ASR:2015-08-03 - 版本历史

Lr：/* display platform */

2015-08-10T04:13:17Z

‎display platform

Lr：/* strategy */

2015-08-10T04:12:36Z

‎strategy

Lr：/* financial group */

2015-08-03T12:38:32Z

‎financial group

2015年8月3日 (一) 11:35 Lr

2015-08-03T11:35:36Z

Zxw：/* Speech Processing */

2015-08-03T07:24:11Z

‎Speech Processing

2015年8月3日 (一) 02:44 Xingchao

2015-08-03T02:44:56Z

Xingchao：/* Text Processing */

2015-08-03T02:04:28Z

‎Text Processing

2015年8月3日 (一) 01:35 Xingchao

2015-08-03T01:35:34Z

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== * grid-14 is on repairation * prepare to buy a server ==== RNN AM==== hold morpheme RNN --z...”为内容创建页面

2015-08-03T01:32:37Z

以“==Speech Processing == === AM development === ==== Environment ==== * grid-14 is on repairation * prepare to buy a server ==== RNN AM==== *hold *morpheme RNN --z...”为内容创建页面

新页面

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

==== Environment ====
* grid-14 is on repairation
* prepare to buy a server

==== RNN AM====
*hold
*morpheme RNN --zhiyuan
*train using 1400h large dataset--mengyuan
*write code to tune learning rate--mengyuan

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

====Data selection unsupervised learning
* hold
* acoustic feature based submodular using Pinan dataset --zhiyong
* write code to speed up --zhiyong

====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

===language vector===
* hold
* train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
:* hold
* write a paper--zhiyuan
* RNN language vector
* train as a paper--xuewei

===rectifier===
* hold
* rectifier RNN --zhiyuan

===monophone===
* hold
* triphone is tranfered to monophone

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

====Neural Based Document Classification====
* (hold)

====RNN Rank Task====
* (hold)

====RNN Word Segment====
* (hold)

====Seq to Seq(09-15)====
* Review papers.
* Reproduce baseline. (08-03)

====Order representation ====
* Nested Dropout
:*semi-linear --> neural based auto-encoder.
* modify the objective function(hold)
====Balance Representation====
* Find error signal

====Recommendation====
* Reproduce baseline.
:*LDA matrix dissovle.
:* LDA (Text classification & Recommendation System) --> AAAI

====DSSM based QA====
:* Demo Release.(English done.)
*Chinese Model start.

====RNN based QA====
*Read Source Code.

===Text Group Intern Project===
====Buddhist Process====
(hold)
====RNN Poem Process====
*Read Paper & Source Code.

====RNN Document Vector====
(hold)
====Image Baseline====
:*Demo Release.
:*Paper Report.
*Read CNN Paper.

=financial group=
===world quant===
* websim(done)
:* learn the websim and test several alpha
:* submit the alpha

===tonglian platform===
* learn the platform
:* test the alpha in tonglian platform
:* verify the Theano in tonglian

===strategy===
* ml strategy
:* ml method
* optimize the strategy
:* optimize the model
* classical strategy
:*

←上一版本		2015年8月10日 (一) 04:13的版本
第128行：		第128行：

	===display platform===		===display platform===
−	* ~~transplant~~ the ~~algorithm~~	+	* set up the test platform in our grid

@@ 第121行： / 第121行： @@
 ===strategy===
 * rule optimize model
-:*
+:* Adaboost method
 * technology  index
 :* survey the current technology index

@@ 第122行： / 第122行： @@
 * rule optimize model
 :*
-* technology
+* technology  index
 * NN
 :* RNN model using Theano

←上一版本		2015年8月3日 (一) 02:44的版本
第113行：		第113行：
	* (Hold)		* (Hold)

−	~~====~~

	=financial group=		=financial group=

@@ 第110行： / 第110行： @@
 ====Trace Learning====
 * (Hold)
 ====

@@ 第115行： / 第115行： @@
 =financial group=
 ===tonglian platform===
 * learn the platform
-:* test the alpha in tonglian platform
+:* arma,ar,boosting tree is done
-:* verify the Theano in tonglian
 ===strategy===
-* ml strategy
+* rule optimize model
-:* ml method
+:*
-* optimize the strategy
+* technology
-:* optimize the model
+* NN
-* classical strategy
+:* RNN model using Theano
 :*

@@ 第11行： / 第11行： @@
 *morpheme RNN --zhiyuan
 *train using 1400h large dataset--mengyuan
-*write code to tune learning rate--mengyuan
+*write code to tune learning rate
 ==== Mic-Array ====

@@ 第106行： / 第106行： @@
 :*Paper Report.
 *Read CNN Paper.
 =financial group=