“Task List”版本间的差异
来自cslt Wiki
（→Task DONE） |
|||
| 第8行： | 第8行： | ||
*Distant speech recognition | *Distant speech recognition | ||
:*RNN-DAE: echo or reverberation | :*RNN-DAE: echo or reverberation | ||
| − | ::*Mengyuan Zhao/Zhiyong Zhang | + | ::*Xuewei Zhang/Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang |
:*Reverberation | :*Reverberation | ||
::*Mutli-microphones | ::*Mutli-microphones | ||
| 第14行： | 第14行： | ||
*Voice conversation | *Voice conversation | ||
| − | |||
*Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method | *Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method | ||
| − | :* | + | :* RNN-Rectifier |
| + | ::*Zhiyuan Tang | ||
| + | :* P-norm | ||
*Sparse DNN | *Sparse DNN | ||
| 第23行： | 第24行： | ||
*Monmentum-like Hessien-Free acceleration | *Monmentum-like Hessien-Free acceleration | ||
| + | :*Zhiyong Zhang | ||
| + | |||
| + | *Correlation based SENONE cluster | ||
| − | |||
*NN Multi-GPU parallel traing | *NN Multi-GPU parallel traing | ||
:*Multi-Machine | :*Multi-Machine | ||
::* nnet2 optimization | ::* nnet2 optimization | ||
| + | ::*Sheng Su | ||
:*Multi-GPU on one Machine | :*Multi-GPU on one Machine | ||
::*Sheng Su | ::*Sheng Su | ||
*Audio Embedding | *Audio Embedding | ||
| + | :*Ke Ning | ||
*Activation value normalization through time | *Activation value normalization through time | ||
| 第48行： | 第53行： | ||
*Decoder | *Decoder | ||
:*Confidence output for task-required | :*Confidence output for task-required | ||
| + | |||
| + | *xx-h Chinese data-set release | ||
| + | :Xuewei Zhang | ||
| + | |||
==Speaker Verification== | ==Speaker Verification== | ||
2015年8月3日 (一) 12:03的版本
目录
Task To Do
Speech Recognition
- 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
- Xuewei Zhang/Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
- Reverberation
- Mutli-microphones
- (Lasso),Xuewei Zhang
- Voice conversation
- Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
- RNN-Rectifier
- Zhiyuan Tang
- P-norm
- Sparse DNN
- Zhiyuan Tang
- Monmentum-like Hessien-Free acceleration
- Zhiyong Zhang
- Correlation based SENONE cluster
- NN Multi-GPU parallel traing
- Multi-Machine
- nnet2 optimization
- Sheng Su
- Multi-GPU on one Machine
- Sheng Su
- Audio Embedding
- Ke Ning
- 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
- xx-h Chinese data-set release
- Xuewei Zhang
Speaker Verification
- binary code
- Lantian Li
- RNN-ivector
- Lantian Li
- DNN clustering
- Lantian Li
Task DONE
- Multi-Mode features based VAD
- Shi Yin
- 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
