Difference between revisions of "2019-01-16"

From cslt Wiki
Jump to: navigation, search
 
(4 intermediate revisions by 3 users not shown)
Line 10: Line 10:
 
|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.
 
||
 
||
 
*   
 
*   
Line 50: Line 50:
 
|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
 
||
 
||
 
*   
 
*   

Latest revision as of 02:14, 24 January 2019

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)