Forums

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

> Use of music, noise, etc for data augmentation

Is it possible to use non-speech audio to do data augmentation for this track?

Posted by: dgromero @ July 23, 2019, 2:02 p.m.

Hi,

Yes, you can use any kind of noise, as long as you are not training on additional speakers.

Posted by: vgg @ July 23, 2019, 2:27 p.m.
Post in this thread