Lantian Li 2015-09-07
1. Go on my three deep speaker embedding tasks:
1). large-scale deep speaker vector framework -- hold.
2). knowledge transfer for i-vector -- in process.
Dev.: Fisher; Eva.: SRE08.
The performance of knowledge transfer is not well good under SRE08.
I tried to readjust the DNN structure and learning rate, but it still does not work.
3). derive binary i-vectors using Hamming distance learning (identification efficiency Exp.)
Identification and verification efficiency experiments are in proess.
All the scripts have been done.
2. Help Pro.Zheng write two patents and have been completed.
1. Go on the 2) and 3) of the task 1.
2. Go on the task 2.