Lantian Li 15-07-07
1. Modify the ChinaSIP oral PPT and complete it.
2. Prepare for three deep speaker embedding tasks:
1). large-scale deep speaker vector framework: -- hold.
2). knowledege transfer for i-vector: DNN-based has been done! RNN-based is still on process.
3). derive binary i-vectors using Hamming distance learning： results as shown in CVSS 373.
1. Go on the task 2 and attempt to make (2)/(3).