Lantian Li 2015-03-23

From cslt Wiki
Revision as of 15:33, 23 March 2015 by Lilt (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Weekly Summary

1. Go on to investigate the use of d-vector.

1). cnn feature extraction with phone posterior as dnn input.

2). segment d-vector achieve better performance.

3). DTW instead of segment d-vector. (still ongoing)

Next Week

1. Go on the task1 and task2.