cslt Wiki - 用户贡献 [zh-cn]

Chao Liu 15-05-18

2015-05-19T11:48:16Z

Liuc：以“=== Accomplished this week === * refine thesis === Planned for next week === * prepare for presentation of thesis”为内容创建页面

=== Accomplished this week ===
* refine thesis

=== Planned for next week ===
* prepare for presentation of thesis

2015-05-17

2015-05-19T11:47:04Z

Liuc：

[[Miao Fan 15-05-17]]

[[Zhiyuan Tang 15-05-17]]

[[Chao Xing 15-05-17]]

[[Xiaoxi Wang 15-05-17]]

[[Mengyuan Zhao 15-05-17]]

[[Tianyi Luo 15-05-17]]

[[Rong Liu 15-05-17]]

[[Zhongwei Yao 15-05-17]]

[[Zhiyong Zhang 15-05-17]]

[[Xiangyu Zeng 15-05-17]]

[[Xuewei Zhang 15-05-17]]

[[Zipeng Ye 15-05-17]]

[[Lantian Li 15-05-18]]

[[Chao Liu 15-05-18]]

Chao Liu 15-04-20

2015-04-21T09:02:11Z

Liuc：以“=== Accomplished this week === * thesis * try RNN training with dark knowledge === Planned for next week === * thesis * cluster monitoring * plan for a report for...”为内容创建页面

=== Accomplished this week ===
* thesis
* try RNN training with dark knowledge

=== Planned for next week ===
* thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-04-20

2015-04-21T08:55:24Z

Liuc：

[[Mengyuan Zhao 15-04-20]]

[[Zipeng Ye 15-04-20]]

[[Dongxu Zhang 15-04-20]]

[[Zhiyuan Tang 15-04-20]]

[[Lantian Li 15-04-20]]

[[Rong Liu 15-04-20]]

[[Xi Ma 15-04-20]]

[[Tianyi Luo 15-04-20]]

[[Chao Liu 15-04-20]]

Weekly reading

2015-04-14T15:05:12Z

Liuc：

==报告==

*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recognition with Recurrent Neural Networks]

*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Weekly reading

2015-04-14T15:04:11Z

Liuc：

==报告==

*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recognition
with Recurrent Neural Networks]

*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Weekly reading

2015-04-14T15:03:55Z

Liuc：

==报告==
*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recognition
with Recurrent Neural Networks]

*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Weekly reading

2015-04-14T15:03:25Z

Liuc：

==报告==
*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf|刘超2015-03-11 Towards End-to-End Speech Recognition
with Recurrent Neural Networks]
*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Weekly reading

2015-04-14T15:03:12Z

Liuc：

==报告==
*[http://www.jmlr.org/proceedings/papers/v32/graves14.pdf 刘超2015-03-11 Towards End-to-End Speech Recognition
with Recurrent Neural Networks]
*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Weekly reading

2015-04-14T15:01:32Z

Liuc：

==报告==

*[[媒体文件:2015 Building DNN Acoustic Models for Large Vocabulary Speech Recognition.pdf|汤志远2015-3-18 - Building DNN Acoustic Models for Large Vocabulary Speech Recognition]]

*[[媒体文件:CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION.pdf|林一叶2015-4-1 - CONTRASTIVE AUTO-ENCODER FOR PHONEME RECOGNITION]]

*[[媒体文件:2014 speech dereverberation using weighted prediction error with laplacian model of the designed signal.pdf|张雪薇2015-4-1 - speech dereverberation using weighted prediction error with laplacian model of the designed signal]]

*[http://arxiv.org/pdf/1312.6184v7.pdf 王东2015-4-1 - Do Deep Nets Really Need to be Deep?]

*[http://arxiv.org/pdf/1503.02531v1.pdf 王东2015-4-1 - Distilling the Knowledge in a Neural Network]

*[[媒体文件:Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition.pdf|殷实2015-4-8 - Neural_Network_Acoustic_Models_with_Superviesed_Hidden_Layers_for_Automatic_Speech_Recognition]]

*[[媒体文件:Ensemble_Deep_Learning_for_Speech_Recognition.pdf|赵梦原2015-4-8 - Ensemble_Deep_Learning_for_Speech_Recognition]]

*[[媒体文件:An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment.pdf|曾翔宇2015-3-11 - An evaluation of target speech for a nonaudible murmur enhancement system in noisy enviroment]]

