“Task List”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
NN Multi-GPU parallel traing
 
(3位用户的9个中间修订版本未显示)
第1行: 第1行:
=Task To Do=
 
==Speech Recognition==
 
===End-to-End speech recognition===
 
* Discriminative-Learning code implementation
 
:* Zhiyuan Tang
 
*Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
 
  
===Multi-task===
+
=Tasks at hand=
* Fusion of speech-recognition and speech-rate
+
:* Xiangyu Zeng
+
* Self-informed neural network structure learning
+
:* Mengyuan Zhao
+
  
===Integrate the class information to HCLG fst for speech recognition===
+
==Speech Recognition==
 
+
===Distant speech recognition===
+
*RNN-DAE: echo or reverberation
+
:*Xuewei Zhang/Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
+
*Reverberation
+
:*Mutli-microphones
+
:*(Lasso),Xuewei Zhang
+
 
+
===Voice conversation===
+
 
+
===Sparse DNN===
+
*Zhiyuan Tang
+
 
+
===Correlation based SENONE cluster===
+
 
+
===NN Multi-GPU parallel traing===
+
*Multi-Machine
+
:*Sheng Su
+
*Multi-GPU on one Machine
+
:*Sheng Su
+
* nnet3 code test
+
 
+
===Audio Embedding===
+
*Ke Ning
+
 
+
===RNN training accelerating===
+
 
+
===Data selection===
+
*Zhiyong Zhang
+
*Sub-modular data selection
+
*Objective-function loss training self-adaptation
+
 
+
===Decoder===
+
*Confidence output for task-required
+
 
+
==Speaker Verification==
+
===binary code===
+
*Lantian Li
+
 
+
===RNN-ivector===
+
*Lantian Li
+
 
+
===DNN clustering===
+
*Lantian Li
+
 
+
=Task DONE=
+
==Multi-Mode features based VAD==
+
* Shi Yin
+
 
+
==DNN based Language identification and Speaker identification==
+
* Xuewei Zhang/Zhiyuan Tang
+
  
==Neural network visulization==
+
===joint learning===
* Mian Wang,DONE
+
* Hang Luo, Zhiyuan Tang
  
==Dark knowledge==
+
===visualization===
* Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu
+
* Ying Shi, Zhiyuan Tang
  
==Normal RNN speech recognition==
+
==Speaker Recognition==
* Mengyuan Zhao
+
*Lantian Li, Yixiang Chen
  
==Monmentum-like Hessien-Free acceleration==
 
* Nestrov/Adagrad/AdaDelta/AdaM
 
* Zhiyong Zhang/Xiangyu Zeng
 
  
==Activation value normalization through time --Batch Normalization==
+
=Tasks Done=
* Zhiyong Zhang
+
  
==Mix-training Balance decision tree==
+
=Technical Reports to write=
* Zhiyong Zhang
+
  
==20-h Chinese data-set release==
+
=Papers to write=
* Xuewei Zhang
+
  
==Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method==
+
=Patents to write=
* nne3 test --Xuewei Zhang
+
  
=Technical Report To Write=
+
=Patents done=
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=
+
=Projects=
  
=Project=
 
* Xiaomi TV
 
:*Mengyuan Zhao/Zhiyong Zhang
 
:*TAG-lm & Domain-specific general lm
 
  
*Chinese-English mix-training
+
------------------------------
 +
[[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