ASR:2015-04-20 - 版本历史

Zhangzy：/* Dark knowledge */

2015-04-22T08:49:29Z

‎Dark knowledge

2015年4月22日 (三) 08:48 Zhangzy

2015-04-22T08:48:43Z

2015年4月22日 (三) 08:47 Zhangzy

2015-04-22T08:47:56Z

Lr：/* Sparse NN in NLP */

2015-04-20T04:47:39Z

‎Sparse NN in NLP

Lr：/* Sparse NN in NLP */

2015-04-20T04:46:39Z

‎Sparse NN in NLP

Lr：/* W2V based document classification */

2015-04-20T04:42:43Z

‎W2V based document classification

Lr：/* online learning */

2015-04-20T04:42:19Z

‎online learning

Lr：/* Text Processing */

2015-04-20T04:40:45Z

‎Text Processing

Lr：以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. * add a server(760) ==== R...”为内容创建页面

2015-04-20T01:22:15Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. * add a server(760) ==== R...”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.
* add a server(760)

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

==== Mic-Array ====
* investigate alpha parameter in time domian and frquency domain
* ALPHA>=0, using data generated by reverber toolkit
* consider theta

====Convolutive network====
* HOLD
* CNN + DNN feature fusion

====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

===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===
*hold
:* 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
:* train on wsj(testbase dev93+evl92)

===Dark knowledge===
:*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --zhiyong
:* trial on logit matching faild --mengyuan
:* adaptation for chinglish under investigation-mengyuan
:* unsupervised training with wsj contributes to aurora4 model--xiangyu
:* test large database with amida--xiangyu

===bilingual recognition===
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359--zhiyuan

==Text Processing==
===tag LM===
* similar word extension in FST
:* will check the formula using Bayes and experiment
:* fixed the bug using the big-lm.
:* will add more test data
:* will test the baseline(no weight) and different weight method

====RNN LM====
*rnn
:* code the character-lm using Theano
*lstm+rnn
:* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)

====W2V based document classification====
* some result about VMF model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=353]
* will try max-method
===Translation===
* v5.0 demo released
:* cut the dict and use new segment-tool

===Sparse NN in NLP===
* test the drop-out model and the performance gets a little improvement, need some result:
* test the order feature

===online learning===
* data is ready.prepare the ACL paper
:* modified the listNet SGD
:* finish some test.
:* test the result on different time.

===relation classifier===
* modified the drop-out method

@@ 第37行： / 第37行： @@
 :* Ensemble
 ::*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang
-:* adaptation for chinglish under investigation  -- Mengyuan Zhao
+:* adaptation for chinglish under investigation  --Mengyuan Zhao
 ::* Try to improve the chinglish performance extremly
 :* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
 ::* test large database with AMIDA
 ===bilingual recognition===

@@ 第36行： / 第36行： @@
 ===Dark knowledge===
 :* Ensemble
-   http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang
+::*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang
 :* adaptation for chinglish under investigation  -- Mengyuan Zhao
 ::* Try to improve the chinglish performance extremly

@@ 第72行： / 第72行： @@
 * test the order feature ,need some result:
 * large dimension result:http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344
-:* sparse-nn on 1000 dimension(le-6,0.71) is better than 200 dimension(le-12,0.69).
+:* sparse-nn on 1000 dimension(le-6,0.705236) is better than 200 dimension(le-12,0.694678).
 ===online learning===

@@ 第72行： / 第72行： @@
 * test the order feature ,need some result:
 * large dimension result:http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344
 ===online learning===

@@ 第61行： / 第61行： @@
 ====W2V based document classification====
-* result about VMF model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=355]
+* result about norm model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=355]
-* reproduce the
 * try CNN model
 ===Translation===
 * v5.0 demo released

@@ 第4行： / 第4行： @@
 ==== Environment ====
 * grid-11 often shut down automatically, too slow computation speed.
-* add a server(760)
+* New grid-13 added, using gpu970
 ==== RNN AM====
 * details at http://liuc.cslt.org/pages/rnnam.html
-* tuning parameters on monophone NN
+* Test monophone on RNN using dark-knowledge
 * run using wsj,MPE
 ==== Mic-Array ====
 * investigate alpha parameter in time domian and frquency domain
 * ALPHA>=0, using data generated by reverber toolkit
 * consider theta
 ====RNN-DAE(Deep based Auto-Encode-RNN)====
-* HOLD -Zhiyong
+* HOLD --Zhiyong Zhang
 * 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
+:* DNN-based sid --Yiye Lin
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=327
-===Ivector based ASR===
+===Ivector&Dvector based ASR===
-*hold
+:* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
 :* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?step=view_request&cvssid=340
 :* Ivector dimention is smaller, performance is better
@@ 第39行： / 第35行： @@
 ===Dark knowledge===
-:*http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --zhiyong
+:* Ensemble
-:* trial on logit matching faild --mengyuan
+   http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=264 --Zhiyong Zhang
-:* adaptation for chinglish under investigation-mengyuan
+:* adaptation for chinglish under investigation  -- Mengyuan Zhao
-:* unsupervised training with wsj contributes to aurora4 model--xiangyu
+::* Try to improve the chinglish performance extremly
-:* test large database with amida--xiangyu
+:* unsupervised training with wsj contributes to aurora4 model --Xiangyu Zeng
 ===bilingual recognition===
-:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359--zhiyuan
+:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zxw&step=view_request&cvssid=359 --Zhiyuan Tang
 ==Text Processing==

@@ 第74行： / 第74行： @@
 ===online learning===
-* data is ready.prepare the ACL paper
+* modified the listNet SGD
-:* modified the listNet SGD
 ===relation classifier===
 * check the CNN code and contact the author of paper

@@ 第52行： / 第52行： @@
 * similar word extension in FST
 :* will check the formula using Bayes and experiment
-:* fixed the bug using the big-lm.
+:* add similarity weight
-:* will add more test data
-:* will test the baseline(no weight) and different weight method
 ====RNN LM====
 *rnn
-:* code the character-lm using Theano
+:* test the ppl and code the character-lm
 *lstm+rnn
 :* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
 ====W2V based document classification====
-* some result about VMF model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=353]
+* result about VMF model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=355]
-* will try max-method
+* reproduce the
 ===Translation===
 * v5.0 demo released
@@ 第71行： / 第70行： @@
 ===Sparse NN in NLP===
 * test the drop-out model and the performance gets a little improvement, need some result:
-* test the order feature
+* test the order feature ,need some result:
 ===online learning===
 * data is ready.prepare the ACL paper
 :* modified the listNet SGD
 ===relation classifier===
-* modified the drop-out method
+* check the CNN code and contact the author of paper