“Zhiyong Zhang”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（→‎Technical Report To Write）
第1行： 第1行：
  
−
=Task To Do=
 
−
* 1, RNN speech recognition (Tied-context-dependent-state and End-to-End)
 
−
* 2, Real environment noise cancellation(DNN-DAE/CNN-DAE/RNN-DAE: echo or reverberation)
 
−
* 3, Integrate the class information to HCLG fst for speech recognition
 
−
* 4, Multi-Mode features based VAD
 
−
* 5, DNN based Language identification and Speaker identification
 
−
* 6, Distant speech recognition(Reverberation, Mutli-microphones)
 
−
* 7, Voice conversation
 
−
* 8, Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method.
 
−
* 9, Sparse DNN
 
−
* 10, Neural network visulization
 
−
* 11, DAE+dropout
 
−
 
−
=Technical Report To Write=
 
−
* 1, DNN-DAE based noise cancellation --Mengyuan Zhao
 
−
* 2, Speech Rate DNN speech recognition --Shi Yin
 
−
* 3, CNN+fbank feature combination --Mian Wang
 
−
* 4, Uyghur low-resource acoustic model enhancement --Shi Yin
 
−
* 5, Uyghur 20h database release --
 
  
 
=Papers To Read =
 
=Papers To Read =

2015年1月15日 (四) 00:43的版本


Papers To Read

  • 1, Learned-Norm pooling for deep feedforward and recurrent neural networks


Task schedules

Summary

   --------------------------------------------------------------------------------------------------------
    Priority | Tasks name                    |      Status          |     Notions
   --------------------------------------------------------------------------------------------------------    
        1    | Bi-Softmax                    | ■■■□□□□□□□ | 1400h am training and problem fixing
   --------------------------------------------------------------------------------------------------------
        2    | RNN+DAE                       | □□□□□□□□□□ |
   --------------------------------------------------------------------------------------------------------

Speech Recognition

Multi-lingual Am training

Bi-Softmax

  • Using two distinct softmax for English and Chinese data.
  • Testing on 100h-Ch+100h-En, better performance observed.
  • Now testing the source code on 1400h_8k data, but stange decoding results got.Need to further investigate.
取自“http://cslt.org/mediawiki/index.php?title=Zhiyong_Zhang&oldid=13541”