Table 3 Default hyper-parameters for the baseline network
From: A depthwise separable convolutional neural network for keyword spotting on an embedded system
Layer Op. | Nfilters | Filter dim. (Wt×Wf) | Stridet | Stridef |
|---|---|---|---|---|
Conv. | 300 | 10×4 | 2 | 1 |
DS-conv. | 300 | 3×3 | 2 | 2 |
DS-conv. | 300 | 3×3 | 1 | 1 |
DS-conv. | 300 | 3×3 | 1 | 1 |
DS-conv. | 300 | 3×3 | 1 | 1 |
DS-conv. | 300 | 3×3 | 1 | 1 |
DS-conv. | 300 | 3×3 | 1 | 1 |
DS-conv. | 300 | 3×3 | 1 | 1 |