Difference between revisions of "2019-12-09"

From cslt Wiki
Jump to: navigation, search
Line 6: Line 6:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*  
+
* MelGan and WaveGlow re-investigation. Good neural vocoder is done.
 +
* Paper review on ICASSP 19, Interspeech 19.
 
||
 
||
*  
+
* Investigate the performance degradation with pure VP-based x-vector regularization compared to the VP+linear model
 +
* Design more concrete way of 'supervised flow', that involves supervision in sparse dimensions.
 +
* Paper review on NIPS 19.
 
||
 
||
 
*   
 
*   

Revision as of 01:02, 9 December 2019

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • MelGan and WaveGlow re-investigation. Good neural vocoder is done.
  • Paper review on ICASSP 19, Interspeech 19.
  • Investigate the performance degradation with pure VP-based x-vector regularization compared to the VP+linear model
  • Design more concrete way of 'supervised flow', that involves supervision in sparse dimensions.
  • Paper review on NIPS 19.
Yunqi Cai
  • VP-flow-lda Finished;
  • 1 try VP-flow without the last layer maping matrix
  • 2 control the class covariance matrix
  • 3 explore the fitting limit of VP-flow
Zhiyuan Tang
Lantian Li
Ying Shi
Wenqiang Du
Haoran Sun
Yue Fan
Jiawen Kang
Ruiqi Liu
Sitong Cheng
Zhixin Liu