*[http://www.kecl.ntt.co.jp/icl/signal/hori/publications/thori_icassp2014.pdf 刘超2015-04-14 Real-time one-pass decoding with recurrent neural network language model for speech recognition]

Chao Liu 2015-04-13

2015-04-14T02:08:56Z

Liuc：以“=== Accomplished this week === * thesis * investigate dark knowledge === Planned for next week === * try dark knowledge * thesis * cluster monitoring * plan for a...”为内容创建页面

=== Accomplished this week ===
* thesis
* investigate dark knowledge

=== Planned for next week ===
* try dark knowledge
* thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-04-13

2015-04-14T02:07:46Z

Liuc：

[[Mengyuan Zhao 2015-04-13]]

[[Rong Liu 2015-04-13]]

[[Chao Xing 2015-04-13]]

[[Tianyi Luo 2015-04-13]]

[[Xiaoxi Wang 2015-04-13]]

[[Dongxu Zhang 2015-04-13]]

[[Zipeng Ye 2015-04-13]]

[[Xuewei Zhang 2015-04-13]]

[[Zhiyuan Tang 2015-04-13]]

[[Chao Liu 2015-04-13]]

Bi-monthly-2015-03

2015-04-09T04:49:07Z

Liuc：/* 报告 */

==小组总评==

*学术 8.64
*工作 8.71
*创新 7.86
*公平 9.07
*工资 8.29
==存在问题==
*GPU不足
*学术力量分散
*整个组多沟通学术
*服务器噪音太大
*方向多倾向于NLP

==个人评价==
[[bi-monthly-2015-03-result|result]]

==报告==

*[[媒体文件:Bi-monthly_report-2015-03.pdf|王东]]

*[[媒体文件:2015.01-03张雪薇季度总结.pdf|张雪薇]]

*[[媒体文件:TZY_20150331.pdf|汤志远]]

*[[媒体文件:个人双月总结-殷实150401.pdf|殷实]]

*[[媒体文件:Yiye_Lin双月3月.pdf|林一叶]]

*[[媒体文件:刘荣1-3月度总结.pdf|刘荣]]

*[[媒体文件:zhangzy_20150103.pdf|张之勇]]

*[[媒体文件:Liuc_201503.pdf|刘超]]

文件:Liuc 201503.pdf

2015-04-09T04:48:33Z

Liuc：

Chao Liu 2015-04-07

2015-04-08T05:06:10Z

Liuc：以“=== Accomplished this week === * prepare for the thesis === Planned for next week === * experiments on larger AM unit decoding * prepare for the thesis * cluster m...”为内容创建页面

=== Accomplished this week ===
* prepare for the thesis

=== Planned for next week ===
* experiments on larger AM unit decoding
* prepare for the thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-04-07

2015-04-08T05:05:43Z

Liuc：

[[Chao Xing 2015-04-07]]

[[Zhiyong Zhang 2015-04-07]]

[[Xiaoxi Wang 2015-04-07]]

[[Yiqiao Pan 2015-04-07]]

[[Xuewei Zhang 2015-04-7]]

[[Mengyuan Zhao 2015-04-07]]

[[Chao Liu 2015-04-07]]

Chao Liu 2015-03-30

2015-03-30T16:29:51Z

Liuc：以“=== Accomplished this week === * experiments on larger AM unit decoding * prepare for the thesis === Planned for next week === * experiments on larger AM unit deco...”为内容创建页面

=== Accomplished this week ===
* experiments on larger AM unit decoding
* prepare for the thesis

=== Planned for next week ===
* experiments on larger AM unit decoding
* prepare for the thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-03-30

2015-03-30T16:29:28Z

Liuc：

[[Chao Xing 2015-03-30]]

[[Mengyuan Zhao 2015-03-30]]

[[Xiangyu Zeng 2015-03-30]]

[[Rong Liu 2015-03-30]]

[[Shi Yin 2015-03-30]]

[[Fanhu Bie 2015-03-30]]

[[Xiaoxi Wang 2015-03-30]]

[[Tianyi Luo 2015-03-30]]

[[Zhiyong Zhang 2015-03-30]]

[[Xi Ma 2015-03-30]]

[[Lantian Li 2015-03-30]]

[[Zipeng ye 2015-03-30]]

[[Zhiyuan Tang 2015-03-30]]

[[Chao Liu 2015-03-30]]

