This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
We're trying to understand the core of the training methods with the paper' equations. We're able to make sense of most of it, but the sigma2_prior_loss() in loss_func.py escape our understanding.
Could someone provide some explanation for it? How to derive that loss from the paper?
First, thanks for sharing this implementation.
We're trying to understand the core of the training methods with the paper' equations. We're able to make sense of most of it, but the
sigma2_prior_loss()
inloss_func.py
escape our understanding.Could someone provide some explanation for it? How to derive that loss from the paper?
Thanks in advance!