IQR-ing corpora

[tremblap]

Hence this:

3 ways of overlapping unmatching descriptor spaces

The problem is well-known and fun to play with - I will do a more formal explanation but a first attempt has been made here: Musaiking non-overlaping spectral descriptor spaces - an attempt at explaining the issue clearly - #4 by tremblap Yesterday in the workshop I’ve shown this bit of SC code. It is underdocumented, but might be helpful as a starting point. It also shows bundled batch processing which quite efficient. This was devised with one scaler when @weefuzzy and I were working on our …

in other words: if your corpus is not filling the total world (in which case it would be boringly reproducing the input) you will have to decide how you want to distort the matching of the 2 spaces, and there are no simple answers - it is a creative endeavour.