Closed staplesinLA closed 5 years ago
Oh, It seems that the pair operations of perm
and unperm
reconstruct the original utterance order.
So, the remaining question is: why we should randomize the utterance samples? Because those utterances are still in a same batch.
I believe if the structure of the batch input contains information about which speaker is associated with which utterance the algorithm will fit itself on the positioning of the batch input instead of the contents of the recording. So I permutate and unpermutate after retrieving the loss function output.
Thanks for sharing your great work. As a newer to to speaker verification, I have two question here. First, what's the purpose of
perm
andunperm
in training script. Second, since the original data matrix is disordered by the perm index, so how the loss is calculated between different speakers?Thanks a lot!