Difference between revisions of "Lantian Li 2016-03-14"

From cslt Wiki
Jump to: navigation, search
 
Line 7: Line 7:
 
:* Replay detection based on low-energy speech segments.
 
:* Replay detection based on low-energy speech segments.
  
:* Joint-training.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=516 here].
+
:* Joint-training.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=516 here]. Hold
  
:* 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]
+
:* 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] Hold
  
:* Deep speaker embedding.
+
:* Deep speaker embedding. Hold
  
 
* This Week
 
* This Week

Latest revision as of 00:52, 14 March 2016

  • Weekly Report
  • Max-margin metric learning task.here Done!
  • Binary speaker embedding. Only need 'variable-sized block training'.
  • Replay detection based on low-energy speech segments.
  • Joint-training.here. Hold
  • Pair-wised speaker vector training.here Hold
  • Deep speaker embedding. Hold
  • This Week
  • Complete Interspeech papers.
  • Joint-training (speaker recognition)