“2019-05-10”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(4位用户的6个中间修订版本未显示)
第64行: 第64行:
 
|Jiawei Yu
 
|Jiawei Yu
 
||  
 
||  
*  
+
* Continue  phonetic attention experiment and write the experiment report.
 
||  
 
||  
*  
+
* ...
 
||
 
||
 
*   
 
*   
第89行: 第89行:
 
|Xueyi Wang
 
|Xueyi Wang
 
||
 
||
*  
+
* carry out 1-d data experiment, and get the conclusion that feature we are using is not suitable for bayesian method
*  
+
* make a summary of segmentation task I have done until now
 
||  
 
||  
*
+
*modify the speech book
 +
*read papers and go through experiments of v-vector
 
||
 
||
 
*   
 
*   
第103行: 第104行:
 
|Ziya Zhou
 
|Ziya Zhou
 
||  
 
||  
*  
+
* Read a tutorial on ASR
 
||
 
||
*  
+
* Revise the speech book
*  
+
* Get familiar with a simple ASR task 
+
 
||
 
||
 
*   
 
*   
第117行: 第117行:
 
|kaicheng li
 
|kaicheng li
 
||
 
||
*  
+
* Read SpecAugment, and acquired a sample demo form github
*  
+
* Read tutorials. Revised a part of the speech book
 
||  
 
||  
*
+
*Revise the speech book
 +
*Verify the correctness of the SpecAugment demo
 
||
 
||
 
*   
 
*   
第130行: 第131行:
 
|Haolin Chen
 
|Haolin Chen
 
||
 
||
*  
+
* Continue learning statistics
*  
+
* Read tutorials on ML
 
||  
 
||  
*  
+
* Continue learning ML,probability and statistics
*
+
 
||
 
||
 
*   
 
*   

2019年5月11日 (六) 11:02的最后版本

People This Week Next Week Task Tracking (DeadLine)
Yibo Liu
Xiuqi Jiang
  • Merge code with Yibo and clean up current Vivi
  • Polish up baselines and add extra regularizations to seq2seq loss
Jiayao Wu
  • made a summary of formal experiment
  • prepare for the weekly report
  • make a further try of Adaboost on ASR on chain model(to get rid of the influence of priors,no priors in chain model)
  • try more experiments on Adaboost ASR
  • modify the speech book
Zhaodi Qi
  • Summarized the previous experiments and explored new methods.
  • Complete the experiment of Mult-scale information and Modify the speech book
Jiawei Yu
  • Continue phonetic attention experiment and write the experiment report.
  • ...
Wenwei Dong
  • use frame fbank feature to train infogan, draw t-sne
  • use gmm to learn the distribution of different dataset
Xueyi Wang
  • carry out 1-d data experiment, and get the conclusion that feature we are using is not suitable for bayesian method
  • make a summary of segmentation task I have done until now
  • modify the speech book
  • read papers and go through experiments of v-vector
Ziya Zhou
  • Read a tutorial on ASR
  • Revise the speech book
  • Get familiar with a simple ASR task
kaicheng li
  • Read SpecAugment, and acquired a sample demo form github
  • Read tutorials. Revised a part of the speech book
  • Revise the speech book
  • Verify the correctness of the SpecAugment demo
Haolin Chen
  • Continue learning statistics
  • Read tutorials on ML
  • Continue learning ML,probability and statistics