“ASR Status Report 2016-10-31”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第29行： 第29行：
 
|Lantian Li   
 
|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1日 (二) 02:50的版本

Date People Last Week This Week


2016.10.24 Hang Luo
Ying Shi
  • DNN and TDNN visualization;CNN baseline(th30) new model DNN+lstm(th30);ML-book
  • ML-book continue DNN visualization maybe I should find a new tool t-sne is not powerful enough
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://cslt.org/mediawiki/index.php?title=ASR_Status_Report_2016-10-31&oldid=23277”