ASR:2015-06-29 - 版本历史

Xingchao：/* Text Processing */

2015-07-02T12:44:02Z

‎Text Processing

Zxw：/* Speech Processing */

2015-07-01T08:07:14Z

‎Speech Processing

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== grid-14 does not work --mengyuan grid-15 runs slowly ==== RNN AM==== *morpheme RNN --zhiyuan...”为内容创建页面

2015-06-29T01:18:54Z

以“==Speech Processing == === AM development === ==== Environment ==== *grid-14 does not work --mengyuan *grid-15 runs slowly ==== RNN AM==== *morpheme RNN --zhiyuan...”为内容创建页面

新页面

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

==== Environment ====
*grid-14 does not work --mengyuan
*grid-15 runs slowly

==== RNN AM====
*morpheme RNN --zhiyuan
*RNN MPE --zhiyuan and xuewei

==== Mic-Array ====
* hold
* compute EER with kaldi

====RNN-DAE(Deep based Auto-Encode-RNN)====
* hold
* deliver to mengyuan
:* http://cslt.riit.tsinghua.edu.cn/cgi-bin/cvss/cvss_request.pl?account=zhangzy&step=view_request&cvssid=261

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

===Ivector&Dvector based ASR===
* hold --Tian Lan
* Cluster the speakers to speaker-classes, then using the distance or the posterior-probability as the metric
* dark-konowlege using i-vector
* train on wsj(testbase dev93+evl92)
:*--hold

===Dark knowledge===
* test random last output layer when train MPE--zhiyuan

===language vector===
* hold --xuewei
* train using chinese and chiglish

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

====W2V based document classification====
* APSIPA paper
* CNN adapt to resolve the low resource problem
===Pair-wise LM===
* draft paper of journal

===Order representation ===
* modify the objective function(hold)
* sup-sampling method to solve the low frequence word(hold)
* journal paper

===binary vector===
* nips paper
===Stochastic ListNet===
*done

===relation classifier===
*done

===plan to do===
* combine LDA with neural network

@@ 第47行： / 第47行： @@
 :* check the lstm-rnnlm code about how to Initialize and update learning rate.(hold)
-====W2V based document classification====
+====Neural Based Document Classification====
-* APSIPA paper
+* (hold)
-* CNN adapt to resolve the low resource problem
-===Pair-wise LM===
-* draft paper of journal
 ===Order representation ===
 * modify the objective function(hold)
-* sup-sampling method to solve the low frequence word(hold)
+===Balance Representation===
-* journal paper
+* Find error signal
-===binary vector===
+===Recommendation===
-* nips paper
+* Reproduce baseline.
-===Stochastic ListNet===
-*done
-===relation classifier===
+===DSSM based QA===
-*done
+* Reproduce baseline.
-−
-===plan to do===
-* combine LDA with neural network

@@ 第3行： / 第3行： @@
 ==== Environment ====
-*grid-14 does not work --mengyuan
-*grid-15 runs slowly
 ==== RNN AM====
 *morpheme RNN --zhiyuan
-*RNN MPE --zhiyuan and xuewei
 ==== Mic-Array ====
 * hold
 * compute EER with kaldi
 ====RNN-DAE(Deep based Auto-Encode-RNN)====
@@ 第32行： / 第35行： @@
 ===Dark knowledge===
-* test random last output layer when train MPE--zhiyuan
+* test random last output layer when train MPE --zhiyuan
 ===language vector===
-* hold --xuewei
+* hold
-* train using chinese and chiglish
 ==Text Processing==

ASR:2015-06-29 - 版本历史

Xingchao：/* Text Processing */

Zxw：/* Speech Processing */

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== *grid-14 does not work --mengyuan *grid-15 runs slowly ==== RNN AM==== *morpheme RNN --zhiyuan...”为内容创建页面

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== grid-14 does not work --mengyuan grid-15 runs slowly ==== RNN AM==== *morpheme RNN --zhiyuan...”为内容创建页面