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

From cslt Wiki
Jump to: navigation, search
(以“* Weekly Report :* 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] Done! :*...”为内容创建页面)
 
Line 4: Line 4:
  
 
:* Binary speaker embedding. Only need 'variable-sized block training'.
 
:* Binary speaker embedding. Only need 'variable-sized block training'.
 
:* Joint-training: d-vector nnet3 reproduce.[http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=516 here].
 
  
 
:* 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].
  
 
:* 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]

Revision as of 00:49, 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.
  • Pair-wised speaker vector training.here
  • Deep speaker embedding.
  • This Week
  • Complete Interspeech papers.
  • Joint-training (speaker recognition)