“Task List”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(4位用户的34个中间修订版本未显示)
第1行: 第1行:
=Task To Do=
 
*End-to-End speech recognition
 
:*Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
 
  
*Real environment noise cancellation
+
=Tasks at hand=
:*(RNN-DAE: echo or reverberation)
+
:*Mengyuan Zhao/Zhiyong Zhang
+
  
*Integrate the class information to HCLG fst for speech recognition
+
==Speech Recognition==
  
*Distant speech recognition
+
===joint learning===
:*(Reverberation, Mutli-microphones)*
+
* Hang Luo, Zhiyuan Tang
:*(Lasso),Xuewei Zhang
+
  
*Voice conversation
+
===visualization===
:*xx
+
* Ying Shi, Zhiyuan Tang
  
*Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
+
==Speaker Recognition==
:*Zhiyong Zhang
+
*Lantian Li, Yixiang Chen
  
*Sparse DNN
 
:*Zhiyuan Tang
 
  
*DNN training GPU parallelization , nnet2 optimization
+
=Tasks Done=
  
*Monmentum-like Hessien-Free acceleration
+
=Technical Reports to write=
  
*Correlation based SEONE cluster
+
=Papers to write=
  
*NN GPU parallel traing
+
=Patents to write=
:*Sheng Su
+
  
*Audio Embedding
+
=Patents done=
  
*Activation value normalize through time
+
=Projects=
:* For bigger learning rate
+
  
*Mix-training Balance decision tree
 
:* Zhiyong Zhang
 
  
*RNN training accelerating
+
------------------------------
 
+
[[task previous]]
*
+
 
+
 
+
=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=
+
 
+
=Project=
+
* Xiaomi TV
+
:*Mengyuan Zhao/Zhiyong Zhang
+
:*TAG-lm & Domain-specific general lm
+
 
+
*Chinese-English mix-training
+

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