This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
We trained a diarization model with our own data, the test result is correct for short utterances. However for longer utterances, the diarization output is all zero. Could you explain the possible reasons for this? Thank you.
We trained a diarization model with our own data, the test result is correct for short utterances. However for longer utterances, the diarization output is all zero. Could you explain the possible reasons for this? Thank you.