2015年10月26日 (一) 07:35的版本 （查看源代码） Zhaomy（讨论 | 贡献） （→‎End-to-End speech recognition） ←上一编辑		2015年10月26日 (一) 07:59的版本 （查看源代码） Zhaomy（讨论 | 贡献） 下一编辑→
第12行：		第12行：
	===Integrate the class information to HCLG fst for speech recognition===		===Integrate the class information to HCLG fst for speech recognition===
		+	*zhiyuan
	===Distant speech recognition===		===Distant speech recognition===
第21行：		第22行：
	===Voice conversation===		===Voice conversation===
		+	*hold
	===Sparse DNN===		===Sparse DNN===
第28行：		第30行：
	===NN Multi-GPU parallel traing===		===NN Multi-GPU parallel traing===
−	*Multi-Machine	+	*Multi-GPU using data parallelization
	:*Sheng Su		:*Sheng Su
−	*Multi-GPU on one Machine	+	* nnet3 mpe
−	:*Sheng Su	+	:* Xuewei Zhang
−	* nnet3 code test	+
	===Audio Embedding===		===Audio Embedding===
第99行：		第100行：
	=Paper to Write=		=Paper to Write=
		+
		+	=Patent done=
		+	* A method of new word enhancement for speech recognition --Yue Zhang
	=Project=		=Project=
第104行：		第108行：
	:*Mengyuan Zhao/Zhiyong Zhang		:*Mengyuan Zhao/Zhiyong Zhang
	:*TAG-lm & Domain-specific general lm		:*TAG-lm & Domain-specific general lm
−
	*Chinese-English mix-training		*Chinese-English mix-training

---

2015年10月26日 (一) 07:59的版本

Task To Do

Speech Recognition

End-to-End speech recognition

• Discriminative-Learning code implementation

• Zhiyuan Tang

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

• zhiyuan

Distant speech recognition

• RNN-DAE: echo or reverberation

• Xuewei Zhang/Zhiyuan Tang/Mengyuan Zhao/Zhiyong Zhang

• Reverberation

• Mutli-microphones
• (Lasso),Xuewei Zhang

Voice conversation

• hold

Sparse DNN

• Zhiyuan Tang

Correlation based SENONE cluster

NN Multi-GPU parallel traing

• Multi-GPU using data parallelization

• Sheng Su

• nnet3 mpe

• Xuewei Zhang

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

Patent done

• A method of new word enhancement for speech recognition --Yue Zhang

Project

• Xiaomi TV

• Mengyuan Zhao/Zhiyong Zhang
• TAG-lm & Domain-specific general lm

• Chinese-English mix-training