In part 1 of this blog post we established that Spectral Expression relies on two key concepts
- being able to automatically determine the optimal number of frequencies- see here.
- capability to determine the frequency weights required to shape the data to a target spectrum- which we will cover in this blog post.
The spectral shaping occurs by determining the optimal combination of weights that minimises the area (grey) between the shaped spectrum (orange curve) and a target function (yellow curve) see below.
|Showing original spectrum (blue), target spectrum (yellow) and shaped spectrum (orange)|