“Task List”版本间的差异
来自cslt Wiki
| 第1行： | 第1行： | ||
=Task To Do= | =Task To Do= | ||
*End-to-End speech recognition | *End-to-End speech recognition | ||
| − | :*Zhiyuan Tang | + | :*Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang |
*Real environment noise cancellation | *Real environment noise cancellation | ||
| − | |||
:*(RNN-DAE: echo or reverberation) | :*(RNN-DAE: echo or reverberation) | ||
| − | :*Zhiyong Zhang | + | :*Mengyuan Zhao/Zhiyong Zhang |
*Integrate the class information to HCLG fst for speech recognition | *Integrate the class information to HCLG fst for speech recognition | ||
| 第21行： | 第20行： | ||
*Sparse DNN | *Sparse DNN | ||
| − | :*Zhiyuan Tang | + | :*Zhiyuan Tang |
*DNN training GPU parallelization , nnet2 optimization | *DNN training GPU parallelization , nnet2 optimization | ||
| 第28行： | 第27行： | ||
*Correlation based SEONE cluster | *Correlation based SEONE cluster | ||
| + | |||
| + | *NN GPU parallel traing | ||
| + | :*Sheng Su | ||
| + | |||
| + | *Audio Embedding | ||
| + | |||
| + | *Activation value normalize through time | ||
| + | :* For bigger learning rate | ||
| + | |||
| + | *Mix-training Balance decision tree | ||
| + | :* Zhiyong Zhang | ||
| + | |||
| + | *RNN training accelerating | ||
| + | |||
| + | * | ||
| 第56行： | 第70行： | ||
=Paper to Write= | =Paper to Write= | ||
| + | |||
| + | =Project= | ||
| + | * Xiaomi TV | ||
| + | :*Mengyuan Zhao/Zhiyong Zhang | ||
| + | :*TAG-lm & Domain-specific general lm | ||
| + | |||
| + | *Chinese-English mix-training | ||
2015年7月28日 (二) 10:39的版本
Task To Do
- End-to-End speech recognition
- Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
- Real environment noise cancellation
- (RNN-DAE: echo or reverberation)
- Mengyuan Zhao/Zhiyong Zhang
- Integrate the class information to HCLG fst for speech recognition
- Distant speech recognition
- (Reverberation, Mutli-microphones)*
- (Lasso),Xuewei Zhang
- Voice conversation
- xx
- Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
- Zhiyong Zhang
- Sparse DNN
- Zhiyuan Tang
- DNN training GPU parallelization , nnet2 optimization
- Monmentum-like Hessien-Free acceleration
- Correlation based SEONE cluster
- NN GPU parallel traing
- Sheng Su
- Audio Embedding
- Activation value normalize through time
- For bigger learning rate
- Mix-training Balance decision tree
- Zhiyong Zhang
- RNN training accelerating
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
