search

RicherMans / PLDA

An LDA/PLDA estimator using KALDI in python for speaker verification tasks
99 stars 24 forks source link

Does the code internally normalize the mean and the length of the ivectors? #4

Open weedwind opened 6 years ago

weedwind commented 6 years ago

Hi, RicherMans,

Usually before we train the PLDA model, we subtract the mean from the ivectors and also normalize their length. I am wondering does your implementation (or Kaldi's) do that internally?

Thank you

RicherMans commented 6 years ago

The norm function does only normalize over the speakers, not the length.