Chao Liu 2015-03-23

2015-03-23T12:35:09Z

2015-03-23

2015-03-23T12:34:37Z

Liuc：

[[Rong Liu 2015-03-23]]

[[Xiaoxi Wang 2015-03-23]]

[[Mengyuan Zhao 2015-03-23]]

[[Shi Yin 2015-03-23]]

[[Zipeng Ye 2015-03-23]]

[[Dongxu Zhang 2015-03-23]]

[[Chao Liu 2015-03-23]]

ASR:2015-03-16

2015-03-18T07:27:05Z

Liuc：

==Speech Processing ==
=== AM development ===

==== Environment ====
* grid-11 often shut down automatically, too slow computation speed.
* GPU has being repired.--Xuewei

==== RNN AM====
* details at http://liuc.cslt.org/pages/rnnam.html
* tuning parameters on monophone NN

==== Mic-Array ====
* reproduce environment for interspeech
* investigate alpha parameter in Lasso

====Dropout & Maxout & rectifier ====
* HOLD
* Need to solve the too small learning-rate problem
* 20h small scale sparse dnn with rectifier. --Mengyuan
* 20h small scale sparse dnn with Maxout/rectifier based on weight-magnitude-pruning. --Mengyuan Zhao

====Convolutive network====
* HOLD
:* CNN + DNN feature fusion
:* reproduce experiments -- Yiye

====RNN-DAE(Deep based Auto-Encode-RNN)====
* HOLD -Zhiyong
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

====Speech rate training====
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
:* Technical report HOLD.-- Xiangyu Zeng, Shi Yin
:* Paper for NCMMSC done

====Neural network visulization====
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
* Technical report done --Mian Wang.

===Speaker ID===
:* DNN-based sid --Yiye
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

===Ivector based ASR===
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340
:* Ivector dimention is smaller, performance is better
:* Augument to hidden layer is better than input layer

==Text Processing==
===LM development===

====Domain specific LM====
* LM2.X
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
::* v2.0c filter the useless word.(next week)
::* set the test set for new word (hold)
:* prepare the wiki data: entity list.

====tag LM====
* Tag Lm(JT)
:* error check
* similar word extension in FST
:* repeat the experiment using same data

====RNN LM====
*rnn
:* the input and output is word embedding and add some token information like NER..
:* map the word to character and train the lm.
*lstm+rnn
:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

===Word2Vector===

====W2V based doc classification====
* data prepare.(hold)
====Knowledge vector====
* make a report on Monday

===Translation===

* v5.0 demo released
:* cut the dict and use new segment-tool

===Sparse NN in NLP===
* prepare the ACL
:* check the code to find the problem .
:* increase the dimension
:* use different test set.
===QA===
====improve fuzzy match====
* add Synonyms similarity using MERT-4 method(hold)
===online learning===
* data is ready.prepare the ACL paper
:* prepare sougouQ data and test it using current online learning method
====framework====
* extract the module
:* extract the context module ,search module,entity recognize module and common module.
:* define the inference in different modules
* composite module

====leftover problem====
* new inter will install SEMPRE

Chao Liu 2015-03-16

2015-03-17T00:14:56Z

Liuc：以“=== Accomplished this week === * experiments on larger AM unit decoding * prepare for the thesis === Planned for next week === * prepare for the thesis * cluster m...”为内容创建页面

=== Accomplished this week ===
* experiments on larger AM unit decoding
* prepare for the thesis

=== Planned for next week ===
* prepare for the thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-03-15

2015-03-17T00:13:55Z

Liuc：

[[Rong Liu 2015-03-15]]

[[Tianyi Luo 2015-03-15]]

[[Lantian Li 2015-03-16]]

[[Mengyuan Zhao 2015-03-16]]

[[Zipeng Ye 2015-03-16]]

[[Zhiyuan Tang 2015-03-16]]

[[Chao Liu 2015-03-16]]

150308-Chao Liu

2015-03-09T16:34:30Z

Liuc：以“=== Accomplished this week === * code & experiments on larger AM unit decoding === Planned for next week === * continue the exps * outline of the thesis * cluster...”为内容创建页面

=== Accomplished this week ===
* code & experiments on larger AM unit decoding

=== Planned for next week ===
* continue the exps
* outline of the thesis
* cluster monitoring
* plan for a report for RNN
* read papers

2015-03-08

2015-03-09T16:31:48Z

Liuc：

[[150308-Miao Fan]]

