“Task List”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(4位用户的44个中间修订版本未显示)
第1行: 第1行:
=Task To Do=
 
  
1,  End-to-End speech recognition          --Zhiyuan Tang
+
=Tasks at hand=
2,  Real environment noise cancellation(RNN-DAE: echo or reverberation)              --Zhiyong Zhang
+
3,  Integrate the class information to HCLG fst for speech recognition
+
4,  Distant speech recognition(Reverberation, Mutli-microphones)                    --(Lasso),Xuewei Zhang
+
5,  Voice conversation                                                              --xx
+
6,  Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method. --Zhiyong Zhang
+
7,  Sparse DNN --Zhiyuan Tang/Chao Liu
+
8,  DNN training GPU parallelization , nnet2 optimization.
+
9,  Monmentum-like Hessien-Free acceleration
+
10, Correlation based SEONE cluster
+
  
 +
==Speech Recognition==
  
=Task DONE=
+
===joint learning===
==Multi-Mode features based VAD==
+
* Hang Luo, Zhiyuan Tang
  --Shi Yin, DONE
+
==DNN based Language identification and Speaker identification==  --Xuewei Zhang/Zhiyuan Tang
+
== Neural network visulization==    --Mian Wang,DONE
+
== Dark knowledge==                --Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu
+
== Normal RNN speech recognition==  --Mengyuan Zhao
+
  
=Technical Report To Write=
+
===visualization===
1, DNN-DAE based noise cancellation -- Xiangyu Zeng / Mengyuan Zhao / Zhiyong Zhang  --DONE
+
* Ying Shi, Zhiyuan Tang
2, Speech Rate DNN speech recognition --Shi Yin/Xiangyu Zeng --DONE
+
3, CNN+fbank feature combination --Mian Wang /Yiye Lin /Mengyuan Zhao /Shi Yin
+
4, Uyghur low-resource acoustic model enhancement -- Shi Yin / Mengyuan Zhao / Zhiyong Zhang --DONE
+
5, Uyghur 20h database release --Kaer /Shi Yin --DONE
+
6,Dark-Knowledge Transfer
+
    *: Xiangyu Zeng/ Mengyuan Zhao / Zhiyong Zhang
+
  
=Paper to Write=
+
==Speaker Recognition==
 +
*Lantian Li, Yixiang Chen
 +
 
 +
 
 +
=Tasks Done=
 +
 
 +
=Technical Reports to write=
 +
 
 +
=Papers to write=
 +
 
 +
=Patents to write=
 +
 
 +
=Patents done=
 +
 
 +
=Projects=
 +
 
 +
 
 +
------------------------------
 +
[[task previous]]

2016年10月16日 (日) 12:31的最后版本

Tasks at hand

Speech Recognition

joint learning

  • Hang Luo, Zhiyuan Tang

visualization

  • Ying Shi, Zhiyuan Tang

Speaker Recognition

  • Lantian Li, Yixiang Chen


Tasks Done

Technical Reports to write

Papers to write

Patents to write

Patents done

Projects


task previous