Fanhu Bie 2015-01-19

From cslt Wiki
Revision as of 15:32, 19 January 2015 by Biefh (Talk | contribs)

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

Last Week:

Finish the experiments on speech quality weighted speaker recognition. But the result is not very well.

This Week:

Check the result, modify the algorithm, improve the performance.

Build the system on DNN based ivector