% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |