ASR:2015-04-13 - 版本历史

Zxw：/* Speech Processing */

2015-04-15T07:42:37Z

‎Speech Processing

Zxw：/* Speech Processing */

2015-04-15T06:41:46Z

‎Speech Processing

Lr：/* Text Processing */

2015-04-13T05:20:05Z

‎Text Processing

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

2015-04-13T01:23:44Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-11 often shut down automatically, too slow computation speed. ==== RNN AM==== * details...”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.

==== 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

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

==Text Processing==
===tag LM===
* similar word extension in FST
:* check the formula using Bayes and experiment
:* add more test data
:* 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 doc classification====
* reproducible test using English data
* Code new version spherical word vector.
* Accomplish movMF model

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

===Sparse NN in NLP===
* prepare the ACL
:* test result is ok now[http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344].
:* find the new direction.

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

===relation classifier===
* check code and find the problem that result is different on sigmoid and tanh

@@ 第4行： / 第4行： @@
 ==== Environment ====
 * grid-11 often shut down automatically, too slow computation speed.
-* add a server
+* add a server(760)
 ==== RNN AM====
@@ 第14行： / 第14行： @@
 ==== Mic-Array ====
 * investigate alpha parameter in time domian and frquency domain
-* ALPHA>=0
+* ALPHA>=0, using data generated by reverber toolkit
@@ 第28行： / 第29行： @@
 ===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
 :* train on wsj(testbase dev93+evl92)
 ==Text Processing==

@@ 第40行： / 第40行： @@
 ===tag LM===
 * similar word extension in FST
-:* check the formula using Bayes and experiment
+:* will check the formula using Bayes and experiment
-:* add more test data
+:* fixed the bug using the big-lm.
-:* test the baseline(no weight) and different weight method
+:* will add more test data
 ====RNN LM====
@@ 第50行： / 第51行： @@
 :* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
-====W2V based doc classification====
+====W2V based document classification====
-* reproducible test using English data
+* some result about VMF model [http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=353]
-* Code new version spherical word vector.
+* will try max-method
-* Accomplish movMF model
-−
 ===Translation===
 * v5.0 demo released
@@ 第60行： / 第59行： @@
 ===Sparse NN in NLP===
-* prepare the ACL
+* test the drop-out model and the performance gets a little improvement, need some result:
-:* test result is ok now[http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=lr&step=view_request&cvssid=344].
+* test the order feature
-:* find the new direction.
 ===online learning===
 * data is ready.prepare the ACL paper
 :* finish some test.
 :* test the result on different time.
 ===relation classifier===
-* check code and find the problem that result is different on sigmoid and tanh
+* modified the drop-out method