[[150308-Xi Ma]]

[[150308-Rong Liu]]

[[150308-Tianyi Luo]]

[[150308-Xiangyu Zeng]]

[[150308-Mengyuan Zhao]]

[[150308-Shi Yin]]

[[150308-Zipeng Ye]]

[[150308-Askar]]

[[150308-Zhiyong Zhang]]

[[150308-Zhiyuan Tang]]

[[150308-Lantian Li]]

[[150308-Chao Liu]]

ASR:2015-03-02

2015-03-06T07:25:31Z

Liuc：

==Speech Processing ==
=== AM development ===

==== Environment ====
* grid-11 often shutdown automatically, too slow computation speed.
* buy a new 800W power -- Xuewei

==== RNN AM====
* details at http://liuc.cslt.org/pages/rnnam.html
* triphone one state based RNN?

==== Mic-Array ====
* the technical report is done.
* reproduce environment for interspeech

====Dropout & Maxout & rectifier ====
* HOLD
* Need to solve the too small learning-rate problem
* 20h small scale sparse dnn with rectifier. --Chao liu
* 20h small scale sparse dnn with Maxout/rectifier based on weight-magnitude-pruning. --Mengyuan Zhao

====Convolutive network====
* Convolutive network(DAE)
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=311
:* Technical report writing, Mian Wang, Yiye Lin, Shi Yin, Mengyuan Zhao
:* reproduce experiments -- Yiye

====DNN-DAE(Deep Auto-Encode-DNN)====
* HOLD
* Technical report to draft, Xiangyu Zeng, Shi Yin, Mengyuan Zhao and Zhiyong Zhang,
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=318

====RNN-DAE(Deep based Auto-Encode-RNN)====
* HOLD
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

====VAD====
* DAE
* Technical report done. -- Shi Yin

====Speech rate training====
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=268
:* Technical report to draft. Xiangyu Zeng, Shi Yin
:* Prepare for NCMSSC

====Confidence====
* HOLD
* Reproduce the experiments on fisher dataset.
* Use the fisher DNN model to decode all-wsj dataset
* preparing scoring for puqiang data

====Neural network visulization====
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
* Technical report writing, Mian Wang.

===Speaker ID===
:* DNN-based sid
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

==Text Processing==
===LM development===

====Domain specific LM====
* LM2.X
:* mix the sougou2T-lm,kn-discount(done)
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
::* v2.0a adjust the weight and smaller weight of transcription is better.(done)
::* v2.0b add the v1.0 vocab(done)
::* v2.0c filter the useless word.(next week)
::* set the test set for new word (hold)

====tag LM====
* Tag Lm
:* add 3-class tag and test
* similar word extension in FST
:* improve the key-word weight in G , and result is good in keyword recognization
:* read to deal with the English-Chinese

====RNN LM====
*rnn
:* test wer RNNLM on Chinese data from jietong-data
:* generate the ngram model from rnnlm and test the ppl with different size txt.
*lstm+rnn
:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

===Word2Vector===

====W2V based doc classification====
* data prepare.
====Knowledge vector====
* paper is done, submitted ACL
====Character to word====
* Character to word conversion(hold)

====Word vector online learing====
* prepare the ACL

===Translation===

* v5.0 demo released
:* cut the dict and use new segment-tool

===Sparse NN in NLP===
* write a technical report(Wednesday) and make a report.
* ready to prepare the ACL

===QA===
====improve fuzzy match====
* add Synonyms similarity using MERT-4 method(hold)
====improve lucene search====
:* commit to Rong Liu to check in.
* online learning to rank
:* tool is ok and ready to test

===online learning===
*a simple edition about online learning part about QA.
====context framework====
* code for organization
:* change to knowledge graph,and learn the D2R tool and JENA[[媒体文件:政府组织机构图谱--汇联.pdf| 政府组织推演]] [[媒体文件:员工信息推演_知识图谱.pdf|员工信息实例推演]]
:* code for demo
::*
====query normalization====
* using NER to normalize the word

* new inter will install SEMPRE

Tools:shadowsocks

2015-03-04T14:50:37Z

Liuc：

'''警告：'''“Tools:shadowsocks”指向这里，但您没有足够的权限来访问它。

Tools:shadowsocks

2015-03-04T01:18:53Z

Liuc：

'''警告：'''“Tools:shadowsocks”指向这里，但您没有足够的权限来访问它。

Tools:shadowsocks

2015-03-02T13:01:48Z

Liuc：以“=== 实验室内 === 设置浏览器的自动代理设置地址为 http://liuc.cslt.org/proxy.pac === 自己连接 === * 下载shadowsocks客户端 http://sourcefor...”为内容创建页面

