“Task List”版本间的差异
来自cslt Wiki
第16行: | 第16行: | ||
*Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method | *Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method | ||
− | :*Zhiyong Zhang | + | :*Zhiyong Zhang/Zhiyuan Tang |
*Sparse DNN | *Sparse DNN | ||
:*Zhiyuan Tang | :*Zhiyuan Tang | ||
− | |||
− | |||
*Monmentum-like Hessien-Free acceleration | *Monmentum-like Hessien-Free acceleration | ||
第28行: | 第26行: | ||
*NN Multi-GPU parallel traing | *NN Multi-GPU parallel traing | ||
− | :*Sheng Su | + | :*Multi-Machine |
+ | ::* nnet2 optimization | ||
+ | :*Multi-GPU on one Machine | ||
+ | ::*Sheng Su | ||
*Audio Embedding | *Audio Embedding |
2015年7月28日 (二) 10:52的版本
Task To Do
- End-to-End speech recognition
- Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
- Integrate the class information to HCLG fst for speech recognition
- Distant speech recognition
- RNN-DAE: echo or reverberation
- Mengyuan Zhao/Zhiyong Zhang
- Reverberation
- Mutli-microphones
- (Lasso),Xuewei Zhang
- Voice conversation
- xx
- Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
- Zhiyong Zhang/Zhiyuan Tang
- Sparse DNN
- Zhiyuan Tang
- Monmentum-like Hessien-Free acceleration
- Correlation based SEONE cluster
- NN Multi-GPU parallel traing
- Multi-Machine
- nnet2 optimization
- Multi-GPU on one Machine
- Sheng Su
- Audio Embedding
- Activation value normalization through time
- For bigger learning rate
- Mix-training Balance decision tree
- Zhiyong Zhang
- RNN training accelerating
- Data selection
- Zhiyong Zhang
- Sub-modular data selection
- Decoder
- Confidence output for task-required
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
Project
- Xiaomi TV
- Mengyuan Zhao/Zhiyong Zhang
- TAG-lm & Domain-specific general lm
- Chinese-English mix-training