An impulse takes raw data, uses signal processing to extract features, and then uses a learning
block to classify new data.
This block does not have any other settings
For optimal accuracy with transfer learning blocks, use a 96x96 or 160x160 image size.
This block only works with a window size of 1000ms at 16000Hz,
and an Audio (MFE) block with default parameters.
You'll need some training data to design your first impulse.