Lantian Li 15-08-11
1. Prepare for three deep speaker embedding tasks:
1). large-scale deep speaker vector framework -- hold.
2). knowledge transfer for i-vector -- in process.
The ivector knowledge transfor(IKT) both on DNN and RNN has been done.
The results show that the performance of DNN-IKT is better than former d-vector system,
but still worse than i-vector baseline. And the RNN-IKT does not work well.
We think it is due to the training-data is insufficient.
3). derive binary i-vectors using Hamming distance learning
obtain the code from Xing Chao, and start to modify the test-code and design the experiments.
1. Go on the task 1 and repeat the DNN-IKT of 2) on Fisher and SRE database.
2. Go on the task 1 and attempt to complete 3).