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