'''警告：'''“Tools:shadowsocks”指向这里，但您没有足够的权限来访问它。

Tools

2015-03-02T12:56:02Z

Liuc：

[[CVSS]]

[[goagent]]

[[Tools:shadowsocks|shadowsocks]]

Tools

2015-03-02T12:55:49Z

Liuc：

[[CVSS]]

[[goagent]]

[[shadowsocks|Tools:shadowsocks]]

Tools

2015-03-02T12:54:01Z

Liuc：

[[CVSS]]

[[goagent]]

[[Tools:shadowsocks]]

Tools

2015-03-02T12:53:51Z

Liuc：

[[CVSS]]

[[goagent]]

[[shadowsocks]]

Chao Liu 2015-02-09

2015-02-10T23:19:45Z

Liuc：以“=== Accomplished this week === * go to Tokyo for 6 days === Planned for next week === * experiments on lstm * cluster monitoring * plan for a report for RNN * read...”为内容创建页面

=== Accomplished this week ===
* go to Tokyo for 6 days

=== Planned for next week ===
* experiments on lstm
* cluster monitoring
* plan for a report for RNN
* read papers about RNN for AM

2015-02-09

2015-02-10T23:19:17Z

Liuc：

[[Rong Liu 2015-02-09]]

[[Xuewei Zhang 2015-02-09]]

[[Tianyi Luo 2015-02-09]]

[[Shi Yin 2015-02-09]]

[[Dongxu Zhang 2015-02-09]]

[[Mengyuan Zhao 2015-02-09]]

[[Fanhu Bie 2015-02-10]]

[[Yiye Lin 2015-02-09]]

[[Xi Ma 2015-02-09]]

[[Lantian Li 2015-02-10]]

[[Xiaoxi Wang 2015-02-10]]

[[Miao FAN 2015-02-09]]

[[Chao Liu 2015-02-09]]

Chao Liu 2014-02-02

2015-02-02T14:50:33Z

Liuc：以“=== Accomplished this week === * experiments on lstm === Planned for next week === * go to Tokyo for 6 days * experiments on lstm * cluster monitoring * plan for a...”为内容创建页面

=== Accomplished this week ===
* experiments on lstm

=== Planned for next week ===
* go to Tokyo for 6 days
* experiments on lstm
* cluster monitoring
* plan for a report for RNN
* read papers about RNN for AM

2015-02-02

2015-02-02T14:49:35Z

Liuc：

[[Mengyuan Zhao 2015-02-02]]

[[Dongxu Zhang 2014-02-02]]

[[Chao Liu 2014-02-02]]

Chao Liu 2015-01-26

2015-01-27T02:03:20Z

Liuc：以“=== Accomplished this week === * experiments on lstm * read papers about RNN for AM === Planned for next week === * experiments on lstm * cluster monitoring * plan...”为内容创建页面

=== Accomplished this week ===
* experiments on lstm
* read papers about RNN for AM

=== Planned for next week ===
* experiments on lstm
* cluster monitoring
* plan for a report for RNN
* read papers about RNN for AM

2015-01-26

2015-01-27T02:02:28Z

Liuc：

[[Lantian Li 2015-01-26]]

[[Rong Liu 2015-01-26]]

[[Zhongda Xie 2015-01-26]]

[[Miao Fan 2015-01-26]]

[[Xiaoxi Wang 2015-01-26]]

[[Bin Yuan 2015-01-26]]

[[Fanhu Bie 2015-01-26]]

[[Mengyuan Zhao 2015-01-26]]

[[Zhiyong Zhang 2015-01-26]]

[[Chao Liu 2015-01-26]]

Chao Liu 2015-01-19

2015-01-20T01:55:32Z

Liuc：以“=== Accomplished this week === * add time span info to decoder results for d-ear * experiments on OBD * experiments on lstm === Planned for next week === * experim...”为内容创建页面

=== Accomplished this week ===
* add time span info to decoder results for d-ear
* experiments on OBD
* experiments on lstm

=== Planned for next week ===
* experiments on lstm
* plan for a report for RNN
* read papers about RNN for AM
* cluster monitoring

