“2020-12-14”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
(以“{| class="wikitable" !People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>) |- |- |Dong Wang || * || * || * |- |- |Yunqi Cai...”为内容创建页面)
 
 
(5位用户的5个中间修订版本未显示)
第6行: 第6行:
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
*  
+
* Bayesian approach for noisy injection
 +
* New factorization model
 
||
 
||
*  
+
* More investigation on factorization model
 
||
 
||
 
*   
 
*   
第17行: 第18行:
 
|Yunqi Cai
 
|Yunqi Cai
 
||   
 
||   
*  
+
* continue on science popularization project
 +
* visual-tactile fusion dataset preprocessing
 +
* Infrared thermal imaging perception survey
 
||
 
||
 
*  
 
*  
第28行: 第31行:
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
*  
+
* Release DGT code.
 +
* Release DNN-ASR-based speaker diarization.
 
||
 
||
*  
+
* Go on deep Gaussian model.
 
||
 
||
 
*   
 
*   
第50行: 第54行:
 
|Haoran Sun
 
|Haoran Sun
 
||  
 
||  
*  
+
* properties of pooling training dnf for speaker
 +
* some attempt to solve problems of within var
 
||
 
||
*  
+
* find a solution keeping generation and pooling training
 
||
 
||
 
*   
 
*   
第72行: 第77行:
 
|Jiao Han
 
|Jiao Han
 
||  
 
||  
*  
+
* Experiments related to PLDA_SB used in NL scoring.
 
||
 
||
*  
+
* Continue to verify and summarize.
 
||
 
||
 
*   
 
*   
第94行: 第99行:
 
|Di Wang
 
|Di Wang
 
||  
 
||  
*  
+
* Model the sigma in the prediction term.
 
||
 
||
*  
+
* Modify and optimize the experiment.
 
||
 
||
 
*   
 
*   
第105行: 第110行:
 
|Tiankai Zhi
 
|Tiankai Zhi
 
||  
 
||  
*  
+
* Continue to the SED experiment.
 
||
 
||
*  
+
* To end the SED experiment.
 
||
 
||
 
*   
 
*   

2020年12月13日 (日) 23:53的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Bayesian approach for noisy injection
  • New factorization model
  • More investigation on factorization model
Yunqi Cai
  • continue on science popularization project
  • visual-tactile fusion dataset preprocessing
  • Infrared thermal imaging perception survey
Lantian Li
  • Release DGT code.
  • Release DNN-ASR-based speaker diarization.
  • Go on deep Gaussian model.
Ying Shi
Haoran Sun
  • properties of pooling training dnf for speaker
  • some attempt to solve problems of within var
  • find a solution keeping generation and pooling training
Yue Fan
Jiao Han
  • Experiments related to PLDA_SB used in NL scoring.
  • Continue to verify and summarize.
Yang Zhang
Di Wang
  • Model the sigma in the prediction term.
  • Modify and optimize the experiment.
Tiankai Zhi
  • Continue to the SED experiment.
  • To end the SED experiment.