“ASR Status Report 2016-10-31”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（以“ {| class="wikitable" !Date!!People !! Last Week !! This Week |- | rowspan="4"|2016.10.24 |Hang Luo || * || * |- |- |Ying Shi || * || * |- |...”为内容创建页面）
 
 
（3位用户的7个中间修订版本未显示）
第6行： 第6行：
  
 
|-
 
|-
−
| rowspan="4"|2016.10.24
+
| rowspan="5"|2016.10.31
 
|Hang Luo   
 
|Hang Luo   
 
||  
 
||  
−
*   
+
*  Know the source code of joint training.
 +
*  Experiments on joint training, change the receive computation blocks and try non-symmetric structure.The result expected on this Thursday.
 
||  
 
||  
−
*   
+
*  Find paper about joint training to read.
−
|-
+
*  Try new experiments according to last two experiments.
 +
|-  
  
  
第19行： 第21行：
 
|Ying Shi   
 
|Ying Shi   
 
||  
 
||  
−
*   
+
*  DNN and TDNN visualization;CNN baseline(th30) new model DNN+lstm(th30);ML-book [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=shiying&step=view_request&cvssid=569 slide]
 
||  
 
||  
−
*   
+
*  ML-book continue DNN visualization maybe I should find a new tool t-sne is not powerful enough
 
|-
 
|-
  
第27行： 第29行：
  
 
|-
 
|-
−
|Lantian Li  
+
|Yixiang Chen  
 
||  
 
||  
−
*
+
* Joint-training (GMM baseline)
 
||  
 
||  
−
*
+
* Joint-training
 
|-
 
|-
  
  
 +
 +
 +
|-
 +
|Lantian Li 
 +
||
 +
* Joint-training on TASLP (DNN i-vector parts). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=573]
 +
* Joint-training on SRE and LRE (Neural model is over-fitting...). [http://192.168.0.51:5555/cgi-bin/cvss/cvss_request.pl?account=tangzy&step=view_request&cvssid=574]
 +
||
 +
* Joint-training on TASLP.
 +
* Joint-training on SRE and LRE.
 +
|-
  
  

2016年11月2日 (三) 01:28的最后版本

Date People Last Week This Week


2016.10.31 Hang Luo
  • Know the source code of joint training.
  • Experiments on joint training, change the receive computation blocks and try non-symmetric structure.The result expected on this Thursday.
  • Find paper about joint training to read.
  • Try new experiments according to last two experiments.
Ying Shi
  • DNN and TDNN visualization;CNN baseline(th30) new model DNN+lstm(th30);ML-book slide
  • ML-book continue DNN visualization maybe I should find a new tool t-sne is not powerful enough
Yixiang Chen
  • Joint-training (GMM baseline)
  • Joint-training
Lantian Li
  • Joint-training on TASLP (DNN i-vector parts). [1]
  • Joint-training on SRE and LRE (Neural model is over-fitting...). [2]
  • Joint-training on TASLP.
  • Joint-training on SRE and LRE.
Zhiyuan Tang
  • O-COCOSDA 16, Bali.
  • report for Weekly Reading;
  • finish the additinal experiments of joint learning (speech & spk) for taslp (multi-task, ivector as part of input)[3].
取自“http://index.cslt.org/mediawiki/index.php?title=ASR_Status_Report_2016-10-31&oldid=23335”