ASR:2015-07-20 - 版本历史

Zxw：/* Speech Processing */

2015-07-22T08:20:30Z

‎Speech Processing

Xingchao：/* Image Baseline */

2015-07-20T01:56:53Z

‎Image Baseline

Xingchao：/* Image Baseline */

2015-07-20T01:56:37Z

‎Image Baseline

Xingchao：/* RNN Poem Process */

2015-07-20T01:54:21Z

‎RNN Poem Process

Xingchao：/* Text Processing */

2015-07-20T01:47:50Z

‎Text Processing

Xingchao：/* DSSM based QA */

2015-07-20T01:43:31Z

‎DSSM based QA

Xingchao：/* Text Group Intern Project */

2015-07-20T00:56:46Z

‎Text Group Intern Project

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== * the GPU of grid-14 does not work ==== RNN AM==== hold morpheme RNN --zhiyuan *train using...”为内容创建页面

2015-07-20T00:56:14Z

以“==Speech Processing == === AM development === ==== Environment ==== * the GPU of grid-14 does not work ==== RNN AM==== *hold *morpheme RNN --zhiyuan *train using...”为内容创建页面

新页面

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

==== Environment ====
* the GPU of grid-14 does not work

==== RNN AM====
*hold
*morpheme RNN --zhiyuan
*train using large dataset--mengyuan

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

====Data selection unsupervised learning
* 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

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

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

===rectifier===
* hold
* WER performs worse using auraro4 --zhiyuan
* train using other dataset
* rectifier RNN

==audio embedding===
* audio ebedding --Wei Xu

==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)

====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.
====Seq to Seq(09-15)====
:* Review papers.(Reported in 07-08)
* Reproduce baseline.

===Text Group Intern Project===
:*====Buddhist Process====
(hold)
====RNN Poem Process====
(hold)
====RNN Document Vector====
(hold)
====Image Baseline====
:*Demo Release.
:*Paper Report.

@@ 第96行： / 第96行： @@
 :*Demo Release.
 :*Paper Report.
-*CNN Paper.
+*Read CNN Paper.

←上一版本		2015年7月20日 (一) 01:56的版本
第96行：		第96行：
	:*Demo Release.		:*Demo Release.
	:*Paper Report.		:*Paper Report.
		+	*CNN Paper.

@@ 第77行： / 第77行： @@
 :* Demo Release.(English done.)
 *Chinese Model start.
 ====Seq to Seq(09-15)====

@@ 第3行： / 第3行： @@
 ==== Environment ====
-* the GPU of grid-14 does not work
+* grid-14 is on reparation
 ==== RNN AM====
 *hold
 *morpheme RNN --zhiyuan
-*train using large dataset--mengyuan
+*train using 1400h large dataset--mengyuan
 ==== Mic-Array ====
@@ 第15行： / 第17行： @@
 ====Data selection unsupervised learning
 * acoustic feature based submodular using Pinan dataset --zhiyong
 * write code to speed up --zhiyong
@@ 第37行： / 第40行： @@
 ===Dark knowledge===
 * test random last output layer when train MPE --zhiyuan,mengyuan
@@ 第42行： / 第46行： @@
 ===language vector===
 * train using language vector with the dataset of 1400h_CN + 100h_EN--mengyuan
 * write a paper--zhiyuan
 ===rectifier===
 * hold
 * rectifier RNN
 ==audio embedding===

@@ 第89行： / 第89行： @@
 (hold)
 ====RNN Poem Process====
-(hold)
+*Read Paper & Source Code.
 ====RNN Document Vector====
 (hold)

@@ 第81行： / 第81行： @@
 ===Text Group Intern Project===
-:*====Buddhist Process====
+====Buddhist Process====
 (hold)
 ====RNN Poem Process====

ASR:2015-07-20 - 版本历史

Zxw：/* Speech Processing */

Xingchao：/* Image Baseline */

Xingchao：/* Image Baseline */

Xingchao：/* RNN Poem Process */

Xingchao：/* Text Processing */

Xingchao：/* DSSM based QA */

Xingchao：/* Text Group Intern Project */

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== * the GPU of grid-14 does not work ==== RNN AM==== *hold *morpheme RNN --zhiyuan *train using...”为内容创建页面

Xingchao：以“==Speech Processing == === AM development === ==== Environment ==== * the GPU of grid-14 does not work ==== RNN AM==== hold morpheme RNN --zhiyuan *train using...”为内容创建页面