“Task List”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第15行: 第15行:
 
=Task DONE=
 
=Task DONE=
 
*Multi-Mode features based VAD*
 
*Multi-Mode features based VAD*
:*--Shi Yin, DONE
+
:*Shi Yin, DONE
 +
 
 
*DNN based Language identification and Speaker identification*
 
*DNN based Language identification and Speaker identification*
:*Xuewei Zhang/Zhiyuan Tang
+
:*Xuewei Zhang/Zhiyuan Tang
 +
 
 
*Neural network visulization*
 
*Neural network visulization*
:*Mian Wang,DONE
+
:*Mian Wang,DONE
 +
 
 
*Dark knowledge*  
 
*Dark knowledge*  
:*Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu
+
:*Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu
 +
 
 
*Normal RNN speech recognition*
 
*Normal RNN speech recognition*
:*Mengyuan Zhao
+
:*Mengyuan Zhao
  
 
=Technical Report To Write=
 
=Technical Report To Write=

2015年7月28日 (二) 10:26的版本

Task To Do

1,  End-to-End speech recognition           --Zhiyuan Tang
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


Task DONE

  • Multi-Mode features based VAD*
  • 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

1, DNN-DAE based noise cancellation -- Xiangyu Zeng / Mengyuan Zhao / Zhiyong Zhang  --DONE
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