“2019-05-17”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(8位用户的10个中间修订版本未显示)
第22行: 第22行:
 
|Xiuqi Jiang
 
|Xiuqi Jiang
 
||  
 
||  
*  
+
* Recompiled the 1031k dataset and retrained the Seq2seq model.
 
||  
 
||  
*  
+
* Justify the loss and fix the rhyme part.
 
||
 
||
 
*   
 
*   
第62行: 第62行:
 
|Jiawei Yu
 
|Jiawei Yu
 
||  
 
||  
*  
+
* Did data preparation for zero-resource language recognition
 
||  
 
||  
*  
+
* Continue to improve the experiment of zero-resource recognition
 
||
 
||
 
*   
 
*   
第74行: 第74行:
 
|Wenwei Dong
 
|Wenwei Dong
 
||
 
||
*  
+
* prepare the report and use KL distance to predict score of L2 sentences
 
||  
 
||  
*
+
* add training data and try different languages
 
||
 
||
 
*   
 
*   
第87行: 第87行:
 
|Xueyi Wang
 
|Xueyi Wang
 
||
 
||
*  
+
* train and test v-vector
*
+
 
 
||  
 
||  
*
+
*be familiar with VAE
*
+
*go to next stage(unsupervised PLDA)
 
||
 
||
 
*   
 
*   
第102行: 第102行:
 
|Ziya Zhou
 
|Ziya Zhou
 
||  
 
||  
*  
+
* Revised the speech book
 +
* Made a list of 1,000 celebrities and downloaded videos of over 30 of them.
 
||
 
||
*  
+
* Continue downloading and editing videos of another 150 celebrities. 
*
+
 
||
 
||
 
*   
 
*   
第115行: 第115行:
 
|kaicheng li
 
|kaicheng li
 
||
 
||
*  
+
* Made the time schedule of the celebrity audio collection.
*  
+
* Start download vedio resources.
 
||  
 
||  
*
+
*Keep finding reliable recourses and make audio clips
*
+
 
||
 
||
 
*   
 
*   
第129行: 第128行:
 
|Haolin Chen
 
|Haolin Chen
 
||
 
||
*
+
* Basic maths:MLE、ztest、ttest、jbtest...
*  
+
||
 +
* Continue learning probability & statistics
 +
||
 +
 +
|-
 +
 
 +
 
 +
 
 +
|-
 +
|Haoran Sun
 +
||
 +
* did some tests on  Fn asr engine
 +
* corrected some errors in the speech-book
 
||  
 
||  
*
+
* continue testing  on the robustness of Fn asr engine
 
||
 
||
 
*   
 
*   

2019年5月17日 (五) 06:17的最后版本

People This Week Next Week Task Tracking (DeadLine)
Yibo Liu
Xiuqi Jiang
  • Recompiled the 1031k dataset and retrained the Seq2seq model.
  • Justify the loss and fix the rhyme part.
Jiayao Wu
  • did some experiments of adaboost on ASR and have some basic results
  • working on the speechbook
  • keep on doing experiments on larger data_set.
Zhaodi Qi
  • Do experiment on Mult-scale information.
  • Do experiment on Multi-language BN
Jiawei Yu
  • Did data preparation for zero-resource language recognition
  • Continue to improve the experiment of zero-resource recognition
Wenwei Dong
  • prepare the report and use KL distance to predict score of L2 sentences
  • add training data and try different languages
Xueyi Wang
  • train and test v-vector
  • be familiar with VAE
  • go to next stage(unsupervised PLDA)
Ziya Zhou
  • Revised the speech book
  • Made a list of 1,000 celebrities and downloaded videos of over 30 of them.
  • Continue downloading and editing videos of another 150 celebrities.
kaicheng li
  • Made the time schedule of the celebrity audio collection.
  • Start download vedio resources.
  • Keep finding reliable recourses and make audio clips
Haolin Chen
  • Basic maths:MLE、ztest、ttest、jbtest...
  • Continue learning probability & statistics
Haoran Sun
  • did some tests on Fn asr engine
  • corrected some errors in the speech-book
  • continue testing on the robustness of Fn asr engine