Jungjee

Hi @zabir-nabil. May I first ask for the configuration you used? - I'm suspecting that you may have set `nPerSpeaker` to 2 whereas you should set to 1 for aamsoftmax

Hi @Spectra456. The easiest thing to say would be that RawNet3 (I assume you used this one, since ECAPA-TDNN outperforms RawNet2) is somehow overfitted to VoxCeleb domain. However, it would...

Hi, can you share your results? I cannot share the exact training recipe because it includes internal codes, which is one of the reasons why I shared trained weight parameters....

@JunLi0514 , hi, thanks for reporting your status. Speaking of EER 0.98%, did you follow the same setup by segmenting it into ten 4-second segments? If you input the full-length...

Please reopen this issue when you have further updates.

Hi Willy, I think the task you are mentioning would be open-set speaker identification. Assuming you're using a neural network to do it, there are two approaches. 1. Train a...

Maybe I'm the one who's confused. In my understanding, if what you want is not an "open-set speaker identification" but "speaker verification" you can simply compare the speaker embedding of...

Hi @wwyl2000 , > Can i average the M embeddings into one? For example, the embeddings are K dimensions, so just get an average the M vectors and save one...

Hi, @ikou-austin. We did not adopt any data augmentations (considering the tasks' property, we are cautious about adopting any kind of augmentations) We also used the official train subset only...

Hi, there's no tutorial as of now. But, I may be able to make one in meanwhile :) I will keep this issue open for now.