Closed zmolikova closed 1 year ago
Hi, I suspect that the computation of variance in CumLN is missing a division by the length of the sequence. That is:
CumLN
https://github.com/asteroid-team/asteroid/blob/140733bbaafb5940e1b542c7522d4e3b0ba875bb/asteroid/masknn/norms.py#L101
should be cum_var = cum_pow_sum / cnt - cum_mean.pow(2) as in $var(x) = E[x^2] - E[x]^2$.
cum_var = cum_pow_sum / cnt - cum_mean.pow(2)
You're fully right, thank you !
Could you please submit a PR ?
Hi, I suspect that the computation of variance in
CumLN
is missing a division by the length of the sequence. That is:https://github.com/asteroid-team/asteroid/blob/140733bbaafb5940e1b542c7522d4e3b0ba875bb/asteroid/masknn/norms.py#L101
should be
cum_var = cum_pow_sum / cnt - cum_mean.pow(2)
as in $var(x) = E[x^2] - E[x]^2$.