“Task List”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
=Task To Do= | =Task To Do= | ||
| − | [['''* 1, RNN speech recognition (Tied-context-dependent-state and End-to-End) --Chao Liu/Zhiyuan Tang | + | [['''* 1, RNN speech recognition (Tied-context-dependent-state and End-to-End) --Chao Liu/Zhiyuan Tang''']]''']] |
| − | * 2, Real environment noise cancellation(RNN-DAE: echo or reverberation) --Zhiyong Zhang | + | [['''* 2, Real environment noise cancellation(RNN-DAE: echo or reverberation) --Zhiyong Zhang''']] |
* 3, Integrate the class information to HCLG fst for speech recognition | * 3, Integrate the class information to HCLG fst for speech recognition | ||
| − | * 4, Multi-Mode features based VAD --Shi Yin, | + | * 4, Multi-Mode features based VAD --Shi Yin, DONE |
| − | * 5, DNN based Language identification and Speaker identification | + | [['''* 5, DNN based Language identification and Speaker identification''']] |
| − | * 6, Distant speech recognition(Reverberation, Mutli-microphones) --(Lasso),Xuewei Zhang | + | [['''* 6, Distant speech recognition(Reverberation, Mutli-microphones) --(Lasso),Xuewei Zhang''']] |
| − | * 7, Voice conversation --Zhongwei Yao | + | [['''* 7, Voice conversation --Zhongwei Yao''']] |
* 8, Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method. --Zhiyong Zhang | * 8, Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method. --Zhiyong Zhang | ||
* 9, Sparse DNN --Zhiyuan Tang/Chao Liu | * 9, Sparse DNN --Zhiyuan Tang/Chao Liu | ||
| − | * 10, Neural network visulization --Mian Wang, | + | * 10, Neural network visulization --Mian Wang,DONE |
| − | * 11, DNN training GPU parallelization , nnet2 optimization. | + | [['''* 11, DNN training GPU parallelization , nnet2 optimization.''']] |
| − | * 12, Monmentum-like Hessien acceleration | + | [['''* 12, Monmentum-like Hessien acceleration''']] |
| − | * 13, Correlation based SEONE cluster | + | [['''* 13, Correlation based SEONE cluster''']] |
| − | + | ||
=Technical Report To Write= | =Technical Report To Write= | ||
| − | * 1, DNN-DAE based noise cancellation -- Xiangyu Zeng / Mengyuan Zhao / Zhiyong Zhang | + | * 1, DNN-DAE based noise cancellation -- Xiangyu Zeng / Mengyuan Zhao / Zhiyong Zhang --DONE |
| − | * 2, Speech Rate DNN speech recognition --Shi Yin | + | * 2, Speech Rate DNN speech recognition --Shi Yin/Xiangyu Zeng --DONE |
* 3, CNN+fbank feature combination --Mian Wang /Yiye Lin /Mengyuan Zhao /Shi Yin | * 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 | + | * 4, Uyghur low-resource acoustic model enhancement -- Shi Yin / Mengyuan Zhao / Zhiyong Zhang --DONE |
| − | * 5, Uyghur 20h database release --Kaer /Shi Yin | + | * 5, Uyghur 20h database release --Kaer /Shi Yin --DONE |
=Paper to Write= | =Paper to Write= | ||
| − | |||
| − | |||
2015年4月22日 (三) 13:26的版本
Task To Do
'''* 1, RNN speech recognition (Tied-context-dependent-state and End-to-End) --Chao Liu/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, Multi-Mode features based VAD --Shi Yin, DONE
'''* 5, DNN based Language identification and Speaker identification''' '''* 6, Distant speech recognition(Reverberation, Mutli-microphones) --(Lasso),Xuewei Zhang''' '''* 7, Voice conversation --Zhongwei Yao'''
- 8, Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method. --Zhiyong Zhang
- 9, Sparse DNN --Zhiyuan Tang/Chao Liu
- 10, Neural network visulization --Mian Wang,DONE
'''* 11, DNN training GPU parallelization , nnet2 optimization.''' '''* 12, Monmentum-like Hessien acceleration''' '''* 13, Correlation based SEONE cluster'''
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
