search

google / uis-rnn

This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Supervised Speaker Diarization.
https://arxiv.org/abs/1810.04719
Apache License 2.0
1.55k stars 320 forks source link

how to control the number of different speaker when predicting? #78

Closed NewEricWang closed 3 years ago

NewEricWang commented 3 years ago

Describe the question

In my experiment, I find the speaker number predicted by uis-rnn model is more than real number. I want to know how to control the different speaker number predicted by uis-rnn model. Which parameters in inference stage can do it?

My background

Have I read the README.md file?

Have I searched for similar questions from closed issues?

Have I tried to find the answers in the paper Fully Supervised Speaker Diarization?

Have I tried to find the answers in the reference Speaker Diarization with LSTM?

Have I tried to find the answers in the reference Generalized End-to-End Loss for Speaker Verification?

wq2012 commented 3 years ago

It's not supported, see Issue #26 and #56

However, you can try to lower --crp_alpha.