“2018-11-28”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
 
（9位用户的15个中间修订版本未显示）
第3行： 第3行：
 
!People !! Last Week !! This Week !! Task Tracking (<font color="red">DeadLine</font>)
 
!People !! Last Week !! This Week !! Task Tracking (<font color="red">DeadLine</font>)
 
|-
 
|-
−
|Miao Zhang
+
 
 +
 
 +
 
 +
 
 +
|-
 +
|Yibo Liu
 
||  
 
||  
−
*  
+
* Run several text classification baseline models
 
||
 
||
−
*  
+
* Reconstruct the code of poem generation.
 +
||
 +
* 
 +
|-
 +
 
 +
 
 +
 
 +
 
 +
|-
 +
|Xiuqi Jiang
 
||  
 
||  
−
*  
+
* Have been following CS224n and learning details about language model.
 +
* Read codes and watched over-fitting problems during practice.
 +
* Compared codes on couplet generating and ViVi.
 +
||
 +
* Read the paper "Generating Sentences from a Continuous Space” and work out how VAE goes for sentences.
 +
* Complete current models.
 +
||
 +
* 
 
|-
 
|-
 +
  
  
  
 
|-
 
|-
−
|Ying Shi 
+
|Jiayao Wu
 
||  
 
||  
−
*  
+
*Read the paper about TDNN-F and the corresponding codes in kaldi.
 +
*establish the TDNN-F baseline for WSJ.
 +
||
 +
*There still exists some bugs in kaldi. solve the configuration problems for kaldi.
 +
*run the baseline but not finished yet.
 
||  
 
||  
 
*  
 
*  
 +
|-
 +
 +
 +
 +
 +
|-
 +
|Zhaodi Qi
 +
||
 +
* Completed the baseline.
 +
* Learned a little tensorflow.
 +
||
 +
* practice tensorflow and read codes about acoustic model.
 
||
 
||
 
*   
 
*   
 
|-
 
|-
 +
  
  
  
 
|-
 
|-
−
|Lantian Li 
+
|Jiawei Yu
 +
||
 +
* Read the Lantian's phd graduation thesis
 +
* Learn CNN structure for SRE
 +
* Adapt BNF to SRE
 
||  
 
||  
−
* Commercial deep speaker model training. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=646]
+
* Continue investigate the latest paper on NN model for SRE
−
* Phone-aware scoring on deep speaker feature. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=643]
+
* Complete the BNF experiment
−
* Phonetic speaker embedding. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=644]
+
−
* Overlap training for speaker features. [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=lilt&step=view_request&cvssid=645]
+
 
||
 
||
−
* Commercial deep speaker model training.
+
*
−
* Phone-aware scoring on deep speaker feature.
+
|-
−
* Phonetic speaker embedding.
+
 
−
* Overlap training for speaker features.
+
 
 +
|-
 +
|Yunqi Cai
 
||  
 
||  
−
*  
+
* Read "Introduction to modern machine learning technology"
 +
||
 +
* Read "Introduction to modern machine learning technology" and think about the research direction
 +
||
 +
* 
 
|-
 
|-
 +
 +
 
|-
 
|-
−
|Zhiyuan Tang
+
|Dan He
 
||  
 
||  
−
* A brief survey on oral language evaluation, both on application and algorithm
+
*Read some paper about tensorizing neural network
 +
*Try to know that how to reduce the number of parameters by tensor decomposition
 +
||
 +
*Continue learn TT-format to represent the dense weight matrix of the fully-connected.
 
||
 
||
−
* A test version of Parrot
+
*
−
* Patent of Parrot
+
|-
 +
 
 +
 
 +
 
 +
 
 +
|-
 +
|Yang Zhang
 +
||
 +
* review school subjects and prepare for my mid-term exams.
 +
* built a basic web-client in WeChat (with my classmate's help)
 +
* Applicated a domain name and SSL certificate, and wrote some back-end code (后端代码).
 +
* made a HTTPs connection and  a web socket connection between WeChat web-client and server.
 +
||
 +
* try to finish this WeChat app as soon as possible.
 
||
 
||
−
*
+
*
 
|-
 
|-
 +
 +
  
  
 
|}
 
|}

2018年11月30日 (五) 04:33的最后版本

People Last Week This Week Task Tracking (DeadLine)
Yibo Liu
  • Run several text classification baseline models
  • Reconstruct the code of poem generation.
Xiuqi Jiang
  • Have been following CS224n and learning details about language model.
  • Read codes and watched over-fitting problems during practice.
  • Compared codes on couplet generating and ViVi.
  • Read the paper "Generating Sentences from a Continuous Space” and work out how VAE goes for sentences.
  • Complete current models.
Jiayao Wu
  • Read the paper about TDNN-F and the corresponding codes in kaldi.
  • establish the TDNN-F baseline for WSJ.
  • There still exists some bugs in kaldi. solve the configuration problems for kaldi.
  • run the baseline but not finished yet.
Zhaodi Qi
  • Completed the baseline.
  • Learned a little tensorflow.
  • practice tensorflow and read codes about acoustic model.
Jiawei Yu
  • Read the Lantian's phd graduation thesis
  • Learn CNN structure for SRE
  • Adapt BNF to SRE
  • Continue investigate the latest paper on NN model for SRE
  • Complete the BNF experiment
Yunqi Cai
  • Read "Introduction to modern machine learning technology"
  • Read "Introduction to modern machine learning technology" and think about the research direction
Dan He
  • Read some paper about tensorizing neural network
  • Try to know that how to reduce the number of parameters by tensor decomposition
  • Continue learn TT-format to represent the dense weight matrix of the fully-connected.
Yang Zhang
  • review school subjects and prepare for my mid-term exams.
  • built a basic web-client in WeChat (with my classmate's help)
  • Applicated a domain name and SSL certificate, and wrote some back-end code (后端代码).
  • made a HTTPs connection and a web socket connection between WeChat web-client and server.
  • try to finish this WeChat app as soon as possible.
取自“http://cslt.org/mediawiki/index.php?title=2018-11-28&oldid=31448”