Split chord segments with keys to blocks

Instead of separate chords we want a context consisting a sequence of several chords. Then we use this chord blocks as an input and key as output for training a key classifier.

For simplicity we do a few things:

remove silent chords (N label) and silent keys
create fixed-size chord blocks such that each block spans a single key



In [1]:

    
import sys

sys.path.append('../../tools/music-processing-experiments')

from analysis import split_block_times



In [2]:

    
split_block_times(200, 50, 10)









    Out[2]:





array([ 0. ,  0.2,  0.4,  0.6,  0.8,  1. ,  1.2,  1.4,  1.6,  1.8,  2. ,
        2.2,  2.4,  2.6,  2.8,  3. ,  3.2,  3.4,  3.6,  3.8])



In [ ]: