Lantian Li 15-08-03
1. Prepare for three deep speaker embedding tasks:
1). large-scale deep speaker vector framework -- hold.
2). knowledege transfer for i-vector -- in process.
Debug the RNN-lstm scripts, and it sames all right.
3). derive binary i-vectors using Hamming distance learning
prepare for the experiments of identification efficiency. -- in process.
1. Go on the task 1 and attempt to complete 2) and 3).