“2019-01-16”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(6位用户的7个中间修订版本未显示)
第10行: 第10行:
 
|Yibo Liu
 
|Yibo Liu
 
||  
 
||  
*  
+
* Use another word vector and lyrics training set to train a model for lyrics generation. (Ongoing)
 
||
 
||
*  
+
* Reconstruct code and make it flexible for different baseline models.
 
||
 
||
 
*   
 
*   
第37行: 第37行:
 
|Jiayao Wu
 
|Jiayao Wu
 
||  
 
||  
*
+
*continue doing sparse-node experiment using the mask method
 
||
 
||
*
+
*run through the first experiment
 
||  
 
||  
 
*  
 
*  
第50行: 第50行:
 
|Zhaodi Qi
 
|Zhaodi Qi
 
||  
 
||  
*  
+
* Finish the speech language recognition of speech book.
 +
* Compared the experiments of tdnn model under different duration test sets
 +
* Research on model acceleration and model compression
 
||  
 
||  
*  
+
* Do experiments to make the lid model smaller and faster
 
||
 
||
 
*   
 
*   
第63行: 第65行:
 
|Jiawei Yu
 
|Jiawei Yu
 
||  
 
||  
*  
+
* Finish the speech emotion recognition of speech book.
 +
* Learning the tensorflow tutorial.
 
||  
 
||  
*  
+
* keep learning tensorflow and do some experiment.
 
||
 
||
 
*   
 
*   
第85行: 第88行:
 
|Dan He
 
|Dan He
 
||  
 
||  
*
+
*Doing some comparative experiments about TT-decompositions.
 
||  
 
||  
*
+
*Summarize the results of the comparative experiments and initially complete the relevant research on TT-decomposition.
 
||
 
||
 
*   
 
*   

2019年1月24日 (四) 02:14的最后版本

People Last Week This Week Task Tracking (DeadLine)
Yibo Liu
  • Use another word vector and lyrics training set to train a model for lyrics generation. (Ongoing)
  • Reconstruct code and make it flexible for different baseline models.
Xiuqi Jiang
  • Focused back on the quatrain generation, thinking of the drawbacks of current model.
  • Tried to weaken the attention mechanism between sentences.
  • Add VAE into model and try to generate instead of predicting.
Jiayao Wu
  • continue doing sparse-node experiment using the mask method
  • run through the first experiment
Zhaodi Qi
  • Finish the speech language recognition of speech book.
  • Compared the experiments of tdnn model under different duration test sets
  • Research on model acceleration and model compression
  • Do experiments to make the lid model smaller and faster
Jiawei Yu
  • Finish the speech emotion recognition of speech book.
  • Learning the tensorflow tutorial.
  • keep learning tensorflow and do some experiment.
Yunqi Cai
  • 1.Run through the bert model. 2.study the details of the bert model.
Dan He
  • Doing some comparative experiments about TT-decompositions.
  • Summarize the results of the comparative experiments and initially complete the relevant research on TT-decomposition.
Yang Zhang
  • exam week.
  • (I will finish all my exams on Friday night)