Lantian Li 15-05-25
From cslt Wiki
Revision as of 12:18, 28 May 2015 by Lilt
1. Make preliminary experiments on Speech watermarking.
2. Prepare for three deep speaker embedding tasks:
1). large-scale deep speaker vector framework: complete the first (i-vector clusters) and second (phone posterior extraction) steps.
2). RNN based deep speaker vector: use kaldi-RNN tools to embed utterance-level deep speaker vector.
3). derive binary i-vectors using Hamming distance learning. complete the fisrt step (data preparation).
1. Go on the task 1 and plan to complete it next week.
2. Go on the task 2 and learn the RNN framework.