Closed predawnang closed 1 year ago
Hi,
We are following the settings of VoxCeleb, a commonly used corpus for automatic speaker verification (ASV) tasks. As VoxCeleb is widely accepted among ASV researchers, we believe that the number of positive and negative samples provided is sufficient for ASV purposes.
thank you so much
Hi,
I noticed that in the evaluation/json/VCTK/pair.json you provide 4 positive samples and 4 negative samples per speaker in vctk dataset. I wonder that is it enough for computing a good threshold value for asv acceptant rate?
Thanks