Difference between revisions of "2020-06-29"

From cslt Wiki
Jump to: navigation, search
 
(2 intermediate revisions by 2 users not shown)
Line 39: Line 39:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*
+
* Study on Gaussians in high dimension
 +
* Enroll-test mismatch (analysis pipeline)
 +
* Experiments on AE + NDA
 
||
 
||
*
+
* Study on properties in latent space.
 
||
 
||
 
*   
 
*   
Line 84: Line 86:
 
|Jiawen Kang
 
|Jiawen Kang
 
||  
 
||  
*
+
* Verify the mismatch assumption.
 +
* make PPT of erxperimental results.
 
||
 
||
*
+
* Arangment codes.
 +
* Code Debug.
 
||
 
||
 
*   
 
*   
Line 95: Line 99:
 
|Ruiqi Liu
 
|Ruiqi Liu
 
||  
 
||  
*
+
* More investigates and experments on i-vector anfd x-vector recipe use CN2 data .
 
||
 
||
*
+
* Further analysis on CN dataset several notable factors, including genres, duration, gender, age ..
 
||
 
||
 
*   
 
*   

Latest revision as of 02:07, 29 June 2020

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Deepnorm2 paper darft finished
  • Deepnorm2 paper polishing
Yunqi Cai
Zhiyuan Tang
  • Test FFJORD.
  • Back to AEFlow.
Lantian Li
  • Study on Gaussians in high dimension
  • Enroll-test mismatch (analysis pipeline)
  • Experiments on AE + NDA
  • Study on properties in latent space.
Ying Shi
  • Gradient based speech enhancement method with Gauss. length norm(x space)
  • Gradient based speech enhancement method with Gauss. length norm(z space)
Haoran Sun
Yue Fan
  • Reproduce the baseline based on MFCC-GMM.
  • Control Variable Experiment
Jiawen Kang
  • Verify the mismatch assumption.
  • make PPT of erxperimental results.
  • Arangment codes.
  • Code Debug.
Ruiqi Liu
  • More investigates and experments on i-vector anfd x-vector recipe use CN2 data .
  • Further analysis on CN dataset several notable factors, including genres, duration, gender, age ..
Sitong Cheng
Zhixin Liu
Haolin Chen
  • FFJORD hands on and test
  • Reviewed papers on unsupervised denoising
  • Investigate other methods