ASR:2015-03-30 - 版本历史

Zxw：/* Speech Processing */

2015-04-01T05:39:40Z

‎Speech Processing

Lr：/* tag LM */

2015-03-30T08:36:33Z

‎tag LM

Lr：/* W2V based doc classification */

2015-03-30T08:35:53Z

‎W2V based doc classification

2015年3月30日 (一) 05:34 Lr

2015-03-30T05:34:42Z

Lr：/* LM development */

2015-03-30T05:29:45Z

‎LM development

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. * GPU has being repired.--X...”为内容创建页面

2015-03-30T05:29:21Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. * GPU has being repired.--X...”为内容创建页面

新页面

==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 ====
* investigate alpha parameter in time domian and frquency domain

====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
:* write paper for interspeech -- Xuewei

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

====Domain specific LM====
* LM2.X
:* train a large lm using 25w-dict.(hanzhenglong/wxx)
::* v2.0c filter the useless Chinese word and add 500 English word. get a little promotion effect.

====tag LM====
* Tag Lm(JT)
:* get new script from mx and test 1 tag lm
* similar word extension in FST
:* experiment done
:* write the paper

====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===

===online learning===
* data is ready.prepare the ACL paper
:* prepare sougouQ data and test it using current online learning method
====framework====
* extract the module
* composite module
* fix the bug
====leftover problem====
* new inter will install SEMPRE

@@ 第4行： / 第4行： @@
 ==== 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 ====
 * investigate alpha parameter in time domian and frquency domain
 ====Convolutive network====
 * HOLD
 :* CNN + DNN feature fusion
 ====RNN-DAE(Deep based Auto-Encode-RNN)====
@@ 第29行： / 第25行： @@
 * http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261
 ===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
@@ 第46行： / 第35行： @@
 :* Ivector dimention is smaller, performance is better
 :* Augument to hidden layer is better than input layer
-:* write paper for interspeech -- Xuewei
+:* train on wsj(testbase dev93+evl92)
 ==Text Processing==

@@ 第51行： / 第51行： @@
 ===tag LM===
 * similar word extension in FST
-:* check the formula using Bays and experiment
+:* check the formula using Bayes and experiment
 ====RNN LM====

@@ 第60行： / 第60行： @@
 ====W2V based doc classification====
-* data prepare.
+* corpus ready
+* learn some benchmark.
 ===Translation===
 * v5.0 demo released

@@ 第49行： / 第49行： @@
 ==Text Processing==
-===LM development===
+===tag LM===
-−
-====Domain specific LM====
-====tag LM====
-* Tag Lm(JT)
-:* get new script from mx and test 1 tag lm
 * similar word extension in FST
-:* experiment done
+:* check the formula using Bays and experiment
-:* write the paper
 ====RNN LM====
 *rnn
-:* the input and output is word embedding and add some token information like NER..
+:* code the character-lm using Theano
-:* 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)
 ====W2V based doc classification====
-* data prepare.(hold)
+* data prepare.
-====Knowledge vector====
-* make a report on Monday
-−
 ===Translation===
 * v5.0 demo released
 :* cut the dict and use new segment-tool
@@ 第82行： / 第70行： @@
 :* check the code to find the problem .
 :* increase the dimension
-:* use different test set.
+:* use different test set,but the result is not good.
-===QA===
 ===online learning===
 * data is ready.prepare the ACL paper
 :* prepare sougouQ data and test it using current online learning method
-====framework====
+:* baseline is not normal.
-* extract the module
-* composite module
-* fix the bug
-====leftover problem====
-* new inter will install SEMPRE