“2022-01-24”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（以“{| class="wikitable" !People !! This Week !! Next Week !! Task Tracking (<font color="red">DeadLine</font>) |- |- |Dong Wang || * || * || * |- |- |Yunqi Cai ||...”为内容创建页面）
 
 
（13位用户的15个中间修订版本未显示）
第5行： 第5行：
 
|Dong Wang
 
|Dong Wang
 
||  
 
||  
−
*
+
* Reschedule the cycleFlow paper
 +
* Keep on investigation for multi-modality information fusion
 
||
 
||
−
*
+
* Rewrite cycleFlow
 
||
 
||
 
*   
 
*   
第16行： 第17行：
 
|Yunqi Cai
 
|Yunqi Cai
 
||   
 
||   
−
*
+
*Investigate railway Bureau; the practical application scenario of intelligent inspection robot
 +
*Prepare a report for Gusu Lab
 
||
 
||
−
*  
+
* keep on intelligent sensor investigation
 
||
 
||
 
*   
 
*   
第27行： 第29行：
 
|Lantian Li
 
|Lantian Li
 
||  
 
||  
−
*  
+
* Push CNCSRC
 +
* Submit final papers
 +
* Prepare hard trials paper
 
||
 
||
−
*  
+
* Go on hard trials paper
 
||
 
||
 
*   
 
*   
第38行： 第42行：
 
|Ying Shi
 
|Ying Shi
 
||  
 
||  
−
*
+
* investige forward attention [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=829 here]
 
||
 
||
−
*
+
* continue on forward attention
 
||
 
||
 
*   
 
*   
第49行： 第53行：
 
|Haoran Sun
 
|Haoran Sun
 
||  
 
||  
−
*  
+
* some experiments on AutoVC [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/1c/Autovc.pdf pdf]
 
||
 
||
−
*  
+
* more experiments for cycle loss
 
||
 
||
 
*   
 
*   
第60行： 第64行：
 
|Chen Chen
 
|Chen Chen
 
||  
 
||  
−
*
+
* Experiments on kmeans and use label for clustering
 +
* Experiments on # of phn kinds
 +
* [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=cchen&step=view_request&cvssid=846 cvss]
 
||
 
||
−
*
+
* Check the experiment of label clustering
 
||
 
||
 
*   
 
*   
第71行： 第77行：
 
|Pengqi Li
 
|Pengqi Li
 
||   
 
||   
−
*  
+
* study representation learning(self-supervised learning)
 +
* Using mel-spectrum and standard softmax on small data, models are trained
 +
* Data preprocessing
 
||
 
||
−
*  
+
* Visualization on a small models(mel-spectrum & MFCC)
 +
* Implement RELAX
 
||
 
||
 
*   
 
*   
第82行： 第91行：
 
|Weida Liang
 
|Weida Liang
 
||   
 
||   
−
*
+
* Conduct wav2vec test
 +
* Adjust andRun wav2vec+decoder model(training 40k/50k)
 +
* Add experiment details to paper
 
||
 
||
−
*
+
* paper submission to Arxiv
 
||
 
||
 
*   
 
*   
第92行： 第103行：
 
|Zixi Yan
 
|Zixi Yan
 
||   
 
||   
−
*
+
* Training supervised speech recognition models using wav2vec features
 
||
 
||
−
*
+
* Experiments with more data sets
 
||
 
||
 
*   
 
*   
第102行： 第113行：
 
|Sirui Li
 
|Sirui Li
 
||   
 
||   
−
*
+
* Extract MFCC features for GAN
 +
* Learning Clustering Algorithms
 
||
 
||
−
*
+
* go on GAN experiment
 
||
 
||
 
*   
 
*   
第113行： 第125行：
 
|Haoyu Jiang
 
|Haoyu Jiang
 
||  
 
||  
−
*
+
* Complete data merge
 +
* Prepare group report
 
||
 
||
−
*
+
* Comparison of audio-video baseline
 
||
 
||
 
*   
 
*   
第124行： 第137行：
 
|Ruihai Hou
 
|Ruihai Hou
 
||  
 
||  
−
*  
+
* Preproess data for the training of UIS-RNN
 +
* Train the UIS-RNN model on small dataset
 
||
 
||
 
*  
 
*  
第134行： 第148行：
 
|Renmiao Chen
 
|Renmiao Chen
 
||  
 
||  
−
*
+
* Finish MI test.
 +
* Finish CKA test.
 
||
 
||
 
*
 
*

2022年1月24日 (一) 11:05的最后版本

People This Week Next Week Task Tracking (DeadLine)
Dong Wang
  • Reschedule the cycleFlow paper
  • Keep on investigation for multi-modality information fusion
  • Rewrite cycleFlow
Yunqi Cai
  • Investigate railway Bureau; the practical application scenario of intelligent inspection robot
  • Prepare a report for Gusu Lab
  • keep on intelligent sensor investigation
Lantian Li
  • Push CNCSRC
  • Submit final papers
  • Prepare hard trials paper
  • Go on hard trials paper
Ying Shi
  • investige forward attention here
  • continue on forward attention
Haoran Sun
  • some experiments on AutoVC pdf
  • more experiments for cycle loss
Chen Chen
  • Experiments on kmeans and use label for clustering
  • Experiments on # of phn kinds
  • cvss
  • Check the experiment of label clustering
Pengqi Li
  • study representation learning(self-supervised learning)
  • Using mel-spectrum and standard softmax on small data, models are trained
  • Data preprocessing
  • Visualization on a small models(mel-spectrum & MFCC)
  • Implement RELAX
Weida Liang
  • Conduct wav2vec test
  • Adjust andRun wav2vec+decoder model(training 40k/50k)
  • Add experiment details to paper
  • paper submission to Arxiv
Zixi Yan
  • Training supervised speech recognition models using wav2vec features
  • Experiments with more data sets
Sirui Li
  • Extract MFCC features for GAN
  • Learning Clustering Algorithms
  • go on GAN experiment
Haoyu Jiang
  • Complete data merge
  • Prepare group report
  • Comparison of audio-video baseline
Ruihai Hou
  • Preproess data for the training of UIS-RNN
  • Train the UIS-RNN model on small dataset
Renmiao Chen
  • Finish MI test.
  • Finish CKA test.
取自“http://cslt.org/mediawiki/index.php?title=2022-01-24&oldid=37698”