2015-01-19

2015-01-20T01:54:00Z

Liuc：

[[Miao Fan 2015-01-17]]

[[2015-01-19 Rong Liu]]

[[Shi Yin 2015-01-19]]

[[Bin Yuan 2015-01-19]]

[[Zhongda Xie 2015-01-19]]

[[Xiaoxi Wang 2015-01-19]]

[[Dongxu Zhang 2015-01-19]]

[[Fanhu Bie 2015-01-19]]

[[Chao Liu 2015-01-19]]

Chao Liu 2015-01-12

2015-01-12T14:17:42Z

Liuc：以“=== Accomplished this week === * experiments on OBD * experiments on lstm * read papers about RNN for AM === Planned for next week === * experiments on lstm * plan...”为内容创建页面

=== Accomplished this week ===
* experiments on OBD
* experiments on lstm
* read papers about RNN for AM

=== Planned for next week ===
* experiments on lstm
* plan for a report for RNN
* read papers about RNN for AM
* cluster monitoring

2015-01-12

2015-01-12T14:16:37Z

Liuc：

[[Miao Fan 2015-01-12]]

[[Xiaoxi Wang 2015-01-12]]

[[Rong Liu 2015-01-12]]

[[Mengyuan Zhao 2015-01-12]]

[[Bin Yuan 2015-01-12]]

[[Zhiyong Zhang 2015-01-12]]

[[Chao Xing 2015-01-12]]

[[Fanhu Bie 2015-01-12]]

[[Askar 2015-01-12]]

[[Yiye Lin 2015-01-12]

[[Chao Liu 2015-01-12]]

Personal Status

2015-01-10T06:24:27Z

Liuc：

[[Zhiyong Zhang]]

[[Mian Wang]]

[[Yiye Lin]]

[[Mengyuan Zhao]]

[[Xiangyu Zeng]]

[http://liuc.cslt.org/pages/status.html Chao Liu]

Chao Liu 2015-01-05

2015-01-05T14:33:18Z

Liuc：以“=== Accomplished this week === * experiments on OBD * experiments on lstm * cluster monitoring * read papers about RNN for AM === Planned for next week === * exper...”为内容创建页面

=== Accomplished this week ===
* experiments on OBD
* experiments on lstm
* cluster monitoring
* read papers about RNN for AM

=== Planned for next week ===
* experiments on lstm
* plan for a report for RNN
* read papers about RNN for AM
* cluster monitoring

2015-01-05

2015-01-05T14:31:56Z

Liuc：

[[Rong Liu 2015-01-05]]

[[Fanhu Bie 2015-01-05]]

[[Lantian Li 2015-01-05]]

[[Dongxu Zhang 2015-01-05]]

[[Yiye Lin 2015-01-05]]

[[Chao Xing 2015-01-05]]

[[Miao Fan 2015-01-05]]

[[Chao Liu 2015-01-05]]

Bi-monthly-2015-01

2015-01-05T09:14:19Z

Liuc：

文件:Bimonth-201501-liuc.pdf

2015-01-05T09:13:41Z

Liuc：

Chao Liu 14-12-29

2014-12-29T16:26:26Z

Liuc：以“=== Accomplished this week === * some experiments on OBD * cluster monitoring * investigate using kaldi-lstm === Planned for next week === * continue experiments o...”为内容创建页面

=== Accomplished this week ===
* some experiments on OBD
* cluster monitoring
* investigate using kaldi-lstm

=== Planned for next week ===
* continue experiments on OBD
* experiments on kaldi-lstm
* cluster monitoring
* read papers about RNN for AM

2014-12-28

2014-12-29T16:25:18Z

Liuc：

[[Miao Fan 2014-12-28]]

[[Mengyuan Zhao 2014-12-28]]

[[Shi Yin 2014-12-28]]

[[Rong Liu 2014-12-28]]

[[Bin Yuan 2014-12-28]]

[[Xiaoxi Wang 2014-12-28]]

[[Dongxu Zhang 2014-12-28]]

[[Tianyi Luo 2014-12-28]]

[[Fanhu Bie 14-12-29]]

[[Zhongda Xie 14-12-29]]

[[Xiangyu Zeng 14-12-29]]

[[Chao Xing 14-12-29]]

[[Lantian Li 14-12-29]]

[[Yiye Lin 14-12-29]]

[[Chao Liu 14-12-29]]