ASR:2015-03-09 - 版本历史

Lr：/* Text Processing */

2015-03-16T01:11:16Z

‎Text Processing

2015年3月11日 (三) 07:26 Zxw

2015-03-11T07:26:56Z

Zxw：/* Speech Processing */

2015-03-10T12:11:33Z

‎Speech Processing

Lr：/* Knowledge vector */

2015-03-09T06:16:28Z

‎Knowledge vector

Lr：/* Domain specific LM */

2015-03-09T06:13:17Z

‎Domain specific LM

Lr：/* Sparse NN in NLP */

2015-03-09T06:11:42Z

‎Sparse NN in NLP

Lr：/* Sparse NN in NLP */

2015-03-09T06:11:15Z

‎Sparse NN in NLP

Lr：/* tag LM */

2015-03-09T06:10:47Z

‎tag LM

Lr：/* Text Processing */

2015-03-09T06:10:08Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shutdown automatically, too slow computation speed. * buy a new 800W power -- Xu...”为内容创建页面

2015-03-09T01:14:24Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shutdown automatically, too slow computation speed. * buy a new 800W power -- Xu...”为内容创建页面

新页面

==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

@@ 第72行： / 第72行： @@
 ====tag LM====
 * Tag Lm(JT)
-:* error
+:* error check
 * similar word extension in FST
 :* add the experiment to tag-lm paper.

@@ 第57行： / 第57行： @@
 ====Domain specific LM====
 * LM2.X
 :* train a large lm using 25w-dict.(hanzhenglong/wxx)
 ::* v2.0c filter the useless word.(next week)
@@ 第71行： / 第70行： @@
 ====RNN LM====
 *rnn
-:* discuss the rnn-lstm lm
+:* the input and output is word embedding and add some token information like NER..
 *lstm+rnn
 :* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
@@ 第89行： / 第89行： @@
 ===Sparse NN in NLP===
 * prepare the ACL
+:* check the code to find the problem .
 ===QA===
 ====improve fuzzy match====
@@ 第95行： / 第97行： @@
 ===online learning===
 * data is ready.prepare the ACL paper
-====context framework====
+:* prepare sougouQ data and test it using current online learning method
-* code for demo
+====framework====
-:* demo is done
+* extract the module
+:* extract the context module ,search module,entity recognize module and common module.
 * new inter will install SEMPRE

@@ 第3行： / 第3行： @@
 ==== Environment ====
-* grid-11 often shutdown automatically, too slow computation speed.
+* grid-11 often shut down automatically, too slow computation speed.
-* buy a new 800W power -- Xuewei
+* GPU has being repired.--Xuewei
 ==== RNN AM====
 * details at http://liuc.cslt.org/pages/rnnam.html
-* triphone one state based RNN?
+* triphone one state based RNN ?--Liu Chao
 ==== Mic-Array ====
 * 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 rectifier. --Mengyuan
 * 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
+* HOLD
 :* Technical report writing, Mian Wang, Yiye Lin, Shi Yin, Mengyuan Zhao
 :* reproduce experiments -- Yiye
@@ 第32行： / 第32行： @@
 ====RNN-DAE(Deep based Auto-Encode-RNN)====
-* HOLD
+* 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 to draft. Xiangyu Zeng, Shi Yin
+:* Technical report to draft.-- Xiangyu Zeng, Shi Yin
 :* Prepare for NCMSSC
 ====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.
+* Technical report writing --Mian Wang.
 ===Speaker ID===
-:* DNN-based sid
+:* DNN-based sid --Yiye
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
 ==Text Processing==

@@ 第88行： / 第88行： @@
 * data prepare.(hold)
 ====Knowledge vector====
-* paper is done, submitted ACL
+* make a report on Monday
 ===Translation===

@@ 第94行： / 第94行： @@
 ===Sparse NN in NLP===
-* write a technical report(Wednesday) and make a report.
+* make a report.
 * ready to prepare the ACL