handle overlapped speech about uis-rnn HOT 3 CLOSED

Our method is consistent for both training and testing:

1. Process the entire audio to produce speaker embeddings. (we don't want to run speaker embedding LSTM on manually trimmed/concatenated audios)
2. Remove the speaker embeddings that correspond to overlapped speakers, in both training and testing data.
3. For computing diarization errors, note that the overlapping speech has been removed from both the numerator and the denominator.

from uis-rnn.

How you know what speaker embeddings that correspond to overlapped speakers to remove?

from uis-rnn.

@chienducnguyen It's from the ground truth. The ground truth has segments labelled with two speakers.

from uis-rnn.