ASR:2015-02-02 - 版本历史

2015年2月6日 (五) 06:52 Zhangzy

2015-02-06T06:52:59Z

Lr：/* QA */

2015-02-03T01:43:56Z

‎QA

Lr：/* improve lucene search */

2015-02-03T01:43:07Z

‎improve lucene search

Lr：/* Text Processing */

2015-02-03T01:06:09Z

‎Text Processing

Lr：/* tag LM */

2015-02-02T11:48:26Z

‎tag LM

Lr：/* Text Processing */

2015-02-02T11:47:33Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 has been repairing. * grid-11 often shutdown automatically, too slow com...”为内容创建页面

2015-02-02T11:16:42Z

以“==Speech Processing == === AM development === ==== Environment ==== * May gpu760 of grid-14 has been repairing. * grid-11 often shutdown automatically, too slow com...”为内容创建页面

新页面

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

==== Environment ====
* May gpu760 of grid-14 has been repairing.
* grid-11 often shutdown automatically, too slow computation speed.

==== RNN AM====
* details at http://liuc.cslt.org/pages/rnnam.html

====Dropout & Maxout & rectifier ====
* 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 to draft, Mian Wang, Yiye Lin, Shi Yin, Mengyuan Zhao

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

====VAD====
* DAE
* Technical report --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. Shi Yin
:* Prepare for ChinaSIP

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

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

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

===Language ID===
* GMM-based language is ready.
* Delivered to Jietong
* Prepare the test-case
* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=328

===Voice Conversion===
* Yiye is reading materials
* HOLD

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

====Domain specific LM====
* LM2.1
:* mix the sougou2T-lm,kn-discount continue
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
::* add more data including poi, document information.
::* add v1.0 vocab and filter the useless word
::* set the test set

====tag LM====
* Tag Lm
:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
* similar word extension in FST
:* write a draft of a paper
:* result :16.32->10.23
====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====
* Knowledge vector
:* run the big data
:* prepare the paper.
* result
====Character to word====
* Character to word conversion(hold)
===Translation===

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

===Sparse NN in NLP===
* write a technical report

===QA===
====improve fuzzy match====
* add Synonyms similarity using MERT-4 method(hold)
====improve lucene search====
:* add more feature to improve search.
::* POS, NER ,tf ,idf ..
:* extract more features about lexical, syntactic and semantic to improve re-ranking performance.
:* using sentence vector
====context framework====
* code for organization
:* change to knowledge graph

====query normalization====
* using NER to normalize the word

* new inter will install SEMPRE

@@ 第114行： / 第114行： @@
 :* Optimize the code about extracting features and reranking and commit to Rong Liu to check in.
 :* using sentence vector, it doesn't work.
+===online learning===
 ====context framework====
 * code for organization

@@ 第8行： / 第8行： @@
 ==== RNN AM====
 * details at http://liuc.cslt.org/pages/rnnam.html
 ====Dropout & Maxout & rectifier ====
@@ 第13行： / 第16行： @@
 * 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====
@@ 第29行： / 第33行： @@
 ====VAD====
 * DAE
-* Technical report --Shi Yin
+:* HOLD
 ====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. Shi Yin
+:* Technical report to draft. Xiangyu Zeng, Shi Yin
 :* Prepare for ChinaSIP
@@ 第43行： / 第48行： @@
 ====Neural network visulization====
-:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
+* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=324
 ===Speaker ID===
@@ 第49行： / 第55行： @@
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327

@@ 第111行： / 第111行： @@
 :* add more feature to improve search.
 ::* POS, NER ,tf ,idf
-::* result:P@1:  0.68734335-->0.7763158   1097-->1239 (The number of queries is 1596.)P@5:  0.80325814-->0.8383459   1282-->1338 (The number of queries is 1596.)[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Huilan-learning-to-rank]
+::* result:P@1:  0.68734335-->0.7763158P@5:  0.80325814-->0.8383459 [http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/Huilan-learning-to-rank]
-:* extract more features about lexical, syntactic and semantic to improve re-ranking performance.
+:* Optimize the code about extracting features and reranking and commit to Rong Liu to check in.
 :* using sentence vector, it doesn't work.
 ====context framework====
 * code for organization

@@ 第77行： / 第77行： @@
 * similar word extension in FST
 :* write a draft of a paper
-:* result (need result)
+:* result [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=mx&step=view_request&cvssid=332]
 ====RNN LM====

@@ 第64行： / 第64行： @@
 ====Domain specific LM====
-* LM2.1
+* LM2.X
 :* mix the sougou2T-lm,kn-discount continue
 :* train a large lm using 25w-dict.(hanzhenglong/wxx)
-::* add more data including poi, document information.
+::* v2.0a adjust the weight and smaller weight of transportation is better.(done)
-::* add v1.0 vocab and filter the useless word
+::* v2.0b add the v1.0 vocab(this week)
-::* set the test set
+::* v2.0c filter the useless word.(next week)
 ====tag LM====
 * Tag Lm
-:* tag Probability should test add the weight(hanzhenglong) and handover to hanzhenglong ("this month")
+:* code is given to jietong .
 * similar word extension in FST
 :* write a draft of a paper
@@ 第89行： / 第90行： @@
 * data prepare.
 ====Knowledge vector====
-* Knowledge vector
+* run the big data
-:* run the big data
+:* continue to test, including paragraph vector and relation.
-:* prepare the paper.
+:* result: http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=326
-* result
+* prepare the paper.
 ====Character to word====
 * Character to word conversion(hold)
@@ 第101行： / 第102行： @@
 ===Sparse NN in NLP===
-* write a technical report
+* write a technical report(Wednesday) and make a repoert.
 ===QA===
@@ 第108行： / 第109行： @@
 ====improve lucene search====
 :* add more feature to improve search.
-::* POS, NER ,tf ,idf ..
+::* POS, NER ,tf ,idf
 :* extract more features about lexical, syntactic and semantic to improve re-ranking performance.
-:* using sentence vector
+:* using sentence vector, it doesn't work.
 ====context framework====
 * code for organization
-:* change to knowledge graph
+:* change to knowledge graph,and learn the D2R tool and JENA
 ====query normalization====