in reademe, 10ms is overlap, but in code:
N_fr = int((signal.shape[0]-wlen)/(wshift))
this formula means 10ms is shift, actually, the N_fr should be:
N_fr = int((signal.shape[0]-(wlen-wshift))/(wshift))
but if 10ms is overlap, N_fr should be:
N_fr = int((signal.shape[0]-wshift)/(wlen-wshift))
if like this, the number of chunk will be less than batch_num.
in reademe, 10ms is overlap, but in code:
N_fr = int((signal.shape[0]-wlen)/(wshift))
this formula means 10ms is shift, actually, the N_fr should be:N_fr = int((signal.shape[0]-(wlen-wshift))/(wshift))
but if 10ms is overlap, N_fr should be:
N_fr = int((signal.shape[0]-wshift)/(wlen-wshift))
if like this, the number of chunk will be less than batch_num.I'm confused.