“Task List”版本间的差异
来自cslt Wiki
（→Task To Do） |
|||
| 第1行： | 第1行： | ||
=Task To Do= | =Task To Do= | ||
| − | 1, | + | 1, End-to-End speech recognition --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 | + | 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- | |
| − | + | 1, Multi-Mode features based VAD --Shi Yin, DONE | |
| + | 2, DNN based Language identification and Speaker identification --Xuewei Zhang/Zhiyuan Tang | ||
| + | 3, Neural network visulization --Mian Wang,DONE | ||
| + | 4, Dark knowledge --Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu | ||
| + | 5, Normal RNN speech recognition --Mengyuan Zhao | ||
=Technical Report To Write= | =Technical Report To Write= | ||
2015年7月28日 (二) 09:20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-
1, Multi-Mode features based VAD --Shi Yin, DONE 2, DNN based Language identification and Speaker identification --Xuewei Zhang/Zhiyuan Tang 3, Neural network visulization --Mian Wang,DONE 4, Dark knowledge --Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu 5, 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
