Temporal Convolutions

Dilated Causal Convolution

Introduced by Oord et al. in WaveNet: A Generative Model for Raw Audio

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 Audio


Paper Code Results Date Stars


Task Papers Share
Speech Synthesis 46 25.99%
Text-To-Speech Synthesis 14 7.91%
Voice Conversion 12 6.78%
Speech Quality 10 5.65%
Time Series 6 3.39%
Audio Generation 6 3.39%
Speech Enhancement 6 3.39%
Speech Recognition 5 2.82%
Time Series Forecasting 4 2.26%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign