The VoxCeleb Speaker Recognition Challenge 2019 - Audio speaker verification - FIXED training data Forum

Go back to competition Back to thread list Post in this thread

> Data to train the PLDA

According to the Evaluation Plan, only the VoxCeleb2 dev set which contains 1,092,009 utterances from 5,994 speakers can be used to train the speaker model.
Is this also applied to the training of PLDA?

Posted by: xx205 @ Aug. 27, 2019, 3:40 a.m.

Yes

Posted by: vgg @ Aug. 27, 2019, 2:04 p.m.
Post in this thread