Difference between revisions of "Lantian Li 2016-02-22"

From cslt Wiki
Jump to: navigation, search
(以“* Weekly Report :* Max-margin metric learning task: : modify the cost function: using sum cost instead of mean cost. : make some experiments based on DNNs tran...”为内容创建页面)
 
 
Line 1: Line 1:
 
* Weekly Report
 
* Weekly Report
  
:* Max-margin metric learning task:  
+
:* Max-margin metric learning task:[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=485 here]
  
 
:  modify the cost function: using sum cost instead of mean cost.
 
:  modify the cost function: using sum cost instead of mean cost.
Line 7: Line 7:
 
:  make some experiments based on DNNs transform instead of the simple linear transform.
 
:  make some experiments based on DNNs transform instead of the simple linear transform.
  
:* Pair-wised speaker vector training.
+
:* Pair-wised speaker vector training.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=510 here]
  
 
:* Deep speaker embedding.
 
:* Deep speaker embedding.

Latest revision as of 12:27, 22 February 2016

  • Weekly Report
  • Max-margin metric learning task:here
modify the cost function: using sum cost instead of mean cost.
make some experiments based on DNNs transform instead of the simple linear transform.
  • Pair-wised speaker vector training.here
  • Deep speaker embedding.
code the first version, but it still has lots of bugs. Need Help!
  • To Do next week
  • max-margin metric learning --> sum cost + DNNs.
  • Pair-wised speaker vector training --> Hold.
  • Deep speaker embedding --> the CNN structure.