“2018-12-05”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（3位用户的4个中间修订版本未显示）
第23行： 第23行：
 
|Xiuqi Jiang
 
|Xiuqi Jiang
 
||  
 
||  
−
*  
+
* Discussed code reconstruction work with Yibo Liu and set forth the aims of simplification and modularization.
 +
* Made research on meta learning and zero-shot learning, preparing for a weekly report.
 
||
 
||
−
*  
+
* Quicken the pace of code reconstruction.
 
||
 
||
 
*   
 
*   
第36行： 第37行：
 
|Jiayao Wu
 
|Jiayao Wu
 
||  
 
||  
−
*  
+
* do research on ASR data size for End2End
 +
* do research on training tricks for End2End ASR of Mandarin & Japanese
 +
* finish a baseline on WSJ
 
||
 
||
−
*  
+
* finish the baseline on AISHELL2
 +
* do some research on compression
 
||  
 
||  
 
*  
 
*  
第49行： 第53行：
 
|Zhaodi Qi
 
|Zhaodi Qi
 
||  
 
||  
−
*  
+
* Made a confusion matrix for Various dialects
 +
* Added svm after ivector
 +
* summarized the entry system method of the dialect finals.
 +
* Learned cnn+ctcloss and tensorflow
 
||
 
||
−
*  
+
* Add acc for ptn
 
||
 
||
 
*   
 
*   
第100行： 第107行：
 
|Yang Zhang
 
|Yang Zhang
 
||  
 
||  
−
*  
+
* 1. Released my VPR app, and Published it in WeChat.
 +
* 2. Wrote a patent about speaker recognition.
 
||
 
||
−
*  
+
* Optimize and update my code. Add more functions in this VPR app.
 
||
 
||
 
*   
 
*   

2018年12月7日 (五) 10:05的最后版本

People Last Week This Week Task Tracking (DeadLine)
Yibo Liu
Xiuqi Jiang
  • Discussed code reconstruction work with Yibo Liu and set forth the aims of simplification and modularization.
  • Made research on meta learning and zero-shot learning, preparing for a weekly report.
  • Quicken the pace of code reconstruction.
Jiayao Wu
  • do research on ASR data size for End2End
  • do research on training tricks for End2End ASR of Mandarin & Japanese
  • finish a baseline on WSJ
  • finish the baseline on AISHELL2
  • do some research on compression
Zhaodi Qi
  • Made a confusion matrix for Various dialects
  • Added svm after ivector
  • summarized the entry system method of the dialect finals.
  • Learned cnn+ctcloss and tensorflow
  • Add acc for ptn
Jiawei Yu
  • learn the method of attention for SRE
  • Read papers about joint learning method combine PLDA.
  • Establish the attention baseline of SRE
Yunqi Cai
Dan He
  • 1.Read the first part of the book "Tensor Networks for Dimensionality Reduction and Large-Scale Optimization" written by Andrzej Cichocki and Ivan Oseledets.
  • 2. Initial understanding of the CP decomposition and Tucker decomposition,but the TT decomposition has not yet understand.
  • 1.Continue read the book to study the TT decomposition.
  • 2. Prepare a paper sharing about tensor decomposition.
Yang Zhang
  • 1. Released my VPR app, and Published it in WeChat.
  • 2. Wrote a patent about speaker recognition.
  • Optimize and update my code. Add more functions in this VPR app.
取自“http://index.cslt.org/mediawiki/index.php?title=2018-12-05&oldid=31554”