“Task List”版本间的差异
来自cslt Wiki
（→Decoder=） |
|||
| 第23行： | 第23行： | ||
===Voice conversation=== | ===Voice conversation=== | ||
| − | ==Sparse DNN=== | + | ===Sparse DNN=== |
*Zhiyuan Tang | *Zhiyuan Tang | ||
| 第45行： | 第45行： | ||
*Objective-function loss training self-adaptation | *Objective-function loss training self-adaptation | ||
| − | ==Decoder== | + | ===Decoder=== |
*Confidence output for task-required | *Confidence output for task-required | ||
| 第59行： | 第59行： | ||
=Task DONE= | =Task DONE= | ||
| − | ===Multi-Mode features based VAD | + | ===Multi-Mode features based VAD== |
* Shi Yin | * Shi Yin | ||
| − | + | ==DNN based Language identification and Speaker identification== | |
* Xuewei Zhang/Zhiyuan Tang | * Xuewei Zhang/Zhiyuan Tang | ||
| − | + | ==Neural network visulization== | |
* Mian Wang,DONE | * Mian Wang,DONE | ||
| − | + | ==Dark knowledge== | |
* Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu | * Mengyuan Zhao, Xiangyu Zeng, Zhiyong Zhang, Chao Liu | ||
| − | + | ==Normal RNN speech recognition== | |
* Mengyuan Zhao | * Mengyuan Zhao | ||
| − | + | ==Monmentum-like Hessien-Free acceleration== | |
* Nestrov/Adagrad/AdaDelta/AdaM | * Nestrov/Adagrad/AdaDelta/AdaM | ||
* Zhiyong Zhang/Xiangyu Zeng | * Zhiyong Zhang/Xiangyu Zeng | ||
| − | + | ==Activation value normalization through time --Batch Normalization== | |
* Zhiyong Zhang | * Zhiyong Zhang | ||
| − | + | ==Mix-training Balance decision tree== | |
* Zhiyong Zhang | * Zhiyong Zhang | ||
| − | + | ==20-h Chinese data-set release== | |
* Xuewei Zhang | * Xuewei Zhang | ||
| − | + | ==Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method== | |
* nne3 test --Xuewei Zhang | * nne3 test --Xuewei Zhang | ||
2015年10月19日 (一) 12:00的版本
目录
- 1 Task To Do
- 1.1 Speech Recognition
- 1.1.1 End-to-End speech recognition
- 1.1.2 Multi-task
- 1.1.3 Integrate the class information to HCLG fst for speech recognition
- 1.1.4 Distant speech recognition
- 1.1.5 Voice conversation
- 1.1.6 Sparse DNN
- 1.1.7 Correlation based SENONE cluster
- 1.1.8 NN Multi-GPU parallel traing
- 1.1.9 Audio Embedding
- 1.1.10 RNN training accelerating
- 1.1.11 Data selection
- 1.1.12 Decoder
- 1.2 Speaker Verification
- 1.1 Speech Recognition
- 2 Task DONE
- 2.1 =Multi-Mode features based VAD
- 2.2 DNN based Language identification and Speaker identification
- 2.3 Neural network visulization
- 2.4 Dark knowledge
- 2.5 Normal RNN speech recognition
- 2.6 Monmentum-like Hessien-Free acceleration
- 2.7 Activation value normalization through time --Batch Normalization
- 2.8 Mix-training Balance decision tree
- 2.9 20-h Chinese data-set release
- 2.10 Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
- 3 Technical Report To Write
- 4 Paper to Write
- 5 Project
Task To Do
Speech Recognition
End-to-End speech recognition
- Discriminative-Learning code implementation
- Zhiyuan Tang
- Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang
Multi-task
- Fusion of speech-recognition and speech-rate
- Xiangyu Zeng
- Self-informed neural network structure learning
- Mengyuan Zhao
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
Sparse DNN
- Zhiyuan Tang
Correlation based SENONE cluster
NN Multi-GPU parallel traing
- Multi-Machine
- Sheng Su
- Multi-GPU on one Machine
- Sheng Su
- nnet3 code test
Audio Embedding
- Ke Ning
RNN training accelerating
Data selection
- Zhiyong Zhang
- Sub-modular data selection
- Objective-function loss training self-adaptation
Decoder
- Confidence output for task-required
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
Monmentum-like Hessien-Free acceleration
- Nestrov/Adagrad/AdaDelta/AdaM
- Zhiyong Zhang/Xiangyu Zeng
Activation value normalization through time --Batch Normalization
- Zhiyong Zhang
Mix-training Balance decision tree
- Zhiyong Zhang
20-h Chinese data-set release
- Xuewei Zhang
Unbound activation function(Rectifier/Maxout/Pnorm) go-through searching method
- nne3 test --Xuewei Zhang
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
